# context-architecture

Context Architecture is a software-architecture specification for structuring repositories so claims about their structure and behavior are legible to people and AI agents and bound to mechanisms that fail when those claims become false.

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

## Record Sufficiency: What a Decision Record Must Preserve When an Unsettled Claim Becomes an Operative Status

DevFeed: [Record Sufficiency: What a Decision Record Must Preserve When an Unsettled Claim Becomes an Operative Status](<https://devfeed.tech/articles/record-sufficiency-what-a-decision-record-must-preserve-when-an-unsettled-claim-becomes-an-operative-status-142186.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23422>)

Author: Amadeus Brandes

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

Content type: article

Language: en

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

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [Pydantic](<https://devfeed.tech/topics/pydantic.md>)

Tags: [challenge](<https://devfeed.tech/tags/challenge.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [decision](<https://devfeed.tech/tags/decision.md>), [digital-services-act](<https://devfeed.tech/tags/digital-services-act.md>), [json-schema](<https://devfeed.tech/tags/json-schema.md>), [schema-validation](<https://devfeed.tech/tags/schema-validation.md>), [status](<https://devfeed.tech/tags/status.md>)

### AI overview

The paper argues that a sufficient decision record must let a reader explain a status, bound it, re-derive it, and challenge it, using ten questions mapped to the DRK v0.1 JSON Schema and four mechanical checks. It distinguishes schema conformance from reader-assessed adequacy, fidelity, and the merits of the decision. In tests on 164 seeded defects across three synthetic records, DRK v0.1 validation caught deleted required properties but accepted records with empty claims, rules, scope, limits, or challenge routes; false records pass every check. The authors stress these are seeded-schema results, not real-world performance estimates. The EU Digital Services Act Transparency Database statement schema fully answers four questions, partly answers two, and omits four. Among 25 sampled platform statements, free text addressed any of the four omitted questions in only two; in 18 (or 24 under a stricter coding reading), it did not explain why the item fell under the rule. The paper makes no deployment or legal claims.

### Source excerpt

arXiv:2611.23422v1 Announce Type: new Abstract: Organisations keep evidence, logs and approvals, but often not the step by which an unsettled claim became an operative status, such as an accepted label or a released image, so later readers cannot tell what the status was allowed to mean. We call a decision record sufficient if it is true and a reader who has only the record and the items it cites can explain the status, bound it, re-derive it and challenge it. From these four uses we argue for ten questions a record must answer, map them onto the author's earlier JSON Schema for decision records (DRK v0.1), and define four mechanical checks. We separate conformance, which the checks decide; adequacy, whether the answers are specific enough to use, which needs a reader; fidelity, which no check on the record decides; and merits, which sufficiency does not require. On 164 single-defect variants of three synthetic records, schema validation, the only check DRK v0.1 implements, rejects every variant with a deleted required property and none of the others, and it accepts a record whose claim, rule, scope, limits and challenge route are empty. These are properties of the schema shown on defects we seeded, not estimates of performance on real records. A false record passes every check. The statement-of-reasons schema of the EU Digital Services Act Transparency Database answers 4 of the questions in full, 2 in part and 4 not at all: why the matter was unsettled, what the status depends on, whether it can be re-derived, and how to challenge it. In 25 real statements from 25 platforms, drawn by a seeded rule and coded by a language model and checked by the author, free text addressed any of those four in only 2, and in 18 (24 under a stricter reading adopted during coding) no free text said why the item fell under the rule. No deployment or legal claim is made.

## Beyond Named Mechanisms: Economic Institutions as a Design Space for Artificial Agents

DevFeed: [Beyond Named Mechanisms: Economic Institutions as a Design Space for Artificial Agents](<https://devfeed.tech/articles/beyond-named-mechanisms-economic-institutions-as-a-design-space-for-artificial-agents-132083.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15017>)

Author: Nikolos Gurney, Fred Morstatter

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

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

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Finance](<https://devfeed.tech/topics/finance.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [copy](<https://devfeed.tech/tags/copy.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-gt](<https://devfeed.tech/tags/cs-gt.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [design](<https://devfeed.tech/tags/design.md>), [econ-gn](<https://devfeed.tech/tags/econ-gn.md>), [institutions](<https://devfeed.tech/tags/institutions.md>), [learn](<https://devfeed.tech/tags/learn.md>), [markets](<https://devfeed.tech/tags/markets.md>), [matching](<https://devfeed.tech/tags/matching.md>), [multiagent](<https://devfeed.tech/tags/multiagent.md>), [organization](<https://devfeed.tech/tags/organization.md>), [ownership](<https://devfeed.tech/tags/ownership.md>), [position](<https://devfeed.tech/tags/position.md>), [prices](<https://devfeed.tech/tags/prices.md>), [private](<https://devfeed.tech/tags/private.md>), [process](<https://devfeed.tech/tags/process.md>), [program](<https://devfeed.tech/tags/program.md>), [q-fin-ec](<https://devfeed.tech/tags/q-fin-ec.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [settlement](<https://devfeed.tech/tags/settlement.md>), [shift](<https://devfeed.tech/tags/shift.md>), [space](<https://devfeed.tech/tags/space.md>)

### AI overview

The paper argues that familiar economic mechanisms are only part of the design space for artificial agents, whose capabilities need not match human constraints. It proposes a provisional chart that describes institutions separately from their agents across positions, rights and duties, allocation, information, time, state, process, value, and external recognition. A simulation shows three ways to institutionalize copying an agent's competence: create an independent supplier, license capacity without creating a participant, or split an economic position among successors with different inherited obligations. The versions yield the same technical trace but differ in who exists, owns the copy, bears obligations, and gets paid. The authors propose refining the chart, mapping how agent capabilities affect which institutions can be implemented, and adding distinctions that engineered agents reveal.

### Source excerpt

arXiv:2611.15017v1 Announce Type: cross Abstract: Multiagent research inherited its economic vocabulary of auctions, markets, prices, bargaining, and matching from a single observed case: human societies. Those institutions bundle identity, competence, execution, ownership, commitment, and settlement in ways that suit agents whose minds are private, who learn rather than copy skills, and who each persist as one person. Engineered agents need not share any of these constraints, making the list of familiar institutions look less like the entirety of economic organization and more like a sample from a larger, unmapped space. We sketch one way to make that space concrete: a provisional chart that records each institution, separately from the agents that run it, as a typed structure over positions, rights and duties, allocation, information, time, state, process, value, and external recognition. In this chart, named institutions become overlapping regions rather than fixed points, neighboring families separate along a few coordinates, and the gaps between them become places to search. We show what the shift in perspective buys with a simulation in which one technical act, copying an agent's competence, is institutionalized as a new independent supplier, as licensed capacity that creates no new participant, and as the splitting of one economic position into successors that inherit some obligations and not others. In a paired task, all three produce an identical technical trace despite differing in who exists, who owns the copy, who is obligated, and who gets paid. We close with a research program: building a principled chart of institution space, mapping how its implementable region shifts with agent capacities, and revising the chart wherever engineered agents expose distinctions it cannot express.

