# knowledge-management

Knowledge management is the systematic discipline and process of capturing, organizing, sharing, and applying organizational knowledge, supported by technical infrastructure such as repositories, search platforms, and information systems engineering.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem

DevFeed: [Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem](<https://devfeed.tech/articles/democratizing-cross-project-knowledge-for-transforming-water-governance-and-climate-resilience-an-agentic-ai-ecosystem-145666.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26398>)

Author: Oriol Al\\\`as, Ian Palac\\'in, Iv\\'an Cester, Edgar Rubi\\'on

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [information retrieval](<https://devfeed.tech/topics/information-retrieval.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [budget](<https://devfeed.tech/tags/budget.md>), [climate](<https://devfeed.tech/tags/climate.md>), [collections](<https://devfeed.tech/tags/collections.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [data](<https://devfeed.tech/tags/data.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [ecosystem](<https://devfeed.tech/tags/ecosystem.md>), [governance](<https://devfeed.tech/tags/governance.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [water](<https://devfeed.tech/tags/water.md>)

### AI overview

The paper presents an agentic retrieval system for finding evidence across EU-funded water and climate projects. It organizes documents from IMPETUS, NATALIE, and InnWater into hierarchical section trees with structured metadata, then uses separate water- and climate-domain embedding models. A ReAct-style controller allocates retrieval budget across domain collections and gathers evidence until a stopping criterion is met. In a benchmark on this corpus, the approach improved Mean Reciprocal Rank by 26.7% relative to a single-domain embedding baseline. The excerpt does not describe evaluation beyond that retrieval benchmark.

### Source excerpt

arXiv:2611.26398v1 Announce Type: cross Abstract: EU-funded projects produce extensive evidence in the form of deliverables, reports, and case studies. However, this knowledge is typically scattered across projects and document structures, making it difficult to locate relevant, contextual information when making decisions. This paper introduces an Agentic AI Ecosystem that consolidates heterogeneous project documentation into a domain-aware knowledge base and provides adaptive access through an agentic Retrieval-Augmented Generation pipeline. Documents from three EU-funded projects (IMPETUS, NATALIE, and InnWater) are reconstructed into hierarchical section trees and indexed with structured metadata. Retrieval is supported by two domain-specific embedding models fine-tuned on domain data (water and climate). On top of this knowledge base, a ReAct-style controller iteratively orchestrates retrieval actions by allocating retrieval budget across domain collections and accumulating evidence until a stopping criterion is met. In a retrieval benchmark over the corpus, the proposed approach improves Mean Reciprocal Rank by 26.7% (relative) compared to a single-domain embedding baseline, indicating more consistent retrieval of relevant evidence to support cross-project knowledge synthesis and climate-resilient decision-making.

## OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution

DevFeed: [OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution](<https://devfeed.tech/articles/openkage-open-ended-lifelong-learning-in-the-open-world-via-knowledge-sharing-agent-group-evolution-142775.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24302>)

Author: Wenhao Yuan, Longhui Yuan, Zexi Jia, Ningzhe Shi, Jingwei Li, Shipeng Cen, Pengcheng Luo, Jie Zhou, Jinchao Zhang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experience](<https://devfeed.tech/tags/experience.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [groups](<https://devfeed.tech/tags/groups.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-sharing](<https://devfeed.tech/tags/knowledge-sharing.md>), [learning](<https://devfeed.tech/tags/learning.md>), [open](<https://devfeed.tech/tags/open.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

OpenKAGE enables groups of agents to keep exploring open worlds and build on one another's experience. It separates situated memories from transferable experiences and skills, retaining conditions for when those skills apply. Textual experiences are consolidated into a shared knowledge graph, while executable skills are shared verbatim. In Minecraft, the framework reportedly sustained group exploration and supported advanced technological milestones. Its accumulated knowledge also improved survival and exploration when transferred to a newly initialized group using a different backbone model.

### Source excerpt

arXiv:2611.24302v1 Announce Type: new Abstract: Building autonomous agents that continually explore open worlds and acquire new capabilities through experience is a long-standing aspiration in artificial intelligence. Existing research often pursues lifelong learning within predefined tasks, curricula, or objectives, with self-improvement largely confined to individual agents. We introduce OpenKAGE, an agent-group evolution framework for open-ended lifelong learning. Within this framework, agents autonomously explore open worlds and continually acquire new capabilities by accumulating and reusing knowledge from their own interactions and the experience of others. OpenKAGE builds on two key mechanisms: (1) a two-layer knowledge representation, with a memory layer for situated memories and an experience layer for transferable experience and skills that retains the applicability conditions needed for reuse; and (2) a knowledge-sharing mechanism that semantically consolidates textual experience into a continuously evolving shared knowledge graph, while executable skills are shared verbatim. In Minecraft, OpenKAGE supports open-ended lifelong learning, enabling agent groups to sustain exploration and reach advanced technological milestones. Furthermore, the accumulated knowledge can be transferred to a newly initialized agent group on a different backbone model, improving its survival and exploration progress.

## Perceived Effectiveness of Social Debt Mitigation Measures: A Preliminary Vignette-Based Survey

DevFeed: [Perceived Effectiveness of Social Debt Mitigation Measures: A Preliminary Vignette-Based Survey](<https://devfeed.tech/articles/perceived-effectiveness-of-social-debt-mitigation-measures-a-preliminary-vignette-based-survey-142139.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23263>)

Author: Philipp M. Z\\"ahl, Tom Siegel, Robin Kha, Chaitanya Chikkala, Zo\\'e Lermusiaux, Anika Hennig

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [bayesian](<https://devfeed.tech/tags/bayesian.md>), [best](<https://devfeed.tech/tags/best.md>), [bottleneck](<https://devfeed.tech/tags/bottleneck.md>), [but](<https://devfeed.tech/tags/but.md>), [change](<https://devfeed.tech/tags/change.md>), [channel](<https://devfeed.tech/tags/channel.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [communication](<https://devfeed.tech/tags/communication.md>), [consider](<https://devfeed.tech/tags/consider.md>), [convenience](<https://devfeed.tech/tags/convenience.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [design](<https://devfeed.tech/tags/design.md>), [effectiveness](<https://devfeed.tech/tags/effectiveness.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [social](<https://devfeed.tech/tags/social.md>), [survey](<https://devfeed.tech/tags/survey.md>)

### AI overview

A vignette survey of 23 IT professionals and advanced students found one clear favorite among 41 social debt mitigation measures: consolidating communication into a single primary channel for Communication Breakdown (P(best)=0.91). For the other five problem dimensions, preferred measures--including structured knowledge transfer and blameless retrospectives--had only moderate support (P(best)=0.38-0.58). Structural measures that reorganize information, decisions, and knowledge scored 0.3-0.4 points higher than role-based or attitudinal measures across scenarios, though not in every scenario. The small convenience sample makes these exploratory findings, rather than firm recommendations.

### Source excerpt

arXiv:2611.23263v1 Announce Type: new Abstract: Software engineering is a socio-technical discipline in which unresolved social and organizational problems accumulate as social debt, gradually eroding collaboration and project health. The literature offers a solid vocabulary for these problems but says little about which countermeasures practitioners consider effective. We address this gap with a vignette-based survey: six social debt problem dimensions (Organizational Silo, Newcomer Isolation, Communication Breakdown, Knowledge Bottleneck, Cultural and Geographical Distance, Psychological Safety Deficit) were presented as realistic team scenarios, and 23 IT professionals and advanced students rated 41 literature-derived mitigation measures. Rankings were analyzed with paired t-tests and a hierarchical Bayesian model that accounts for the within-subject design and yields, for each measure, the probability of being the best option in its scenario. Only for Communication Breakdown is the answer unambiguous: consolidating communication into a single primary channel is almost certainly preferred (P(best)=0.91). For the other five dimensions, the model identifies favorites with moderate evidence (P(best) between 0.38 and 0.58), such as structured knowledge transfer and blameless retrospectives. Across scenarios, structural measures that change how information, decisions, and knowledge are organized were rated higher than role-based or attitudinal measures (by 0.3 to 0.4 scale points), although not in every scenario. Given the small convenience sample, the results are exploratory, but they offer software engineering managers an evidence-graded starting point for selecting mitigation measures.