## Bliki: Generated Glossary

DevFeed: [Bliki: Generated Glossary](<https://devfeed.tech/articles/bliki-generated-glossary-130843.md>)

Original publisher: [Read original article](<https://martinfowler.com/bliki/GeneratedGlossary.html>)

Author: Martin Fowler

Published: 2026-11-12T14:15:00Z

Content type: article

Language: en

Sources: [Martin Fowler](<https://devfeed.tech/sources/martin-fowler.md>)

Topics: [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [context window](<https://devfeed.tech/topics/context-window.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [also](<https://devfeed.tech/tags/also.md>), [audio](<https://devfeed.tech/tags/audio.md>), [bliki](<https://devfeed.tech/tags/bliki.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [case](<https://devfeed.tech/tags/case.md>), [cases](<https://devfeed.tech/tags/cases.md>), [cause](<https://devfeed.tech/tags/cause.md>), [chat](<https://devfeed.tech/tags/chat.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [doing](<https://devfeed.tech/tags/doing.md>), [domain](<https://devfeed.tech/tags/domain.md>), [draft](<https://devfeed.tech/tags/draft.md>), [easy](<https://devfeed.tech/tags/easy.md>), [effective](<https://devfeed.tech/tags/effective.md>), [experts](<https://devfeed.tech/tags/experts.md>), [glossary](<https://devfeed.tech/tags/glossary.md>)

### AI overview

A domain glossary can help LLMs work with organizational vocabulary that may be absent from their training. Generate candidate terms from internal documents, email, and chat, including familiar words used in unfamiliar ways; ask for concise definitions and note context when meanings differ. Have domain experts review the draft, store it where models can consult it efficiently, and refresh it regularly under version control. The article recommends separate glossaries where bounded contexts use terms differently, rather than forcing a single standard glossary; comparing glossaries, including source code with human-written material, can expose differences. For large glossaries, provide term names and links first, letting the model retrieve full definitions as needed. Glossaries can guide generated code and documents, while identifying internal, customer-inappropriate, or deprecated terms and preferred alternatives.

### Source excerpt

When we use LLMs in a specialized domain, such as the operations of any reasonably-large organization, there is a lot of specialized vocabulary. Such words and specialized meanings will be foreign to an LLM because they aren't in its training set, making it harder for the LLM to be effective when doing tasks in that domain. One technique to aid this is to use an LLM to generate a glossary of the terminology in that domain, and make this glossary available for any LLMs doing work in those circumstances. The sources for the LLM can be any material within the organization concerned such as documents, emails, and chat logs. In some cases getting transcripts of audio or video may be helpful, although most organizations generate enough text to do the job. The glossary-generating LLM should look for single words, and phrases of several words that regularly hang out together to form a meaningful term. The generator should be asked to identify terms that are new to it, but also known terms that are being used in unfamiliar ways. The latter can often cause the most confusion. Once we have a list of specialized vocabulary we can ask the agent to produce a glossary, with definitions for each term. Some terms may be used in different ways, in which case the LLM should provide alternative definitions, with a note as to what context the differences appear in. The LLM can be asked to follow the output format of a dictionary, with a focus on precision and conciseness. Once we have a draft glossary, then human experts in that domain should review it, and amend it for cases where the LLM has got the wrong ends of sticks. We then put the glossary somewhere where any other LLM can use it. It should be in a form that's easy for the LLM to consult, and minimize the tokens the LLM should consume in order to find meaning. We should set up a schedule to review and refresh the glossary at regular intervals, by agents and humans. We should keep it in version control, so we can see how it chang

## What's new in Runpod for Agents: November 2026

DevFeed: [What's new in Runpod for Agents: November 2026](<https://devfeed.tech/articles/what-s-new-in-runpod-for-agents-november-2026-127094.md>)

Original publisher: [Read original article](<https://www.runpod.io/blog/runpod-agent-skills-mcp-server>)

Author: Bohdan Yurov

Published: 2026-11-10T15:32:46Z

Content type: article

Language: en

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

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [hardened ai agent skills](<https://devfeed.tech/topics/hardened-ai-agent-skills.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [ci](<https://devfeed.tech/tags/ci.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cold-start](<https://devfeed.tech/tags/cold-start.md>), [comfyui](<https://devfeed.tech/tags/comfyui.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [dc](<https://devfeed.tech/tags/dc.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [evals](<https://devfeed.tech/tags/evals.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [november-2026](<https://devfeed.tech/tags/november-2026.md>), [rules](<https://devfeed.tech/tags/rules.md>), [skills](<https://devfeed.tech/tags/skills.md>), [tests](<https://devfeed.tech/tags/tests.md>), [what-s-new](<https://devfeed.tech/tags/what-s-new.md>)

### AI overview

Runpod's agent setup pairs a hosted MCP server, which exposes typed infrastructure operations, with Markdown skills that guide tool choice and procedures. The article's central finding is that skills go stale unless their claims are sourced and tested. Runpod describes a concept graph whose rules cite documentation, API references or probes, plus build checks, more than 80 skill eval cases, and 52 live-account user stories run with and without skills. Live recipe runs and agent reports feed fixes back into the skills, rules and tests. One example rule delays creating a network volume until stock selection determines the Pod's data center, avoiding repeated volume deletion when trying another location. The article says this system helps agents diagnose issues from worker logs and follow correct volume and deployment procedures; it does not provide measured performance results.

### Source excerpt

Skills tell an agent what to do and the MCP server does it. See how sourced rules, evals and live-account tests keep Runpod's agent skills accurate.

## How we rebuilt the Shopify app in 12 weeks

DevFeed: [How we rebuilt the Shopify app in 12 weeks](<https://devfeed.tech/articles/how-we-rebuilt-the-shopify-app-in-12-weeks-126837.md>)

Original publisher: [Read original article](<https://shopify.engineering/shopify-app-rebuild>)

Author: Remi Vanhee

Published: 2026-11-10T14:36:23Z

Content type: article

Language: en

Sources: [Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering.md>), [Shopify Engineering - Shopify Engineering](<https://devfeed.tech/sources/shopify-engineering-shopify-engineering.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [mobile-app-performance](<https://devfeed.tech/topics/mobile-app-performance.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Shopify](<https://devfeed.tech/topics/shopify.md>), [Android](<https://devfeed.tech/topics/android.md>), [android-app-bundle](<https://devfeed.tech/topics/android-app-bundle.md>), [app startup](<https://devfeed.tech/topics/app-startup.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [app](<https://devfeed.tech/tags/app.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [shopify](<https://devfeed.tech/tags/shopify.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [validation](<https://devfeed.tech/tags/validation.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Shopify says it rebuilt its mobile app from React Native to native Swift and Kotlin in 12 weeks with about 30 engineers and agents writing most of the code. The central change was the workflow around implementation: a shared cross-platform Reflex architecture, a CLI and testable business logic for millisecond feedback without a device, small migration checkpoints checked against the existing app, and CI guardrails for architectural drift. Pods of two engineers owned product areas across both platforms; agents reviewed PRs first, while humans retained final review and shipping decisions. Consistency made cross-platform changes easier to compare and reuse, at the cost of some platform idiom. Faster code generation shifted constraints to compute, CI, review, merging, and coordination. Shopify reports launch-time reductions, smaller Android binaries and lower memory use, and improved Android crash-free sessions; the excerpt provides figures for these outcomes. It also says new features without an existing screen remain a distinct challenge.

### Source excerpt

What changed when agents started writing our mobile code, and how we redesigned our architecture, tooling, and workflow around validation.

## Software is NOT Dead

DevFeed: [Software is NOT Dead](<https://devfeed.tech/articles/software-is-not-dead-110707.md>)

Original publisher: [Read original article](<https://craftbettersoftware.com/p/software-is-not-dead>)

Author: Daniel Moka

Published: 2026-11-01T08:03:19Z

Content type: opinion

Language: en

Sources: [Craft Better Software](<https://devfeed.tech/sources/craft-better-software.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Software](<https://devfeed.tech/topics/software.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>)

Tags: [abstractions](<https://devfeed.tech/tags/abstractions.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [build](<https://devfeed.tech/tags/build.md>), [building-software](<https://devfeed.tech/tags/building-software.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [control](<https://devfeed.tech/tags/control.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fundamentals](<https://devfeed.tech/tags/fundamentals.md>), [future](<https://devfeed.tech/tags/future.md>), [quality](<https://devfeed.tech/tags/quality.md>), [ship](<https://devfeed.tech/tags/ship.md>), [software](<https://devfeed.tech/tags/software.md>), [write](<https://devfeed.tech/tags/write.md>)

### AI overview

The author argues that software engineering fundamentals remain essential as AI takes over more coding work: an agent's codebase provides context, and poorly structured code can confuse agents as it can people. Strong types, clean abstractions, and high-quality tests are presented as constraints that reduce agents' room for poor decisions. The proposed shift is from manually writing, reading, testing, and documenting code toward engineering agents to perform those tasks and verifying their work.

### Source excerpt

Software is more alive than ever. Our job is not to write code. Our job is to lead agents to ship quality software.

## Old Ideas

DevFeed: [Old Ideas](<https://devfeed.tech/articles/old-ideas-109265.md>)

Original publisher: [Read original article](<https://blog.fogus.me/thoughts/old-ideas.html>)

Author: fogus

Published: 2026-10-30T11:07:49Z

Content type: article

Language: en

Sources: [Mike Fogus](<https://devfeed.tech/sources/mike-fogus.md>)

Topics: [legacy systems](<https://devfeed.tech/topics/legacy-systems.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Functional programming](<https://devfeed.tech/topics/functional-programming.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [computing](<https://devfeed.tech/tags/computing.md>), [design](<https://devfeed.tech/tags/design.md>), [designer](<https://devfeed.tech/tags/designer.md>), [history](<https://devfeed.tech/tags/history.md>), [history-of-computing](<https://devfeed.tech/tags/history-of-computing.md>), [ideas](<https://devfeed.tech/tags/ideas.md>), [llm](<https://devfeed.tech/tags/llm.md>), [systems](<https://devfeed.tech/tags/systems.md>), [value](<https://devfeed.tech/tags/value.md>)

### AI overview

The author argues that older computing ideas should be engaged with before being dismissed as obsolete: a technology's decline does not mean its ideas were disproved or absorbed by what replaced it. Earlier work preserves approaches shaped by different constraints and can expand a systems designer's "intellectual tool-chest," offering alternative ways to frame future problems. Examples include McCarthy's advice taker and its relevance to modern agentic systems, conceptual treatments of data and representation, "Out of the Tar Pit" on complexity and state, symbolic-computing architectures, and Common Lisp's enduring design ideas. The author does not claim every old approach deserves revival; the value lies in gaining perspectives and exercising judgment, especially as software artifact production becomes more automated.

### Source excerpt

Whereby I discuss the value of old ideas...

## Elegance and intelligence are anticorrelated

DevFeed: [Elegance and intelligence are anticorrelated](<https://devfeed.tech/articles/elegance-and-intelligence-are-anticorrelated-108350.md>)

Original publisher: [Read original article](<https://seangoedecke.com/elegance-and-intelligence-are-anticorrelated/>)

Published: 2026-10-30T00:00:00Z

Content type: opinion

Language: en

Sources: [Sean Goedecke](<https://devfeed.tech/sources/seangoedecke-com-rss-feed.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Trends](<https://devfeed.tech/topics/ai-trends.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [abstractions](<https://devfeed.tech/tags/abstractions.md>), [ai](<https://devfeed.tech/tags/ai.md>), [correlation](<https://devfeed.tech/tags/correlation.md>), [creativity](<https://devfeed.tech/tags/creativity.md>), [intelligence](<https://devfeed.tech/tags/intelligence.md>), [mathematical-proofs](<https://devfeed.tech/tags/mathematical-proofs.md>), [memory](<https://devfeed.tech/tags/memory.md>), [software-design](<https://devfeed.tech/tags/software-design.md>), [software-engineers](<https://devfeed.tech/tags/software-engineers.md>)

### AI overview

The essay argues that raw intelligence and elegance can pull in opposite directions: someone with a large working memory may solve problems by tracking many steps directly, while elegant design reduces that burden through abstractions and interfaces. This can make some strong engineers comfortable with messy code. The author applies the idea to AI-generated proofs, which may be verbose because sufficiently capable models can follow long chains of reasoning; less elegant proofs could also offer fewer abstractions that spark new conjectures. The author leaves open whether machines can match human creativity, noting that von Neumann both calculated readily and invented mathematics, and that some engineers still value neatness.

### Source excerpt

Elegance and intelligence can have a surprisingly negative correlation. Intelligent people sometimes produce inelegant solutions because they're capable of rapidly brute-forcing problems. If I had to remember a hundred names, I would spend time coming up with clever mnemonics. John von Neumann would probably just remember them. There's a famous von Neumann story where he was asked how far a fly must travel if it kept flying between two cyclists who were approaching each other at some fixed speed. The trick to the puzzle was to notice that the cyclists would take an hour to meet, so the fly must be travelling for an hour: given the fly's speed, it's then easy to calculate the total distance. When von Neumann solved the puzzle instantly, the questioner assumed he'd heard the trick before, but in fact he had just summed the infinite series. If you can do that instantly in your head, why bother with the clever trick? For software engineers, the most important kind of raw intelligence is often the size of your working memory: how many moving pieces you can hold in your head at a given time. Software design involves finding elegant ways to reduce that number of moving pieces, typically by abstracting them away or moving them behind some interface. It can be frustrating1 to work with engineers with a giant working memory, because they don't care as much about decomposing the problem into some elegant design -- they don't need to. This is why some2 really good engineers are surprisingly okay with working in a sloppy codebase: because they can see the whole thing clearly at a glance. Since they never get lost or confused, the level of mess is acceptable to them. When needed, they will effortlessly visualize a ten or twelve step execution flow to see what needs changing or where the problem is. Something like this might be going on with AI-generated mathematical proofs, which read as unacceptably verbose and unfocused in the eyes of human mathematicians. However, for a suffici

## From Ripple to Boundary: Deterministic Impact Boundaries for LLM-Based Software Evolution

DevFeed: [From Ripple to Boundary: Deterministic Impact Boundaries for LLM-Based Software Evolution](<https://devfeed.tech/articles/from-ripple-to-boundary-deterministic-impact-boundaries-for-llm-based-software-evolution-103643.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36549>)