## Biomedical Knowledge Composition: A Software Engineering Perspective

DevFeed: [Biomedical Knowledge Composition: A Software Engineering Perspective](<https://devfeed.tech/articles/biomedical-knowledge-composition-a-software-engineering-perspective-142115.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.08927>)

Author: Natallia Kokash, Adam S. Z. Bellouma, Paola Grosso

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [biomedical](<https://devfeed.tech/tags/biomedical.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data](<https://devfeed.tech/tags/data.md>), [data-integration](<https://devfeed.tech/tags/data-integration.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [development](<https://devfeed.tech/tags/development.md>), [digital-twins](<https://devfeed.tech/tags/digital-twins.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [drug-discovery](<https://devfeed.tech/tags/drug-discovery.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [entity-resolution](<https://devfeed.tech/tags/entity-resolution.md>), [governance](<https://devfeed.tech/tags/governance.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [package-management](<https://devfeed.tech/tags/package-management.md>), [perspectives](<https://devfeed.tech/tags/perspectives.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [practices](<https://devfeed.tech/tags/practices.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The article argues that biomedical knowledge graphs are central to integrating molecular, clinical, and population data, but their construction is hindered by identifier mapping, entity resolution, schema alignment, evidence integration, and provenance tracking. It connects these domain challenges to limited adoption of mature software engineering practices, including package management, typed namespaces, canonical interchange formats, service composition, reproducible pipelines, and lifecycle governance. It catalogs eight open integration challenges, noting that partial solutions exist but no universally adopted stack. Its main emphasis is on reproducible KG assembly: reusable build pipelines and versioned dependencies that let others compile and customize graphs from source, rather than relying only on static deployed artifacts.

### Source excerpt

arXiv:2608.08927v2 Announce Type: replace Abstract: Biomedical research has accumulated vast molecular, clinical, and population data, yet translating this wealth into actionable knowledge remains constrained by technical and organizational difficulties. This article presents a unified treatment of two perspectives on biomedical knowledge infrastructure. The first introduces the biomedical domain to software engineers: it explains why knowledge graphs (KGs) are the central integrative data structure in modern biomedicine, characterizes five data harmonization challenges (identifier mapping, entity resolution, schema alignment, evidence integration, and provenance tracking), surveys application domains from drug discovery to digital twins, and profiles six representative KG systems with contrasting choices. The second perspective asks why engineering biomedical knowledge infrastructure remains so difficult. We argue that a contributing root cause is limited adoption of software tooling and practices that make development in other mature domains - particularly web engineering - reliably composable and reproducible: package management, typed namespaces, canonical interchange formats, service composition protocols, reproducible pipelines, and lifecycle governance. Against this backdrop, eight open engineering challenges for biomedical data integration are catalogued, each with partial solutions but no universally adopted stack. Crucially, the article shifts emphasis from describing deployed KG instances toward the reproducible process of assembling them: reusable build pipelines, versioned dependencies, and engineering practices that let others compile and customize a KG from source rather than consuming a static artifact. Together, the two perspectives provide domain grounding for newcomers and a research agenda for software engineers seeking to make transformative contributions to biomedical knowledge infrastructure.

## Why we started Context

DevFeed: [Why we started Context](<https://devfeed.tech/articles/why-we-started-context-144648.md>)

Original publisher: [Read original article](<https://www.mintlify.com/blog/why-we-started-context>)

Author: Chloe Wu-Breshears

Published: 2026-11-19T00:00:00Z

Content type: news

Language: en

Sources: [Mintlify Blog](<https://devfeed.tech/sources/mintlify-blog.md>)

Topics: [Documentation](<https://devfeed.tech/topics/documentation.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [context](<https://devfeed.tech/topics/context.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [context](<https://devfeed.tech/tags/context.md>), [devrel](<https://devfeed.tech/tags/devrel.md>), [docs](<https://devfeed.tech/tags/docs.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [editor](<https://devfeed.tech/tags/editor.md>), [event](<https://devfeed.tech/tags/event.md>), [events](<https://devfeed.tech/tags/events.md>), [experience](<https://devfeed.tech/tags/experience.md>)

### AI overview

At Mintlify's first Context event, documentation leaders discussed how to serve both human readers and agents as agents account for almost 80% of docs traffic, according to the excerpt. They identified a "Goldilocks" challenge: too little context leaves readers guessing, while too much obscures what matters, and the right amount may vary by reader. The discussion also raised open questions about whether people will continue to value polished, rendered docs alongside faster reading tools, and whether knowledge will shift toward plain Markdown. Panelists suggested that documentation formats may adapt to how each reader learns, while emphasizing that finding, reading and acting on information makes UX central to docs. The excerpt presents these as current questions rather than settled predictions.

### Source excerpt

A recap of our first evening at Letterform Archive, where technical writers, DevRel and engineering leaders talked about how people and agents will read, write and share knowledge.

## What is a semantic knowledge graph, and does your AI need one?

DevFeed: [What is a semantic knowledge graph, and does your AI need one?](<https://devfeed.tech/articles/what-is-a-semantic-knowledge-graph-and-does-your-ai-need-one-140278.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4249101/what-is-a-semantic-knowledge-graph-and-does-your-ai-need-one.html>)

Author: Maria Korolov

Published: 2026-11-18T10:00:00Z

Content type: article

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [graph-database](<https://devfeed.tech/topics/graph-database.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [analytics-artificial-intelligence-data-engineering-data-governance-data-management-databases-e](<https://devfeed.tech/tags/analytics-artificial-intelligence-data-engineering-data-governance-data-management-databases-e.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [business](<https://devfeed.tech/tags/business.md>), [data](<https://devfeed.tech/tags/data.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-governance](<https://devfeed.tech/tags/data-governance.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [data-lakehouse](<https://devfeed.tech/tags/data-lakehouse.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [database](<https://devfeed.tech/tags/database.md>), [databases](<https://devfeed.tech/tags/databases.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [emerging-technology](<https://devfeed.tech/tags/emerging-technology.md>), [employee](<https://devfeed.tech/tags/employee.md>), [erp](<https://devfeed.tech/tags/erp.md>), [explain](<https://devfeed.tech/tags/explain.md>), [flexible](<https://devfeed.tech/tags/flexible.md>), [graph](<https://devfeed.tech/tags/graph.md>), [it-leadership](<https://devfeed.tech/tags/it-leadership.md>), [it-strategy](<https://devfeed.tech/tags/it-strategy.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [risk-management](<https://devfeed.tech/tags/risk-management.md>), [security](<https://devfeed.tech/tags/security.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [storytype-feature](<https://devfeed.tech/tags/storytype-feature.md>)

### AI overview

A semantic knowledge graph gives AI agents both connected enterprise data and context about what that data means and how the business uses it. The excerpt contrasts tables with graph databases, where nodes and edges make relationships easier to traverse, and explains that a semantic layer can encode concepts such as client status, job roles, workflows, and business priorities. At Cosentino, a human-led project augmented by AI helped agents identify delayed orders and their causes; the company reports shorter delays for credit-blocked orders and savings, while noting that building and maintaining the layer still requires skilled human oversight. New York Life uses knowledge graphs for multi-agent orchestration and vector databases for generative AI retrieval of unstructured information. The text presents the approaches as serving different uses and says graph-based retrieval can provide more targeted context with fewer irrelevant materials and tokens. It also cautions that AI-generated relationships may be wrong and that model inaccuracies can compound across agent calls.