Author: Jiameng Bai, Zhitao Wang, Long Wang, Keyue Qian, Sai Wu

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

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

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Model driven development](<https://devfeed.tech/topics/model-driven-development.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [asset](<https://devfeed.tech/tags/asset.md>), [change](<https://devfeed.tech/tags/change.md>), [code](<https://devfeed.tech/tags/code.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dag](<https://devfeed.tech/tags/dag.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [design](<https://devfeed.tech/tags/design.md>), [effect](<https://devfeed.tech/tags/effect.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [graph](<https://devfeed.tech/tags/graph.md>), [hash](<https://devfeed.tech/tags/hash.md>), [impact](<https://devfeed.tech/tags/impact.md>), [llm](<https://devfeed.tech/tags/llm.md>), [ripple](<https://devfeed.tech/tags/ripple.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

The paper proposes a deterministic way to identify which generated code should change when a design asset is updated. It represents design assets as a Knowledge Graph organized into a content-addressed Merkle DAG, then uses two-phase diffing to trace a causal chain and define a modification boundary. The authors say this boundary lets an LLM receive narrowly scoped code and design context, addressing risks they attribute to probabilistic retrieval and text-based diffing: missing required changes or altering unrelated code. The Knowledge Graph also supports natural-language design retrieval. The abstract reports early deployment on an industrial payment platform, where the mechanism computed impact boundaries and generated incremental modifications matching expected design changes; it provides no further evaluation details.

### Source excerpt

arXiv:2610.36549v1 Announce Type: new Abstract: The landscape of software evolution is undergoing a fundamental paradigm shift in the era of Large Language Models. As industrial software engineering increasingly transitions toward design-driven code generation, the bottleneck of evolution has shifted from writing code to maintaining deterministic consistency between multi-source design assets and the generated code. When a design asset changes, LLM agents currently lack a deterministic impact boundary to identify which code must be evolved, leading to two failure modes: hallucinating missing changes or breaking unrelated code. Probabilistic approaches, such as semantic retrieval or text-based diffing, fail to capture the structural ripple effects across highly interconnected design dependencies. We propose a paradigm shift from probabilistic semantic retrieval to deterministic structural constraints. We formalize the design assets as a Knowledge Graph and organize them into a content-addressed Merkle Directed Acyclic Graph. Our key insight reveals a topological isomorphism between the logical ripple effect of a design change and the content hash propagation within the DAG. By leveraging this, we transform ambiguous impact analysis into verifiable structural operations. Through a two-phase diffing process, we extract a precise causal chain that defines the exact modification boundary. This boundary enables deterministic context injection, providing the LLM agent with strictly scoped code and design updates, thereby fundamentally guaranteeing evolution safety. As a by-product, the KG serves as an agent-queryable knowledge base for natural language design retrieval. Early deployment on a large-scale industrial payment platform demonstrates that our mechanism successfully computes the exact impact boundary and generates incremental code modifications that meet the expected design changes.

## Architecting AI-SDLC: Five Lessons For DevSecFinOps Teams

DevFeed: [Architecting AI-SDLC: Five Lessons For DevSecFinOps Teams](<https://devfeed.tech/articles/architecting-ai-sdlc-five-lessons-for-devsecfinops-teams-102010.md>)

Original publisher: [Read original article](<https://hackernoon.com/architecting-ai-sdlc-five-lessons-for-devsecfinops-teams?source=rss>)

Author: krishna dutt

Published: 2026-10-27T05:22:27Z

Content type: article

Language: en

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

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [finops](<https://devfeed.tech/topics/finops.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Cross-Compilation](<https://devfeed.tech/topics/cross-compilation.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2014](<https://devfeed.tech/tags/2014.md>), [2022](<https://devfeed.tech/tags/2022.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [absolute](<https://devfeed.tech/tags/absolute.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-sdlc](<https://devfeed.tech/tags/ai-sdlc.md>), [ai-sdlc-intelligence](<https://devfeed.tech/tags/ai-sdlc-intelligence.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [cognitive-debt](<https://devfeed.tech/tags/cognitive-debt.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [governance](<https://devfeed.tech/tags/governance.md>), [like](<https://devfeed.tech/tags/like.md>), [need](<https://devfeed.tech/tags/need.md>), [sdlc](<https://devfeed.tech/tags/sdlc.md>), [software-architecture](<https://devfeed.tech/tags/software-architecture.md>), [teams](<https://devfeed.tech/tags/teams.md>), [token](<https://devfeed.tech/tags/token.md>), [token-consumption](<https://devfeed.tech/tags/token-consumption.md>), [using](<https://devfeed.tech/tags/using.md>)

### AI overview

The article argues that enterprise AI adoption shifts engineering effort from typing to comprehension, cost control, orchestration, and governance. It recommends requiring developers to trace AI-generated code and explain its architectural rationale in reviews, while tracking token budgets, enforcing rate limits, and measuring feature-level unit economics. For multi-agent workflows, it describes LangGraph as suited to strict, auditable processes and CrewAI as more natural for collaborative stepwise tasks; it favors hierarchical tree orchestration over hub-and-spoke bottlenecks or noisy peer-to-peer setups. It proposes routing agent actions through a gateway with input sanitization, output checks, and pre-tool safeguards, plus automated SBOM generation in CI/CD (for example, with CycloneDX). The article also urges engineers to define architecture and failure constraints before prompting, treating AI as help with syntax and boilerplate rather than a substitute for understanding.

### Source excerpt

Using AI in enterprises is challenging due to issues like cognitive debt, unpredictable token consumption, and the need for strict governance.

## How to Keep AI-Written Code Clean When Nobody Reads It

DevFeed: [How to Keep AI-Written Code Clean When Nobody Reads It](<https://devfeed.tech/articles/how-to-keep-ai-written-code-clean-when-nobody-reads-it-100959.md>)

Original publisher: [Read original article](<https://proandroiddev.com/what-keeps-agent-written-code-clean-when-nobody-reads-it-62b771eb4a50?source=rss----c72404660798---4>)

Author: Ramiz Raja

Published: 2026-10-26T13:37:31Z

Content type: article

Language: en

Sources: [ProAndroidDev](<https://devfeed.tech/sources/proandroiddev-medium.md>)

Topics: [clean-code](<https://devfeed.tech/topics/clean-code.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [mutation-testing](<https://devfeed.tech/topics/mutation-testing.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [Android](<https://devfeed.tech/topics/android.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [android](<https://devfeed.tech/tags/android.md>), [android-development](<https://devfeed.tech/tags/android-development.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [clean-architecture](<https://devfeed.tech/tags/clean-architecture.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [data](<https://devfeed.tech/tags/data.md>), [domain](<https://devfeed.tech/tags/domain.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [ios](<https://devfeed.tech/tags/ios.md>), [ios-development](<https://devfeed.tech/tags/ios-development.md>), [kotlin](<https://devfeed.tech/tags/kotlin.md>), [layers](<https://devfeed.tech/tags/layers.md>), [review](<https://devfeed.tech/tags/review.md>), [software-architecture](<https://devfeed.tech/tags/software-architecture.md>), [test](<https://devfeed.tech/tags/test.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

Written architecture rules alone did not preserve the boundary in ResizePing: a rule checked once allowed media kit imports to spread into 20 UI files and 5 domain files. The author's approach is to enforce important seams with build-failing tests that scan imports, fail if the source root is missing, and are proven against deliberate violations. A grep-based JVM test is a lightweight option for single-module Android apps; separate Gradle modules or Swift packages can make forbidden imports compiler errors. The author also has a different model inspect the repository when reviewing plans and code, and uses shared JSON cases and fixtures to check matching behavior across native Kotlin and Swift implementations. These contracts cover only their defined cases, and changes to the cases need review.

### Source excerpt

AI agents write most of the code in my Android and iOS apps now, and I don't read it line by line. I read plans, verdicts and test results. That leaves a fair question: if nobody reads the code, what keeps the clean architecture clean? Clean architecture with AI coding agents is what keeps the next change cheap. When an SDK changes, I want to touch one adapter, not forty screens. And the next agent should find one obvious place for the next feature. The short answer: written rules don't do it on their own. Boundary tests that fail the build do, plus a second model that reviews the plan and reads the repo instead of trusting the writer. The rest of this piece is the evidence, starting with a boundary that broke. The apps involved are my own: ResizePing (image and video resizing), StatusPing (WhatsApp status saving), PlannedPing (scheduled WhatsApp messages) and ChatPing (a bring-your-own-key AI chat app). All are native Kotlin on Android and Swift on iOS. The rule that lived in a prompt Here's the boundary that broke, because it shows the problem better than anything that held. ResizePing is an image and video resizer. Its engine lives in a shared kit, ping-media-kit, which both the Android and iOS apps consume. The first integration task said the app's domain and UI layers must never import kit types. Everything goes through one app-side repository, so the kit could be replaced later without changing call sites. The independent review that gated that task checked it with a grep: grep -rn com.pingfamily.mediakit app/src/main` returns hits ONLY in `data/resize/EngineGateway.kt` and `data/resize/ResizeRepositoryImpl.kt`. Any hit in `domain/` or `ui/` is a FAIL. It passed. Then the app kept growing: video, combine-to-PDF, export options. I ran the same grep while writing this. It now finds kit imports in 20 files under ui/ and 5 under domain/. The iOS app has the same leak in its video view model. Nobody decided to drop the rule. It was checked once, at one review, and

## Lukewarm recommendations for improving AI agents' interactions with your projects

DevFeed: [Lukewarm recommendations for improving AI agents' interactions with your projects](<https://devfeed.tech/articles/lukewarm-recommendations-for-improving-ai-agents-interactions-with-your-projects-100137.md>)

Original publisher: [Read original article](<https://www.jvt.me/posts/2026/10/25/renovate-agent-improvements/>)

Author: Jamie Tanna

Published: 2026-10-25T17:25:54Z

Content type: article

Language: en

Sources: [Jamie Tanna](<https://devfeed.tech/sources/articles-on-jamie-tanna-software-engineer.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [bestpractice](<https://devfeed.tech/topics/bestpractice.md>), [pnpm](<https://devfeed.tech/topics/pnpm.md>), [Maintainers](<https://devfeed.tech/topics/maintainers.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [agents-md](<https://devfeed.tech/tags/agents-md.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [blogumentation](<https://devfeed.tech/tags/blogumentation.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [code-style](<https://devfeed.tech/tags/code-style.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [contributors](<https://devfeed.tech/tags/contributors.md>), [development](<https://devfeed.tech/tags/development.md>), [docs](<https://devfeed.tech/tags/docs.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [llm](<https://devfeed.tech/tags/llm.md>), [projects](<https://devfeed.tech/tags/projects.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [renovate](<https://devfeed.tech/tags/renovate.md>), [standard](<https://devfeed.tech/tags/standard.md>), [standards](<https://devfeed.tech/tags/standards.md>), [structure](<https://devfeed.tech/tags/structure.md>), [style](<https://devfeed.tech/tags/style.md>), [things](<https://devfeed.tech/tags/things.md>)

### AI overview

Renovate found that a predictable codebase and contributor documentation helped agents produce mostly technically correct code even before AI-specific changes. The author recommends keeping AGENTS.md or CLAUDE.md brief and directing agents to fuller development standards; providing a single `check` command for CI-like checks, including selected-file and no-test modes; and using a Claude Code `Stop` hook to require checks before an agent finishes. Common review complaints can be encoded as lint rules. Renovate uses `mise` and a Claude Code `PreToolUse` hook to steer agents toward required tools such as pnpm and Vitest; cloud agents then need less preinstalled software. The author also reports better results by having Claude Sonnet review and improve code produced by Amp's Claude Opus, at the cost of more tokens. These practices are presented as useful to human contributors as well as agents.

### Source excerpt

Over the last week I've been chatting with some folks who are looking at integrating AI more into their development work. I shared a couple of things that we've found have worked well for Renovate, as a codebase that takes a lot of human (and since mid-last year, AI) contributions. Although I've written about this a bit in my reflection on the last year, this naturally deserves its own blogumentation. Before we did anything to explicitly optimise the codebase for AI agents, we ended up finding that we'd - for the most part - receive fairly technically correct code, although it wouldn't necessarily fit in the areas that it was added for, or wouldn't completely fit our code style, but would handle a lot of file-directory architecture choices. We credit this down to the fact that we've structured our codebase in a predictable and - in my opinion, reasonable - structure, which has been optimised for the humans who are interacting with it. As well as this, we've also had documentation for new contributors to understand how best to get started, which also helps the agents! I've called this a "lukewarm" set of recommendations because for anyone who's fairly invested in doing work with AI agents, these are going to feel like so last $timePeriod. I appreciate that they're not ground breaking, but they're useful for folks who may be earlier in their AI journey than others. These recommendations build on great work that Sergei Zharinov and Sebastian Poxhofer - as well as a few other folks - have been doing. AGENTS.md / CLAUDE.md I'm largely adding this for completeness - it's a fairly standard recommendation that you'll get from most people, but the interesting angle we've got is that it doesn't need to be exhaustive. You can see that we've barely updated AGENTS.md since adding it in May, but we have made many docs edits for our "development standards" documentation. These docs were originally built for human readers, and are still our recommended area for this information to

## AGENTS.md Is a Config File, Not a Wishlist

DevFeed: [AGENTS.md Is a Config File, Not a Wishlist](<https://devfeed.tech/articles/agents-md-is-a-config-file-not-a-wishlist-91831.md>)

Original publisher: [Read original article](<https://hackernoon.com/agentsmd-is-a-config-file-not-a-wishlist?source=rss>)

Author: Bhaskar

Published: 2026-10-20T21:53:16Z

Content type: opinion

Language: en

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

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [agent-evaluation](<https://devfeed.tech/tags/agent-evaluation.md>), [agent-instructions](<https://devfeed.tech/tags/agent-instructions.md>), [agents-md](<https://devfeed.tech/tags/agents-md.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-configuration](<https://devfeed.tech/tags/ai-agent-configuration.md>), [ai-assisted-coding](<https://devfeed.tech/tags/ai-assisted-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [config](<https://devfeed.tech/tags/config.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [gent-evaluation](<https://devfeed.tech/tags/gent-evaluation.md>), [mlops](<https://devfeed.tech/tags/mlops.md>), [repository](<https://devfeed.tech/tags/repository.md>), [versioning](<https://devfeed.tech/tags/versioning.md>)

### AI overview

Treat AGENTS.md as behavior-changing configuration: its claims can become stale, contradict current code, or grow so long that agents miss important guidance. Keep it short and factual, version it in git, review edits as behavior changes, and periodically check each line for truth and usefulness. The article recommends testing proposed changes against a small golden set by comparing agent outcomes with the old and new files; remove lines that do not improve behavior. Prefer verifiable repo facts and pointers to architecture documents over aspirations or untraceable tribal rules.