### Source excerpt

A traditional database organizes information into tables. One column is the name, another is the company they work for. A graph database stores the same information not in tables but in nodes and edges. A person could be one node, the company they work for is another, and the edge is the connection between the two. Any node can be connected to any other one, making graph databases much more flexible. And finding related entities is as simple as following the edges from one node to another. They're useful for navigating supply chain dependencies, detecting fraud, or mapping user preferences to make better recommendations. All of that is already potentially useful to AI agents, but that's not all. A knowledge graph sits on top of the graph database and is a map of the relationships. The node with the person's name, for example, could be connected to the node with the company information because the person is an employee of that company. The knowledge graph helps explain what the data is. A semantic graph, or a semantic knowledge graph, takes this one step further and adds a deeper level of meaning. For example, the list of companies could actually be a list of clients or potential clients. The list of people could also be potential contacts for sales calls, and their job titles could indicate their relative importance. The semantic layer is all about what the data means for the enterprise and how the data is actually used in practice. When AI agents are assigned actual work tasks, they need to have this information. "Agentic AI is AI that can do things, not just tell you things," says Rafael Domene, global CIO at manufacturing company Cosentino. "But you have to provide what AI needs to do the job in the right way. Not just data, but information. It's about business knowledge and understanding what's going on." Cosentino had already invested a lot of money into a massive data lake and data lakehouse, as well as ERP and CRM systems. "You can collect all the data, but t

## Expertise capture in workplace AI

DevFeed: [Expertise capture in workplace AI](<https://devfeed.tech/articles/expertise-capture-in-workplace-ai-137699.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21456>)

Author: Andreas Ekelhart, Ahmad Mohsin, Iqbal H. Sarker, Helge Janicke

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [absorption](<https://devfeed.tech/tags/absorption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [capture](<https://devfeed.tech/tags/capture.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [design](<https://devfeed.tech/tags/design.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [workplace](<https://devfeed.tech/tags/workplace.md>)

### AI overview

The abstract argues that workplace AI can absorb workers' professional judgment into resources controlled by employers or platforms, creating an imbalance when workers leave: organizations retain capabilities shaped by their contributions while workers lose access. How contributions can be attributed, separated, or revoked depends on where they reside and how they have been transformed; separation becomes harder as they move into derivatives, learned components, and successor systems. The authors propose write-time provenance, extraction of separable contributions, and an executable exit procedure to make agreed allocations technically actionable, while recognizing that some contributions cannot be separated.

### Source excerpt

arXiv:2611.21456v1 Announce Type: cross Abstract: AI assistants are becoming part of how knowledge workers think and perform, accumulating the prompts, exemplars, memory and interaction histories that encode a worker's professional judgment. This infrastructure typically runs under employer or platform control. We name the resulting process expertise capture, the absorption of worker-applied knowledge and judgment into AI resources under organizational control. We develop a framework of contribution forms, technical residences and transformation families, and show that how far a contribution can be attributed, separated and revoked depends on where it resides and how it has been transformed, properties fixed by system design long before any dispute arises. When a worker departs, the organization retains a capability shaped by their judgment while the worker loses access to it, and the asymmetry compounds as contributions move from inspectable artifacts into derivatives, learned components and successor systems. We outline three measures, write-time provenance, extraction of separable contributions and an executable exit procedure, that make an agreed allocation technically performable, and make explicit what cannot be separated at all.

## Hivemind: A Federated Protocol for AI-Mediated Tacit Knowledge Sharing in Organisations

DevFeed: [Hivemind: A Federated Protocol for AI-Mediated Tacit Knowledge Sharing in Organisations](<https://devfeed.tech/articles/hivemind-a-federated-protocol-for-ai-mediated-tacit-knowledge-sharing-in-organisations-137642.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20988>)

Author: Srinivasan Sundaresan (Rakuten Group, Inc.)

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-assisted-work](<https://devfeed.tech/tags/ai-assisted-work.md>), [ai-memory](<https://devfeed.tech/tags/ai-memory.md>), [ai-memory-systems](<https://devfeed.tech/tags/ai-memory-systems.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benefit](<https://devfeed.tech/tags/benefit.md>), [can](<https://devfeed.tech/tags/can.md>), [capture](<https://devfeed.tech/tags/capture.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [federated](<https://devfeed.tech/tags/federated.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-sharing](<https://devfeed.tech/tags/knowledge-sharing.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [tacit](<https://devfeed.tech/tags/tacit.md>), [tacit-knowledge](<https://devfeed.tech/tags/tacit-knowledge.md>)

### AI overview

Hivemind proposes a federated protocol for AI agents to share users' tacit work knowledge asynchronously across team and department boundaries, without direct human interaction. It connects individual AI memory systems--which capture decisions, reasoning, and context--with a shared space for that knowledge to flow. The paper evaluates centralised and decentralised designs, grounds its federated architecture in the SECI model, and demonstrates a proof of concept using Design Science Research. Measuring the enterprise benefit remains future work.

### Source excerpt

arXiv:2611.20988v1 Announce Type: new Abstract: This paper presents Hivemind, a federated protocol that enables AI agents to exchange tacit knowledge on behalf of their users, asynchronously and without requiring any direct human interaction. Individual AI memory systems capture the decisions, reasoning, and contextual knowledge that surface during AI-assisted work. Hivemind creates the shared space in which this captured knowledge can flow between individuals across team and departmental boundaries, addressing a structural gap that neither centralised knowledge repositories nor existing AI tooling closes, even where partial solutions such as expert-finding systems exist. The paper evaluates centralised versus decentralised design approaches, proposes a federated architecture grounded in Nonaka and Takeuchi's (1995) Socialisation, Externalisation, Combination and Internalisation (SECI) model, and demonstrates a proof-of-concept implementation using Design Science Research (DSR) methodology. Measuring the enterprise benefit of federated tacit expertise sharing remains an open task for future work.

## Knowledge-Centric Automated Issue Resolution: A Systematic Survey and Taxonomy

DevFeed: [Knowledge-Centric Automated Issue Resolution: A Systematic Survey and Taxonomy](<https://devfeed.tech/articles/knowledge-centric-automated-issue-resolution-a-systematic-survey-and-taxonomy-137955.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18569>)

Author: Zhenxi Chen, Mingwei Liu, Zihao Wang, Zhanhui Ren, Leyan Hu, Xueying Du, Ying Wang, Chenxi Zhang, Chong Wang, Zhenchang Xing, Haofen Wang, Xin Peng, Yanlin Wang

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [issue](<https://devfeed.tech/tags/issue.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [procedural-knowledge](<https://devfeed.tech/tags/procedural-knowledge.md>), [repository](<https://devfeed.tech/tags/repository.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [survey](<https://devfeed.tech/tags/survey.md>), [taxonomy](<https://devfeed.tech/tags/taxonomy.md>)

### AI overview

The survey of 133 studies finds that automated issue resolution agents rely mainly on existing code and development-tool knowledge, with repository history and repair experience increasingly used. It organizes issue-resolution knowledge into background, repository, and procedural layers and examines its types, sources, representations, uses, workflow stages, and evolution. Design architecture knowledge and explicitly modeled background knowledge receive comparatively little attention. The authors argue for reusable, traceable, evolving knowledge infrastructures to support more controllable, verifiable, and generalizable agents.

### Source excerpt

arXiv:2611.18569v1 Announce Type: new Abstract: Automated issue resolution is a knowledge-intensive software maintenance task in which LLM-based agents must acquire, represent, use, and update knowledge from repositories, execution environments, historical artifacts, documents, tools, and prior repair processes. This paper presents a systematic survey of 133 studies on automated issue resolution from a knowledge-centric perspective. We introduce a three-layer taxonomy that organizes issue-resolution knowledge into the Background Knowledge Layer, the Repository Knowledge Layer, and the Procedural Knowledge Layer, and analyze the knowledge lifecycle along six dimensions: knowledge types, sources and extraction methods, representation formats, usage methods, workflow stages, and temporal evolution. Our analysis shows that current systems primarily rely on Existing Code Knowledge and Development Tool Knowledge, while Repository Evolution Knowledge and Experiential Knowledge are increasingly adopted, indicating a shift toward history-informed, feedback-aware, and experience-oriented issue resolution. In contrast, Design Architecture Knowledge and explicitly modeled Background Knowledge remain comparatively underexplored. These findings suggest that future systems should move beyond temporary context construction toward reusable, traceable, and evolvable software knowledge infrastructures that support more controllable, verifiable, and generalizable software engineering agents. The surveyed studies and related resources are maintained at https://github.com/SYSUSELab/Awesome-Knowledge-for-AIR.

## Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore

DevFeed: [Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon-bedrock-agentcore-136124.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon-bedrock-agentcore/>)

Author: Elias Bedmar

Published: 2026-11-16T17:04:11Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-data-automation](<https://devfeed.tech/tags/amazon-bedrock-data-automation.md>), [amazon-neptune](<https://devfeed.tech/tags/amazon-neptune.md>), [amazon-opensearch-serverless](<https://devfeed.tech/tags/amazon-opensearch-serverless.md>), [anthropic-claude](<https://devfeed.tech/tags/anthropic-claude.md>), [aws-cdk](<https://devfeed.tech/tags/aws-cdk.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [aws-step-functions](<https://devfeed.tech/tags/aws-step-functions.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [hybrid-search](<https://devfeed.tech/tags/hybrid-search.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [manufacturing-technology](<https://devfeed.tech/tags/manufacturing-technology.md>), [novo-nordisk](<https://devfeed.tech/tags/novo-nordisk.md>), [process-intelligence](<https://devfeed.tech/tags/process-intelligence.md>)

### AI overview

Novo Nordisk's Manufacturing Technology team built a process-intelligence assistant on Amazon Bedrock AgentCore to answer manufacturing questions with cited information from controlled documents. It pairs a curated knowledge graph in Amazon Neptune, which captures process hierarchy and relationships, with hybrid semantic and BM25 search in Amazon OpenSearch Serverless, followed by reranking. In guided mode, the agent resolves scope--such as site, product generation, or equipment--from graph data before searching; it uses approved, effective documents by default and states when content is unavailable or ambiguous. The article reports that SME tasks that once took hours or days can take minutes. It describes a vault of about four million documents, while noting that document metadata may be mapped in the graph before full text is indexed; the assistant distinguishes these states.

### Source excerpt

Novo Nordisk's Manufacturing Technology team within the Tablet area team built a process-intelligence assistant on Amazon Bedrock AgentCore, using a GraphRAG architecture that pairs a knowledge graph in Amazon Neptune with hybrid search in Amazon OpenSearch Serverless to turn millions of controlled manufacturing documents into grounded, cited answers.

## The Information Problem

DevFeed: [The Information Problem](<https://devfeed.tech/articles/the-information-problem-136358.md>)

Original publisher: [Read original article](<https://philipptheserver.com/posts/the-information-problem/>)

Author: Philipp Lehmann (philipp.lehmann@gruppe.ai)

Published: 2026-11-16T07:00:00Z

Content type: article

Language: en

Sources: [Philipp Lehmann](<https://devfeed.tech/sources/philipp-lehmann.md>)

Topics: [Data Management](<https://devfeed.tech/topics/data-management.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [data-processing](<https://devfeed.tech/topics/data-processing.md>), [schema design](<https://devfeed.tech/topics/schema-design.md>), [consistency](<https://devfeed.tech/topics/consistency.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Electrical engineering and computer science (EECS)](<https://devfeed.tech/topics/electrical-engineering-and-computer-science-eecs.md>)

Tags: [22](<https://devfeed.tech/tags/22.md>), [about](<https://devfeed.tech/tags/about.md>), [acceptance](<https://devfeed.tech/tags/acceptance.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [argument](<https://devfeed.tech/tags/argument.md>), [cpp](<https://devfeed.tech/tags/cpp.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [information](<https://devfeed.tech/tags/information.md>), [methodology](<https://devfeed.tech/tags/methodology.md>), [moving](<https://devfeed.tech/tags/moving.md>), [needs](<https://devfeed.tech/tags/needs.md>), [revisions](<https://devfeed.tech/tags/revisions.md>), [testing](<https://devfeed.tech/tags/testing.md>), [traces](<https://devfeed.tech/tags/traces.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

Nisaba treats information as revisable claims about a changing world, with explicit limits on what records can establish. Its core is a responsibility loop: observe sources, create attributed and versioned assertions with declared dependencies, answer declared questions under eligibility conditions, deliver to accountable recipients, and observe outcomes. Revisions track world validity, record history, observation time, and current admissibility; this preserves what the system believed before a correction and distinguishes world changes from new knowledge or overdue review. Deterministic source transactions, parsers, rules, and human judgments form the baseline; AI is optional. Sixteen adversarial traces test failures such as treating missing allergy data as "no allergies," confusing an ACK with accepted responsibility, or a timer with proof of removal. The source describes a conditional specification with a working C++23 implementation, not a deployment. It explicitly excludes built-in AI, UI, and authentication, and states that identical observations cannot certify which of two unobserved worlds is real.

### Source excerpt

Nisaba treats information as stale claims about a moving world: bitemporal revisions, adversarial traces, and a closed loop that needs no AI.

## EU Machinery Regulation 2027: How It Impacts Technical Writers

DevFeed: [EU Machinery Regulation 2027: How It Impacts Technical Writers](<https://devfeed.tech/articles/eu-machinery-regulation-2027-how-it-impacts-technical-writers-133675.md>)

Original publisher: [Read original article](<https://document360.com/blog/eu-machinery-regulation-2027/>)

Author: Selvaraaju Murugesan

Published: 2026-11-13T12:24:08Z

Content type: article

Language: en

Sources: [Knowledge Management Tips, Best Practices and More](<https://devfeed.tech/sources/knowledge-management-tips-best-practices-and-more.md>)

Topics: [Documentation](<https://devfeed.tech/topics/documentation.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [2023](<https://devfeed.tech/tags/2023.md>), [accessibility](<https://devfeed.tech/tags/accessibility.md>), [council](<https://devfeed.tech/tags/council.md>), [eu](<https://devfeed.tech/tags/eu.md>), [parliament](<https://devfeed.tech/tags/parliament.md>), [regulation](<https://devfeed.tech/tags/regulation.md>), [technical](<https://devfeed.tech/tags/technical.md>), [technical-documentation](<https://devfeed.tech/tags/technical-documentation.md>)

### AI overview

Regulation (EU) 2023/1230 applies from 20 January 2027 and allows machinery instructions to be supplied digitally via a URL or QR code. Digital manuals must be downloadable and savable, available in the relevant EU market language, and accessible for the machinery's expected lifetime and at least 10 years after market placement. A free paper copy must be provided within one month if requested; safety information for consumer machinery must remain on paper. The text recommends auditing existing manuals, restructuring content into reusable topics, localising it, controlling documentation and software versions for product configurations, and testing whether users can find safety information on mobile devices. Platforms should support long-term access and redirects if URLs change. The excerpt distinguishes the Machinery Regulation's safety focus and full manuals from the Digital Product Passport's sustainability focus and structured data fields.

### Source excerpt

Regulation (EU) 2023/1230 was adopted by the European Parliament and the Council on ... The post EU Machinery Regulation 2027: How It Impacts Technical Writers appeared first on Document360.