### Source excerpt

Outdated AGENTS.md instructions can undermine AI coding agents. Learn how versioning, pruning, and evaluations can keep repository guidance reliable.

## Context Graph Makes Haiku 5.5 23% faster, for 19% less money, in fewer steps

DevFeed: [Context Graph Makes Haiku 5.5 23% faster, for 19% less money, in fewer steps](<https://devfeed.tech/articles/context-graph-makes-haiku-5-5-23-faster-for-19-less-money-in-fewer-steps-90260.md>)

Original publisher: [Read original article](<https://blog.postman.com/context-graph-makes-haiku-5-5-23-faster-for-19-less-money-in-fewer-steps/>)

Author: Talia Kohan

Published: 2026-10-19T15:00:01Z

Content type: article

Language: en

Sources: [Postman](<https://devfeed.tech/sources/postman-blog.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-haiku-5-5](<https://devfeed.tech/tags/claude-haiku-5-5.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-graph](<https://devfeed.tech/tags/context-graph.md>), [general](<https://devfeed.tech/tags/general.md>), [git](<https://devfeed.tech/tags/git.md>), [github](<https://devfeed.tech/tags/github.md>), [postman](<https://devfeed.tech/tags/postman.md>)

### AI overview

A benchmark compared Claude Haiku 5.5 answering 17 engineering questions across 802 repositories with and without a Context Graph query. Across 102 runs, the graph-assisted approach used 20% fewer input tokens, made 9% fewer tool calls, cost 19% less, and reduced end-to-end answer time by 23%. Accuracy was roughly similar overall, while graph-assisted answers performed better on all nine cross-repository dependency questions. The results are limited by the benchmark's question set and checked-out code; the post notes that inventory questions need more work.

### Source excerpt

We ran 17 questions across 802 repos with and without the Context Graph. Haiku 5.5 was 19% cheaper and 23% faster. See the full benchmark. The post Context Graph Makes Haiku 5.5 23% faster, for 19% less money, in fewer steps appeared first on Postman Blog.

## Wix proposes page-local regions to simplify frontend code for AI agents

DevFeed: [Wix proposes page-local regions to simplify frontend code for AI agents](<https://devfeed.tech/articles/components-are-dead-and-now-for-something-completely-different-90000.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/components-are-dead-and-now-for-something-completely-different>)

Author: Wix Engineering

Published: 2026-10-19T11:08:20Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Fluent Design System](<https://devfeed.tech/topics/fluent-design.md>)

Tags: [all](<https://devfeed.tech/tags/all.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [ast](<https://devfeed.tech/tags/ast.md>), [complex](<https://devfeed.tech/tags/complex.md>), [data](<https://devfeed.tech/tags/data.md>), [design](<https://devfeed.tech/tags/design.md>), [design-system](<https://devfeed.tech/tags/design-system.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [execution](<https://devfeed.tech/tags/execution.md>), [frontend](<https://devfeed.tech/tags/frontend.md>)

### AI overview

Wix Engineering proposes a frontend architecture called Jay that flattens design-system templates into page-local HTML regions while keeping behavior in shared headless components. The post argues this can reduce runtime composition work and make code easier for AI agents to inspect and verify. It describes reactive updates, server-side rendering for static values, and CLI validation and synchronization to detect drift and preserve marked local edits.

### Source excerpt

Introduction The component abstraction was designed to solve a human cognitive limit: a developer cannot hold an entire UI hierarchy in their head, so we learned to encapsulate UI once and reference it across files. But as AI agents increasingly write and maintain frontend code, that trade-off inverted. Agents struggle with multi-file indirection and slot composition seams, but thrive on local context they can see and verify in a single file. Components are the abstraction for humans; regions...

## Knowledge graphs fuel AI innovation for financial services at Raymond James Financial

DevFeed: [Knowledge graphs fuel AI innovation for financial services at Raymond James Financial](<https://devfeed.tech/articles/knowledge-graphs-fuel-ai-innovation-for-financial-services-at-raymond-james-financial-88549.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/16/knowledge-graphs-ai-raymond-james-neo4j-neo4jgraphsummit/>)

Author: Mark Albertson

Published: 2026-10-16T16:42:53Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-operations](<https://devfeed.tech/tags/ai-operations.md>), [ai-reasoning](<https://devfeed.tech/tags/ai-reasoning.md>), [contextual-ai](<https://devfeed.tech/tags/contextual-ai.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data-governance](<https://devfeed.tech/tags/data-governance.md>), [data-relationships](<https://devfeed.tech/tags/data-relationships.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [explainable-ai](<https://devfeed.tech/tags/explainable-ai.md>), [financil-services](<https://devfeed.tech/tags/financil-services.md>), [graph-databases](<https://devfeed.tech/tags/graph-databases.md>), [graph-technology](<https://devfeed.tech/tags/graph-technology.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [graphsummit-2026](<https://devfeed.tech/tags/graphsummit-2026.md>), [jeff-griffith](<https://devfeed.tech/tags/jeff-griffith.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [knowledge-layer](<https://devfeed.tech/tags/knowledge-layer.md>), [naveen-mahankali](<https://devfeed.tech/tags/naveen-mahankali.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [neo4jgraphsummit](<https://devfeed.tech/tags/neo4jgraphsummit.md>), [news](<https://devfeed.tech/tags/news.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rai](<https://devfeed.tech/tags/rai.md>), [raymond-james](<https://devfeed.tech/tags/raymond-james.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [semantic-search](<https://devfeed.tech/tags/semantic-search.md>), [thecube](<https://devfeed.tech/tags/thecube.md>), [trustworthy-ai](<https://devfeed.tech/tags/trustworthy-ai.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

Raymond James uses Neo4j knowledge graphs to connect business data and provide trusted context for AI agents. The company evaluates agent outputs against established sources and is exploring dynamic data queries to help financial advisors analyze information. Its Raimond AI operations agent is also changing how employees handle routine work.

### Source excerpt

Knowledge graphs are becoming a critical context and reasoning layer for agentic AI, helping enterprises connect data and ground agents in key areas of business expertise. For diversified financial services companies such as Raymond James Financial Inc., graph technologies have become an important part of developing trustworthy infrastructure to support AI. The technology has been [...] The post Knowledge graphs fuel AI innovation for financial services at Raymond James Financial appeared first on SiliconANGLE.

## Uvi says its context platform cuts enterprise AI agent costs by reducing repeated information gathering

DevFeed: [Uvi says its context platform cuts enterprise AI agent costs by reducing repeated information gathering](<https://devfeed.tech/articles/developers-are-paying-frontier-prices-for-amnesia-uvi-wants-to-stop-the-agent-relearning-brain-drain-88469.md>)

Original publisher: [Read original article](<https://thenewstack.io/uvi-ai-agent-context/>)

Author: Adrian Bridgwater

Published: 2026-10-16T11:00:00Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [all](<https://devfeed.tech/tags/all.md>), [cost](<https://devfeed.tech/tags/cost.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>)

### AI overview

Uvi says its platform links company data and prior decisions so AI agents can retrieve relevant context without repeatedly searching systems such as Slack, Jira, and GitHub. In internal tests using more than 900 employee questions, the company reported that this approach reduced costs and response times compared with agents searching those systems directly; the tests were not independently verified.