## The AI at the source of water management reform

DevFeed: [The AI at the source of water management reform](<https://devfeed.tech/articles/the-ai-at-the-source-of-water-management-reform-131447.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4247561/ai-leadership-inside-how-the-climate-crisis-has-changed-water-management-why-did-the-korea-water-resources-corporation-choose-ai.html>)

Author: Jihyun Lee

Published: 2026-11-13T10:00:00Z

Content type: article

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Data Management](<https://devfeed.tech/topics/data-management.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-change-management-government-government-it-industry-it-leadership-it-o](<https://devfeed.tech/tags/artificial-intelligence-change-management-government-government-it-industry-it-leadership-it-o.md>), [change-management](<https://devfeed.tech/tags/change-management.md>), [climate-change](<https://devfeed.tech/tags/climate-change.md>), [data](<https://devfeed.tech/tags/data.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [government](<https://devfeed.tech/tags/government.md>), [government-it](<https://devfeed.tech/tags/government-it.md>), [industry](<https://devfeed.tech/tags/industry.md>), [it](<https://devfeed.tech/tags/it.md>), [it-leadership](<https://devfeed.tech/tags/it-leadership.md>), [it-operations](<https://devfeed.tech/tags/it-operations.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [markets](<https://devfeed.tech/tags/markets.md>), [plants](<https://devfeed.tech/tags/plants.md>), [quality](<https://devfeed.tech/tags/quality.md>), [storytype-case-study](<https://devfeed.tech/tags/storytype-case-study.md>), [water](<https://devfeed.tech/tags/water.md>)

### AI overview

K-water is bringing AI efforts across dam operations, water treatment, and distribution into one organization-wide framework to improve water forecasting and management amid harder-to-predict rainfall and drought. Work accelerated after downstream flood damage in 2020; its AI Division, established in late 2025, combines specialists across technical and administrative fields. Years of operational data and improved metadata standards provide a foundation, but using that data for AI requires an ontology to connect information across facilities, alongside retrieval-augmented generation (RAG). Large-scale data extraction has strained equipment, prompting upgrades and multiple collection routes; K-water also plans an AI data center in Sejong by 2030. For employees, it moved from an in-house Llama-based K-water GPT to secure access to external models including ChatGPT, Gemini, and Claude, while managing public-sector adoption constraints, costs through individual usage limits, and project timelines that lag rapid model changes. The excerpt describes these efforts as early-stage.

### Source excerpt

Korea Water Resources Corporation, better known as K-water, serves as sort of a water wholesaler, managing water in dams, treating it at purification plants, and supplying it to local municipalities. Now, the company is using AI to transform how to connect the flow of water from one end to the other. K-water has a long history of using technology to operate dams. In the past, however, it relied largely on historical climate patterns and operating experience accumulated over many years. As climate change brings more frequent and unexpected extremes of rainfall and drought, more situations are proving difficult to predict using those methods. So K-water needed new tools for analysis and forecasting, and AI was the answer. Source of the matter Flood damage downstream of dams in 2020 prompted K-water to begin adopting AI and digital twin technology in earnest. To extend that work across the organization, it established the AI Division in late 2025, which brings together internal specialists from a range of disciplines, including IT, administration, civil engineering, mechanical engineering, electrical engineering, environmental engineering, and telecommunications. Its task is to bring technologies developed in separate areas -- including digital twins for water management, AI-powered treatment plants, and smart water distribution network management -- into a single framework. That framework spans the entire process of managing water in dams, treating it, and delivering it to users. Ha-Dong Jung, VP of K-water's AI division, joined in 1997 and became its first head. He's witnessed its IT evolution firsthand, and to him, the division's creation was a natural progression. K-water has consistently used technology to drive internal innovation, and AI is a continuation of that work. Data management has been a particular focus. Initially, K-water collected information on dam levels, rainfall and water quality mainly for monitoring. It later began using that data to forecast wate

## The AI-Native Organization: Smaller Teams, Faster Execution, Fewer Roadmaps

DevFeed: [The AI-Native Organization: Smaller Teams, Faster Execution, Fewer Roadmaps](<https://devfeed.tech/articles/the-ai-native-organization-smaller-teams-faster-execution-fewer-roadmaps-130195.md>)

Original publisher: [Read original article](<https://hackernoon.com/the-ai-native-organization-smaller-teams-faster-execution-fewer-roadmaps?source=rss>)

Author: Aditya Vithaldas

Published: 2026-11-12T07:23:15Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [roadmaps](<https://devfeed.tech/topics/roadmaps.md>), [Linear](<https://devfeed.tech/topics/linear.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [accountability](<https://devfeed.tech/tags/accountability.md>), [adapting](<https://devfeed.tech/tags/adapting.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [ai-native-organizations](<https://devfeed.tech/tags/ai-native-organizations.md>), [ai-organizational-structure](<https://devfeed.tech/tags/ai-organizational-structure.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-management](<https://devfeed.tech/tags/engineering-management.md>), [execution](<https://devfeed.tech/tags/execution.md>), [future-of-work](<https://devfeed.tech/tags/future-of-work.md>), [linear](<https://devfeed.tech/tags/linear.md>), [meta](<https://devfeed.tech/tags/meta.md>), [organization](<https://devfeed.tech/tags/organization.md>), [product](<https://devfeed.tech/tags/product.md>), [product-management](<https://devfeed.tech/tags/product-management.md>), [ramp](<https://devfeed.tech/tags/ramp.md>), [roadmaps](<https://devfeed.tech/tags/roadmaps.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [small-team-structures](<https://devfeed.tech/tags/small-team-structures.md>), [teams](<https://devfeed.tech/tags/teams.md>), [tech-company-restructuring](<https://devfeed.tech/tags/tech-company-restructuring.md>)

### AI overview

The article describes a shift toward small, outcome-owning teams and shorter planning cycles as AI tools make building cheaper and more accessible. It cites Meta's three-to-five-person pods, LinkedIn's engineer-designer-PM trios, and examples of one-person teams. Roles are becoming more fluid, while small central platform teams maintain shared AI harnesses such as Ramp's Inspect and Shopify's River, which the article says help employees outside engineering build and execute work. Specialists can support multiple pods, and frontier teams track new developments. Long feature roadmaps are giving way to leader-set three-to-six-month direction, weekly reprioritization, and execution cycles measured in weeks; teams test plans by shipping previews or early-access releases. Speed still has limits: the article says high-risk security, stability, and compliance matters require review, and Shopify still has a human review every production PR. Its recommendations include cross-functional teams, shared practices, decisive leadership, and visible token spending.

### Source excerpt

How Anthropic, Ramp, Shopify, Meta and Linear are organizing product and engineering teams for 2027, and what it means for yours.

## JioHotstar Benchmarks Knowledge Bases for AI Coding Agents

DevFeed: [JioHotstar Benchmarks Knowledge Bases for AI Coding Agents](<https://devfeed.tech/articles/jiohotstar-benchmarks-knowledge-bases-for-ai-coding-agents-129195.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/jiohotstar-codingagent-retrieval/>)

Author: Leela Kumili

Published: 2026-11-11T14:28:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [code search](<https://devfeed.tech/topics/code-search.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code](<https://devfeed.tech/tags/code.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [design](<https://devfeed.tech/tags/design.md>), [development](<https://devfeed.tech/tags/development.md>), [harness](<https://devfeed.tech/tags/harness.md>), [jiohotstar-codingagent-retrieval](<https://devfeed.tech/tags/jiohotstar-codingagent-retrieval.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>), [news](<https://devfeed.tech/tags/news.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [token](<https://devfeed.tech/tags/token.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tools](<https://devfeed.tech/tags/tools.md>), [trade](<https://devfeed.tech/tags/trade.md>)

### AI overview

JioHotstar's evaluation found no retrieval approach that worked best across all coding tasks. Filesystem tools remained competitive on concrete work; Sourcebot's indexed text and symbol search improved results on harder SWE-bench Verified tasks at lower cost, while retrieval often added overhead on simpler SWE-bench Lite tasks. On CodeScaleBench, semantic retrieval helped with ambiguous requirements that were hard to map through exact text or symbol searches. The team recommends keeping filesystem tools as a baseline, matching structural or semantic search to the task, and measuring tool-use traces alongside accuracy. The excerpt describes tests using Claude Sonnet, subsets of SWE-bench and CodeScaleBench, and an internal question-answering harness; it does not establish a universal ranking.