### Source excerpt

Every time an AI agent has to trawl Slack threads, Jira tickets and old pull requests to piece together something The post "Developers are paying frontier prices for amnesia": Uvi wants to stop the agent relearning brain drain appeared first on The New Stack.

## Stolen AI API keys are paying for hackers' autonomous scans

DevFeed: [Stolen AI API keys are paying for hackers' autonomous scans](<https://devfeed.tech/articles/stolen-ai-api-keys-are-paying-for-hackers-autonomous-scans-88281.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/10/16/stolen-ai-api-keys-autonomous-scans/>)

Author: Anamarija Pogorelec

Published: 2026-10-16T05:00:24Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [token jacking](<https://devfeed.tech/topics/token-jacking.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-api](<https://devfeed.tech/tags/ai-api.md>), [ai-api-keys](<https://devfeed.tech/tags/ai-api-keys.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [api-security](<https://devfeed.tech/tags/api-security.md>), [bitsight](<https://devfeed.tech/tags/bitsight.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cybercrime](<https://devfeed.tech/tags/cybercrime.md>), [indirect-prompt-injection](<https://devfeed.tech/tags/indirect-prompt-injection.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [news](<https://devfeed.tech/tags/news.md>), [report](<https://devfeed.tech/tags/report.md>), [security](<https://devfeed.tech/tags/security.md>), [threat-intelligence](<https://devfeed.tech/tags/threat-intelligence.md>)

### AI overview

A threat intelligence review describes an autonomous hacking tool sold on a criminal forum that uses stolen OpenAI, Anthropic and Google API keys to run scans billed to the key owners. Bitsight tracked rising discussion of AI agents, indirect prompt injection and MCP across underground forums, alongside malicious plugins and other AI-enabled attacks. The article recommends scanning for exposed keys, verifying agent and MCP plugin sources, restricting coding-agent access, and monitoring for unusual automated logins.

### Source excerpt

A seller on a restricted criminal forum is marketing an autonomous hacking tool that runs on stolen OpenAI, Anthropic and Google API keys, so the key's owner pays for the scans. Bitsight's threat intelligence team tracked the shift across thousands of posts on 16 underground forums from February through August 2026. Over that window, mentions of AI agents, indirect prompt injection and the Model Context Protocol (MCP) rose 67 percent. Two groups are exposed. A ... More -> The post Stolen AI API keys are paying for hackers' autonomous scans appeared first on Help Net Security.

## Onboard your AI agents like new hires to prevent automated mistakes

DevFeed: [Onboard your AI agents like new hires to prevent automated mistakes](<https://devfeed.tech/articles/onboard-your-ai-agents-like-new-hires-to-prevent-automated-mistakes-88275.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4236060/onboard-your-ai-agents-like-new-hires-to-prevent-automated-mistakes.html>)

Author: mbarrett

Published: 2026-10-15T20:54:08Z

Content type: article

Language: en

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

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [trust](<https://devfeed.tech/topics/trust.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [context-layer](<https://devfeed.tech/tags/context-layer.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [has](<https://devfeed.tech/tags/has.md>), [institutional-knowledge](<https://devfeed.tech/tags/institutional-knowledge.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [storytype-brandpost](<https://devfeed.tech/tags/storytype-brandpost.md>)

### AI overview

The article argues that enterprises should onboard AI agents with task-specific context assembled from data, processes, and institutional knowledge. It recommends maintaining that context as a governed, versioned layer with access controls, human review, and portable standards, so agents can use relevant information as business conditions change.

### Source excerpt

Imagine a brand-new marketing hire being handed a spreadsheet and expected to execute a campaign on day one. Would you blame them if it went badly, when no one had explained customer profiles, conversion goals, or lead qualification criteria? AI agents may be the largest batch of new hires your company will bring on for years to come. Like any new employee, they start without the institutional knowledge their experienced colleagues have acquired on the job. They aren't familiar with your data assets, your company goals, or the semantics that make your business unique. Give an agent raw data without that context, and it will behave like a poorly trained employee, misinterpreting goals and concepts while bypassing required procedures. This is the context ceiling most enterprise AI pilots hit long before model intelligence becomes a limiting factor. How you onboard agents, and the context you feed them, will determine whether they become productive members of the enterprise or merely automate mistakes at great speed. Move beyond traditional data catalogs to onboard AI agents effectively For many enterprises, the obvious place to start onboarding agents is their existing data catalog. Give an agent access to the company's data and definitions, and it should have what it needs to get to work. The problem is that traditional catalogs were designed for human discovery, not the constantly changing, task-specific context that agents require. Much of that knowledge also lives elsewhere, spread across process documents, chat histories, data systems, and the accumulated know-how of experienced employees. We're moving from cataloging everything and searching it later to assembling context around intent. Agents need context organized around the job they're asked to do. If an agent is running a marketing campaign, it shouldn't have to sift through everything the company knows to find what matters. A context layer can start with the marketing task, pull in the relevant institutiona

## How an Agentic SDLC Platform Can Govern AI Agents Across Engineering

DevFeed: [How an Agentic SDLC Platform Can Govern AI Agents Across Engineering](<https://devfeed.tech/articles/how-to-set-up-a-software-factory-platform-guide-87520.md>)

Original publisher: [Read original article](<https://www.port.io/blog/agentic-sdlc-platform-foundation>)

Author: John Crowley

Published: 2026-10-15T08:51:09Z

Content type: article

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-sdlc](<https://devfeed.tech/tags/agentic-sdlc.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [platform](<https://devfeed.tech/tags/platform.md>), [sdlc](<https://devfeed.tech/tags/sdlc.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>)

### AI overview

The article argues that organizations need a shared agentic SDLC platform to manage AI agents built across engineering teams. It describes four functions: supplying shared context, orchestrating actions, registering agents and tools, and enforcing governance through scoped access, approvals, and audit records. It presents dLocal's dCoder as an example and positions Port as the platform layer providing these capabilities.

### Source excerpt

Learn why an agentic SDLC platform is the foundation to scale AI agents across your SDLC with governed context, access, and audit.

## Scuba launches with $34M to help teams and AI agents manage business data

DevFeed: [Scuba launches with $34M to help teams and AI agents manage business data](<https://devfeed.tech/articles/scuba-launches-with-34m-to-help-teams-and-ai-agents-manage-business-data-86441.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/13/scuba-launches-with-34m-to-help-teams-and-ai-agents-manage-business-data/>)

Author: Maria Deutscher

Published: 2026-10-13T22:59:06Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Managed Inference and Agents](<https://devfeed.tech/topics/managed-inference-and-agents.md>)

Tags: [accel](<https://devfeed.tech/tags/accel.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [data-management](<https://devfeed.tech/tags/data-management.md>), [funding](<https://devfeed.tech/tags/funding.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [homebrew](<https://devfeed.tech/tags/homebrew.md>), [investment](<https://devfeed.tech/tags/investment.md>), [news](<https://devfeed.tech/tags/news.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [scuba](<https://devfeed.tech/tags/scuba.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>)

### AI overview

Scuba, a productivity service that organizes work information in shared Collections and makes it available to AI tools through an MCP server, raised $34 million in two funding rounds. The company says its Capture tools gather materials such as notes, correspondence and media, while AI-generated Briefings summarize changes in Collections. Scuba plans to use the funding to expand engineering and go-to-market efforts.