### Source excerpt

JioHotstar evaluated 6 approaches to code retrieval for AI coding agents using SWE, CodeScale Bench, and an internal question-answering harness. Structural search performed well on concrete tasks, while semantic retrieval helped with ambiguous requirements. The findings highlight trade-offs in accuracy, token use, and tool design, underscoring the need to match retrieval tools to task types. By Leela Kumili

## Nintendo Is Officially Investing In Game Preservation

DevFeed: [Nintendo Is Officially Investing In Game Preservation](<https://devfeed.tech/articles/nintendo-is-officially-investing-in-game-preservation-127304.md>)

Original publisher: [Read original article](<https://games.slashdot.org/story/26/11/10/1814241/nintendo-is-officially-investing-in-game-preservation>)

Author: BeauHD

Published: 2026-11-10T19:00:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [Retrocomputing](<https://devfeed.tech/topics/retrocomputing.md>)

Tags: [2022](<https://devfeed.tech/tags/2022.md>), [game](<https://devfeed.tech/tags/game.md>), [game-preservation](<https://devfeed.tech/tags/game-preservation.md>), [investing](<https://devfeed.tech/tags/investing.md>), [nintendo](<https://devfeed.tech/tags/nintendo.md>)

### AI overview

Nintendo is hiring a digital archivist for a 12-month role to design and implement a framework for organizing technical records, engineering documentation, source materials, and institutional knowledge about legacy systems and platforms. The excerpt says the hiring aims to preserve historical records for future generations. It also recounts criticism from the Video Game History Foundation after Nintendo announced the Wii U and 3DS eShop closures in 2022, including the foundation's claim that the decision was destructive to video game history and its concern about preservation-related lobbying funded through the Entertainment Software Association.

### Source excerpt

Nintendo is hiring a digital archivist to help ensure the company's historical records are "preserved for future generations." The 12-month position is tasked with designing and implementing a "structured framework for organizing technical records, engineering documentation, source materials, and institutional knowledge related to legacy systems and platforms." Polygon reports: In the past, Nintendo has drawn criticism from the preservation community. In 2022, the Video Game History Foundation publicly criticized the company for announcing it would be closing the Wii U and 3DS eShops. The foundation released a statement saying that Nintendo's decision was "actively destructive to video game history." The statement also pointed out that Nintendo is part of the Entertainment Software Association, which funds lobbying that prevents a number of preservation efforts. Read more of this story at Slashdot.

## Culture is the new AI barrier: Why trust and adoption are more than technical challenges

DevFeed: [Culture is the new AI barrier: Why trust and adoption are more than technical challenges](<https://devfeed.tech/articles/culture-is-the-new-ai-barrier-why-trust-and-adoption-are-more-than-technical-challenges-126326.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4246437/culture-is-the-new-ai-barrier-why-trust-and-adoption-are-more-than-technical-challenges.html>)

Author: Paul Solé

Published: 2026-11-10T10:00:00Z

Content type: article

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [trust](<https://devfeed.tech/topics/trust.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [risk-management](<https://devfeed.tech/topics/risk-management.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [identity and access management](<https://devfeed.tech/topics/identity-and-access-management.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-digital-transformation-it-leadership](<https://devfeed.tech/tags/artificial-intelligence-digital-transformation-it-leadership.md>), [business](<https://devfeed.tech/tags/business.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [contributor](<https://devfeed.tech/tags/contributor.md>), [controls](<https://devfeed.tech/tags/controls.md>), [data](<https://devfeed.tech/tags/data.md>), [digital-transformation](<https://devfeed.tech/tags/digital-transformation.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [employees](<https://devfeed.tech/tags/employees.md>), [foundations](<https://devfeed.tech/tags/foundations.md>), [governance](<https://devfeed.tech/tags/governance.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [it](<https://devfeed.tech/tags/it.md>), [it-leadership](<https://devfeed.tech/tags/it-leadership.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [organizational](<https://devfeed.tech/tags/organizational.md>), [storytype-opinion](<https://devfeed.tech/tags/storytype-opinion.md>), [technical](<https://devfeed.tech/tags/technical.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

The article argues that scaling AI depends on organizational readiness as well as technical infrastructure. It proposes three layers: foundations, trust and adoption. Foundations include traceable, adaptable governance that covers security, data access, compliance and when humans must intervene; low-risk agents may act independently, while critical decisions such as insurance underwriting should retain human judgment. Trust requires transparency into agents' reasoning and actions, security controls, and realistic testing to find vulnerabilities. Adoption means training employees and giving agents organizational knowledge through expert-provided materials and ongoing feedback. The text presents employees as overseers, mentors and sources of domain expertise, helping turn generic AI into a capability suited to the organization.

### Source excerpt

There's intense focus among business leaders on building the right IT foundation to support AI across the organization. There's a rush to provision computing resources, unify data sources and modernize security, among other investments. But the implementation of AI is both a technical and organizational challenge. To actually get value, employees must know how to effectively wield the tools and understand their role in the emerging agentic processes, both as a security check and a mentor. Businesses need to trust they have the right infrastructure in place to scale, and employees have to trust the outputs are accurate -- particularly as AI agents operate with growing independence. Increasingly, AI can move beyond simply monitoring systems. Agents can start to act like a site reliability engineer, for example, retrying failed jobs, identifying problems and initiating self-healing actions. Or in post-trade processing, AI agents can automate exception management, a traditionally manual process that requires information to move back and forth between financial institutions and counterparties. To manage both the cultural and technical changes required, companies should think of AI adoption in three layers: foundations, trust and adoption. Foundations AI success starts with the fundamentals. At the most basic level, it's about making sure the resources are there to power the AI agents. But soon enough, any company will be able to buy or rent enough hardware to run AI at scale. The bigger challenge is actually governing AI activity across the organization. Enterprises need to be able to trace what AI agents are doing, understand the decisions they are making and govern those actions appropriately. And governance must extend beyond access controls and identity management to compliance. Every industry faces its own regulatory requirements that change depending on the region of operations and use case. For example, financial services firms have to comply with FINRA in the U.S.

## What Is Content Ambiguity? How to Identify and Fix It

DevFeed: [What Is Content Ambiguity? How to Identify and Fix It](<https://devfeed.tech/articles/what-is-content-ambiguity-how-to-identify-and-fix-it-121727.md>)

Original publisher: [Read original article](<https://document360.com/blog/content-ambiguity/>)

Author: Selvaraaju Murugesan

Published: 2026-11-06T08:46:09Z

Content type: article

Language: en

Sources: [Knowledge Management Tips, Best Practices and More](<https://devfeed.tech/sources/knowledge-management-tips-best-practices-and-more.md>)

Topics: [Documentation](<https://devfeed.tech/topics/documentation.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [added](<https://devfeed.tech/tags/added.md>), [addition](<https://devfeed.tech/tags/addition.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [articles](<https://devfeed.tech/tags/articles.md>), [base](<https://devfeed.tech/tags/base.md>), [content](<https://devfeed.tech/tags/content.md>), [first](<https://devfeed.tech/tags/first.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [information](<https://devfeed.tech/tags/information.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [post](<https://devfeed.tech/tags/post.md>), [presence](<https://devfeed.tech/tags/presence.md>), [trust](<https://devfeed.tech/tags/trust.md>), [what-is](<https://devfeed.tech/tags/what-is.md>)

### AI overview

Conflicting knowledge base articles can mislead chatbots and prevent AI agents from completing tasks. The excerpt groups ambiguity into factual conflicts, outdated information, conflicting scope, unsupported inference, and regional differences. It recommends frequent audits, using embeddings to narrow candidate articles, then an LLM to inspect and validate conflicts; writers can resolve issues, edit and publish articles through MCP tools, and repeat the process on a schedule. A direct MCP search depends on available token budget and context window and may find only pairs of conflicting articles. Writers must verify the correct information with stakeholders. Prepublication checks, chatbot evaluations, MCP prompt reviews, and AI agent prompt logs can help assess and reassess impact. The excerpt reports a 2026 research finding that 83% of high-traffic documentation sites had at least one page flagged as possibly incorrect or outdated, and one in three reader questions could not be fully answered.

### Source excerpt

The presence of conflicting information across your knowledge base articles erodes trust in ... The post What Is Content Ambiguity? How to Identify and Fix It appeared first on Document360.

## Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex

DevFeed: [Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex](<https://devfeed.tech/articles/toward-a-compositional-knowledge-architecture-for-a-shared-organizational-cortex-118374.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05753>)

Author: Andrew Miracle, Phyl Georgiou, Christine Okoth, Ese Monday

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [cortex](<https://devfeed.tech/tags/cortex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [dimension](<https://devfeed.tech/tags/dimension.md>), [dimensions](<https://devfeed.tech/tags/dimensions.md>), [domains](<https://devfeed.tech/tags/domains.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [layer](<https://devfeed.tech/tags/layer.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [network](<https://devfeed.tech/tags/network.md>), [organizational](<https://devfeed.tech/tags/organizational.md>), [organizations](<https://devfeed.tech/tags/organizations.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

The proposed four-layer architecture--Signals, Domains, Claims and Dimensions--aims to preserve organizational interpretations alongside their evidence, assumptions and standing. A truth-maintenance network revises that standing as evidence changes, while validated, versioned Dimensions position interpretations on named axes. In a registered retrieval experiment, adding the Dimension term improved nDCG@10 by 0.028 (p = 0.002); the full retrieval configuration improved it by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both p < 0.001).

### Source excerpt

arXiv:2611.05753v1 Announce Type: new Abstract: Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances change. Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation. We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence changes, and validated, versioned Dimensions position interpretations on named axes. We call the result a shared organizational cortex. In a registered retrieval experiment, the Dimension term gains 0.028 nDCG@10 (p = 0.002). In system-level comparisons, the full retrieval configuration improves nDCG@10 by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both reported p < 0.001). The architecture gives organizations a persistent, revisable basis for shared judgement.

## The Death of Google Search: How AI Is Changing the Internet Forever

DevFeed: [The Death of Google Search: How AI Is Changing the Internet Forever](<https://devfeed.tech/articles/the-death-of-google-search-how-ai-is-changing-the-internet-forever-116245.md>)

Original publisher: [Read original article](<https://hackernoon.com/the-death-of-google-search-how-ai-is-changing-the-internet-forever?source=rss>)

Author: Isaac Correa

Published: 2026-11-04T08:27:24Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Google Search](<https://devfeed.tech/topics/google-search.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Search engine optimization (SEO)](<https://devfeed.tech/topics/seo.md>), [Internet](<https://devfeed.tech/topics/internet.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [centralization](<https://devfeed.tech/topics/centralization.md>)

Tags: [advertising](<https://devfeed.tech/tags/advertising.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-and-the-internet](<https://devfeed.tech/tags/ai-and-the-internet.md>), [ai-answers](<https://devfeed.tech/tags/ai-answers.md>), [ai-search](<https://devfeed.tech/tags/ai-search.md>), [analog](<https://devfeed.tech/tags/analog.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [business](<https://devfeed.tech/tags/business.md>), [call-to-action](<https://devfeed.tech/tags/call-to-action.md>), [chat](<https://devfeed.tech/tags/chat.md>), [communication](<https://devfeed.tech/tags/communication.md>), [content](<https://devfeed.tech/tags/content.md>), [convenience](<https://devfeed.tech/tags/convenience.md>), [data](<https://devfeed.tech/tags/data.md>), [future-of-work](<https://devfeed.tech/tags/future-of-work.md>), [generative-engine-optimization](<https://devfeed.tech/tags/generative-engine-optimization.md>), [geo](<https://devfeed.tech/tags/geo.md>), [google](<https://devfeed.tech/tags/google.md>), [google-ai-search](<https://devfeed.tech/tags/google-ai-search.md>), [internet](<https://devfeed.tech/tags/internet.md>), [search](<https://devfeed.tech/tags/search.md>), [search-engines](<https://devfeed.tech/tags/search-engines.md>), [searching](<https://devfeed.tech/tags/searching.md>), [seo](<https://devfeed.tech/tags/seo.md>)

### AI overview

The author argues that AI answers are replacing link-by-link searching for routine questions, while Google remains useful for quick queries and powerful models are reserved for harder ones. This shift could redirect traffic and advertising, squeeze businesses that depend on search rankings, and push content makers toward GEO so AI systems cite them. The author's central concern is that instant answers make it easier to accept errors without scrutiny and may divide people into personalized information worlds. As a safeguard, the author distrusts an initial answer and compares it with blind evaluations from other models before relying on it. The essay closes by urging people to retain responsibility for the final decision.

### Source excerpt

Searching the web is giving way to asking an AI that answers at once. This essay weighs what that shift costs the person who stops searching.

## RAHC: Rule-Augmented Hyper-Relational Knowledge Graph Completion for Materials Synthesis

DevFeed: [RAHC: Rule-Augmented Hyper-Relational Knowledge Graph Completion for Materials Synthesis](<https://devfeed.tech/articles/rahc-rule-augmented-hyper-relational-knowledge-graph-completion-for-materials-synthesis-117530.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04809>)

Author: Jiawei Sun, Sijia Xu, Zihan Chen, Zhengyi Yang

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [rule-engine](<https://devfeed.tech/topics/rule-engine.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [completion](<https://devfeed.tech/tags/completion.md>), [condition](<https://devfeed.tech/tags/condition.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [graph](<https://devfeed.tech/tags/graph.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [literature](<https://devfeed.tech/tags/literature.md>), [materials](<https://devfeed.tech/tags/materials.md>), [planning](<https://devfeed.tech/tags/planning.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [rules](<https://devfeed.tech/tags/rules.md>), [selection](<https://devfeed.tech/tags/selection.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>)

### AI overview

RAHC completes missing synthesis conditions in hyper-relational knowledge graphs by combining graph structure with traceable rules derived from training records and retrieved literature. Hard rules constrain valid candidates, while soft rules guide ranking; RAHC-G weights rules by global reliability, and RAHC-Q also learns query-specific relevance. For joint multi-condition completion, tuple-conclusion rules provide evidence across conditions. Across five materials-synthesis datasets, the paper reports gains in single-slot and joint completion, including up to 15.6% higher Semi-inductive MRR than MAYPL. It also reports improved results on the entity-disjoint ILPC'22 Small benchmark. These findings suggest potential use in selecting experimental conditions and planning synthesis; the supplied text gives no detailed metrics beyond the stated gain.

### Source excerpt

arXiv:2611.04809v1 Announce Type: new Abstract: Scientific discovery depends on reusing experimental knowledge, yet records scattered across papers and repositories are often incomplete. In materials synthesis, recovering missing conditions requires reasoning about the target material and the observed context of a specific experiment. Hyper-relational knowledge graphs (HKGs) represent this context through qualifiers, but existing completion methods leave domain knowledge and experimental regularities implicit. We propose RAHC, a rule-augmented HKG framework for single-slot and joint multi-slot synthesis-condition completion. RAHC builds a traceable rule catalog from training records and retrieved literature, retrieves rules for each query-candidate pair, and separately encodes graph structure and rule evidence. Hard rules constrain candidate validity, while soft rules guide ranking. RAHC-G aggregates rules using global reliability; RAHC-Q additionally learns query-specific relevance. Gated fusion combines structural and rule representations, while tuple-conclusion rules provide cross-condition evidence for joint completion. Experiments on five materials-synthesis datasets show improvements in single-slot and joint completion under Semi-inductive and Open-Answer Inductive settings, with Semi-inductive MRR gains of up to 15.6% over MAYPL. RAHC also improves performance on the entity-disjoint ILPC'22 Small benchmark, supporting transfer to fully inductive KG completion. These results support experimental condition selection, synthesis planning, and the reuse of scientific knowledge.

## Your AI Agent Needs an Operating Environment. Who's Engineering It?

DevFeed: [Your AI Agent Needs an Operating Environment. Who's Engineering It?](<https://devfeed.tech/articles/your-ai-agent-needs-an-operating-environment-who-s-engineering-it-117836.md>)

Original publisher: [Read original article](<https://devops.com/your-ai-agent-needs-an-operating-environment-whos-engineering-it>)

Author: John Capobianco

Published: 2026-11-03T12:00:00Z

Content type: opinion

Language: en

Sources: [Automate Your Network](<https://devfeed.tech/sources/automate-your-network.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [allowed](<https://devfeed.tech/tags/allowed.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [article](<https://devfeed.tech/tags/article.md>), [completion](<https://devfeed.tech/tags/completion.md>), [context](<https://devfeed.tech/tags/context.md>), [devops](<https://devfeed.tech/tags/devops.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [environment](<https://devfeed.tech/tags/environment.md>), [harness](<https://devfeed.tech/tags/harness.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [model](<https://devfeed.tech/tags/model.md>), [operating-environment](<https://devfeed.tech/tags/operating-environment.md>), [techstrong-council](<https://devfeed.tech/tags/techstrong-council.md>), [test](<https://devfeed.tech/tags/test.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

An infrastructure agent's safety and reliability depend on the operating environment engineers provide, not just the model. The article recommends starting with a bounded task, scoped diagnostic tools and validated change capabilities, task-specific context with clear freshness requirements, and controls that enforce approvals and verification. Procedures can guide an agent, but execution systems must block changes when mandatory requirements are unmet and define what happens when verification fails. Teams should set evidence-based completion criteria, test rejection, timeout, partial-completion, and recovery scenarios, and ensure reports match execution records. They can build, adopt, or combine platforms; the relevant responsibilities include integration, authorization, testing, observability, and maintenance. Test the agent and its environment together as models, tools, and procedures change.

### Source excerpt

DevOps.com - Article - John explains why infrastructure agents need scoped tools, current context, enforced approvals, and evidence of completion, and why engineers must own and test the operating environment around the model.

## IBM aims to simplify mainframe modernization with AI-powered insight

DevFeed: [IBM aims to simplify mainframe modernization with AI-powered insight](<https://devfeed.tech/articles/ibm-aims-to-simplify-mainframe-modernization-with-ai-powered-insight-112984.md>)

Original publisher: [Read original article](<https://www.networkworld.com/article/4243443/ibm-aims-to-simplify-mainframe-modernization-with-ai-powered-insight.html>)

Author: Michael Cooney

Published: 2026-11-02T21:12:10Z

Content type: news

Language: en

Sources: [Network World](<https://devfeed.tech/sources/network-world.md>)

Topics: [Mainframe](<https://devfeed.tech/topics/mainframe.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Legacy Modernization](<https://devfeed.tech/topics/legacy-modernization.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-data-center-high-performance-computing-mainframes-networking](<https://devfeed.tech/tags/artificial-intelligence-data-center-high-performance-computing-mainframes-networking.md>), [atlas](<https://devfeed.tech/tags/atlas.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [high-performance-computing](<https://devfeed.tech/tags/high-performance-computing.md>), [ibm](<https://devfeed.tech/tags/ibm.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [mainframe](<https://devfeed.tech/tags/mainframe.md>), [mainframe-modernization](<https://devfeed.tech/tags/mainframe-modernization.md>), [mainframes](<https://devfeed.tech/tags/mainframes.md>), [map](<https://devfeed.tech/tags/map.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [middleware](<https://devfeed.tech/tags/middleware.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [modernize](<https://devfeed.tech/tags/modernize.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [networking](<https://devfeed.tech/tags/networking.md>), [os](<https://devfeed.tech/tags/os.md>), [outages](<https://devfeed.tech/tags/outages.md>), [patch-management](<https://devfeed.tech/tags/patch-management.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

IBM's proposed Z Atlas would map dependencies across a client's z/OS infrastructure, middleware, and applications to help teams assess the effects of changes before production. IBM says automated discovery, topology modeling, dependency analysis, natural-language interactions, and AI workflows would support impact assessments and change evidence, easing work such as patch management, regulatory response, testing, and cross-team coordination. For example, teams could trace how a middleware upgrade may affect dependent applications and identify systems and processes to validate. The aim is to reduce outages caused by changes not proven safe and preserve shared system knowledge as experienced staff retire. Z Atlas is only at the statement-of-direction stage; the text describes intended capabilities, not a released product or demonstrated results.

### Source excerpt

IBM is going to use AI to help and hasten mainframe customers looking to modernize seriously complex Big Iron operations. Understanding how the entire IBM Z environment is interconnected has become increasingly important as many mainframe teams still rely on manual analysis, fragmented tooling, and institutional knowledge to understand dependencies and evaluate risk across teams, creating a manual process that is slow and ineffective, wrote Skyla Loomis, general manager, IBM Z Software in a blog about the news. "As experienced professionals retire and modernization initiatives accelerate, the siloed knowledge problem is magnified with mainframe teams having trouble measuring the full impact of their changes before they reach production," Loomis stated. Enter Z Atlas, a native AI-based package Loomis says will map a client's entire z/OS stack across infrastructure, middleware, and applications. The package will then use that system intelligence to reduce the manual effort of tasks such as patch management, regulatory response, and knowledge sharing across every team, from systems programmers to application developers. The idea behind Z Atlas, which is only in the "statement of direction" phase, is to eliminate the leading cause of unplanned z/OS outages -- changes that aren't proven to be safe -- by mapping how a change impacts the z/OS stack by testing and validating it, Loomis stated. "For example, z/OS system programmers can use this solution to evaluate how a middleware upgrade might affect dependent applications, identify related infrastructure and operational processes that may require validation, determine which systems should be included in a test plan, or coordinate validation activities across application, infrastructure, and operations teams," Loomis wrote. "IBM Z Atlas' system intelligence is built on a foundation of automated discovery, topology modeling, dependency analysis, natural-language interactions, and AI-powered workflows to create impact assessme

## Article: Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures

DevFeed: [Article: Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures](<https://devfeed.tech/articles/article-systemic-approach-to-memory-knowledge-and-context-in-agentic-ai-architectures-111799.md>)

Original publisher: [Read original article](<https://www.infoq.com/articles/agentic-ai-context-memory-knowledge/>)

Author: Adi Polak

Published: 2026-11-02T11:00:00Z

Content type: article

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>)

Tags: [2023](<https://devfeed.tech/tags/2023.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [agentic-ai-context-memory-knowledge](<https://devfeed.tech/tags/agentic-ai-context-memory-knowledge.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [approach](<https://devfeed.tech/tags/approach.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [article](<https://devfeed.tech/tags/article.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [budgeting](<https://devfeed.tech/tags/budgeting.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engine](<https://devfeed.tech/tags/context-engine.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [data](<https://devfeed.tech/tags/data.md>), [engine](<https://devfeed.tech/tags/engine.md>), [information](<https://devfeed.tech/tags/information.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [loops](<https://devfeed.tech/tags/loops.md>), [memory](<https://devfeed.tech/tags/memory.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [model](<https://devfeed.tech/tags/model.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

The article's central claim is that reliable agents need a context engine to assemble a small, relevant, current reasoning state before each model call. It distinguishes temporary context, persistent memory, and curated knowledge, then describes a lifecycle of selection, injection, compression, and expiration or refresh. The engine should combine historical experience with live signals, filter and rank retrieved data, and structure it for the task; raw retrieval alone can bury useful facts in noise. It recommends tiered memory: a prompt window for working state, a session cache for recent activity, and asynchronous long-term storage for synthesized insights. Compression can reduce token cost and latency, but summaries need validation. Large prompts may increase cost and latency and obscure facts, while stale context can mislead. The article presents domain-specific curation, token budgeting, freshness checks, and safeguards such as validating inputs and removing PII as architectural measures to improve reliability.

### Source excerpt

The article argues that reliable agentic AI architecture depends on a context engine that selects, injects, compresses, and expires information before it reaches the model. It separates context, memory, and knowledge, and recommends tiered memory, curated knowledge, and token budgeting. It also covers common anti-patterns, such as context stuffing and stale data loops, with mitigations. By Adi Polak

[Next page](<https://devfeed.tech/topics/knowledge-management.md?cursor=WyIyMDI2LTExLTAyVDExOjAwOjAwKzAwOjAwIiwgImY0ZTAzY2Y4LWQwYTMtNDEzMC04NDY2LTljZjJjZTNhNDgyZCJd>)