### Source excerpt

Scuba, the developer of an eponymous productivity service, today announced that it has received $34 million in funding. The company raised the capital over two rounds. Accel led the first investment and co-led the second with IVP. The firms were joined by BoxGroup, Conviction, Homebrew and Scribble Ventures. Scuba also boasts a long list of [...] The post Scuba launches with $34M to help teams and AI agents manage business data appeared first on SiliconANGLE.

## Improving Deep Agents with harness engineering

DevFeed: [Improving Deep Agents with harness engineering](<https://devfeed.tech/articles/improving-deep-agents-with-harness-engineering-86205.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/improving-deep-agents-with-harness-engineering>)

Author: LangChain Accounts

Published: 2026-10-13T19:56:07Z

Content type: article

Language: en

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

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agent-delegation](<https://devfeed.tech/tags/agent-delegation.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [coding](<https://devfeed.tech/tags/coding.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [harness-engineering](<https://devfeed.tech/tags/harness-engineering.md>), [tracing](<https://devfeed.tech/tags/tracing.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

LangChain describes how changes to its coding-agent harness raised the agent's Terminal Bench 2.0 score from 52.8 to 66.5 while keeping the model fixed. Its approach uses trace analysis to identify failure patterns, then adjusts prompts, tools, middleware, and context. The article highlights build-and-verify loops, environment context, loop detection, and allocating reasoning compute to improve agent performance.

### Source excerpt

Harness engineering improved LangChain's coding agent from Top 30 to Top 5 on Terminal Bench using self-verification, tracing, and context optimization.

## Phasis develops platform for agentic orientation using World APIs and reality layers

DevFeed: [Phasis develops platform for agentic orientation using World APIs and reality layers](<https://devfeed.tech/articles/phasis-develops-platform-for-agentic-orientation-using-world-apis-and-reality-layers-85294.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/12/orienting-ai-agents-phasis-thecube-models-neo4jdatatoknowledge/>)

Author: Mark Albertson

Published: 2026-10-12T15:55:51Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [World models](<https://devfeed.tech/topics/world-models.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-luminaries](<https://devfeed.tech/tags/ai-luminaries.md>), [ai-ready-data](<https://devfeed.tech/tags/ai-ready-data.md>), [ai-roi](<https://devfeed.tech/tags/ai-roi.md>), [all](<https://devfeed.tech/tags/all.md>), [autonomous-systems](<https://devfeed.tech/tags/autonomous-systems.md>), [based](<https://devfeed.tech/tags/based.md>), [brandon-farley](<https://devfeed.tech/tags/brandon-farley.md>), [business](<https://devfeed.tech/tags/business.md>), [capital-markets](<https://devfeed.tech/tags/capital-markets.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [change](<https://devfeed.tech/tags/change.md>), [co-founder](<https://devfeed.tech/tags/co-founder.md>), [connected-data](<https://devfeed.tech/tags/connected-data.md>), [cube-event-coverage](<https://devfeed.tech/tags/cube-event-coverage.md>), [data-ai](<https://devfeed.tech/tags/data-ai.md>), [data-governance](<https://devfeed.tech/tags/data-governance.md>), [data-plus-ai-turning-data-into-knowledge-for-autonomous-systems-2026](<https://devfeed.tech/tags/data-plus-ai-turning-data-into-knowledge-for-autonomous-systems-2026.md>), [decision-intelligence](<https://devfeed.tech/tags/decision-intelligence.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [graph-databases](<https://devfeed.tech/tags/graph-databases.md>), [graph-technology](<https://devfeed.tech/tags/graph-technology.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [industrial-ai](<https://devfeed.tech/tags/industrial-ai.md>), [intelligent-automation](<https://devfeed.tech/tags/intelligent-automation.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [neo4jdatatoknowledge](<https://devfeed.tech/tags/neo4jdatatoknowledge.md>), [neo4jdatatoknowledge26eventpage](<https://devfeed.tech/tags/neo4jdatatoknowledge26eventpage.md>), [news](<https://devfeed.tech/tags/news.md>), [orienting-ai-agents](<https://devfeed.tech/tags/orienting-ai-agents.md>), [phasis](<https://devfeed.tech/tags/phasis.md>), [semantic-models](<https://devfeed.tech/tags/semantic-models.md>), [thecube](<https://devfeed.tech/tags/thecube.md>), [thecube-plus-nyse-wired](<https://devfeed.tech/tags/thecube-plus-nyse-wired.md>), [world-api](<https://devfeed.tech/tags/world-api.md>)

### AI overview

SiliconANGLE reports on Phasis, whose World API provides maintained, evidence-backed domain information to orient enterprise AI agents before they search, plan, or strategize. Its /orient endpoint returns relevant context, changes, supporting evidence, and uncertainties. Phasis says this can help agents stay grounded in changing circumstances.

### Source excerpt

When the founders at Phasis Inc. sought to develop a platform for orienting AI agents, they turned to graphs as a way to obtain a measurement of culture. The company wanted to better understand relations not just between people, but between a person and their values, beliefs and subcultures. The goal was to map culture [...] The post Phasis develops platform for agentic orientation using World APIs and reality layers appeared first on SiliconANGLE.

## Harness Knowledge Graph vs Port Context Lake: Key Differences

DevFeed: [Harness Knowledge Graph vs Port Context Lake: Key Differences](<https://devfeed.tech/articles/harness-knowledge-graph-vs-port-context-lake-key-differences-85005.md>)

Original publisher: [Read original article](<https://www.port.io/blog/harness-vs-port>)

Author: Michael Douglas

Published: 2026-10-11T12:58:11Z

Content type: comparison

Language: en

Sources: [Port](<https://devfeed.tech/sources/developer-experience-platform-engineering-blog-port.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agentic-sdlc](<https://devfeed.tech/tags/agentic-sdlc.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [argocd](<https://devfeed.tech/tags/argocd.md>), [cloud-native](<https://devfeed.tech/tags/cloud-native.md>), [compare](<https://devfeed.tech/tags/compare.md>), [data-modeling](<https://devfeed.tech/tags/data-modeling.md>), [engineering](<https://devfeed.tech/tags/engineering.md>)

### AI overview

The article compares Harness Knowledge Graph with Port Context Lake as approaches to representing software delivery and operational context. Harness focuses on deployment analysis and governance within its ecosystem. Port is presented as a way to model operational context across multiple tools, including service ownership, dependencies, incidents and infrastructure. The choice depends on whether an engineering organization needs Harness-centered deployment visibility or context spanning a heterogeneous SDLC stack.

### Source excerpt

Compare Harness Knowledge Graph and Port Context Lake across context coverage, ontology, integrations and operational actions.

[Next page](<https://devfeed.tech/topics/context-architecture.md?cursor=WyIyMDI2LTEwLTExVDEyOjU4OjExKzAwOjAwIiwgIjAzNmJkYzIzLTMzOTQtNGE0MS05ZDllLTYxYWZmNTUyNTYwZSJd>)