# supervisor agent pattern

A multi-agent architecture in which a coordinating agent dynamically assigns work to sub-agents and synthesizes their results.

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

## What Is an AI Agent? How Agents Work and Why They Fail

DevFeed: [What Is an AI Agent? How Agents Work and Why They Fail](<https://devfeed.tech/articles/what-is-an-ai-agent-how-agents-work-and-why-they-fail-141928.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-ai-agent>)

Author: Ruslan Sultanov

Published: 2026-11-18T18:39:05Z

Content type: article

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents-in-production](<https://devfeed.tech/tags/agents-in-production.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-examples](<https://devfeed.tech/tags/ai-agent-examples.md>), [ai-agent-vs-chatbot](<https://devfeed.tech/tags/ai-agent-vs-chatbot.md>), [ai-agent-vs-workflow](<https://devfeed.tech/tags/ai-agent-vs-workflow.md>), [ai-agents-explained](<https://devfeed.tech/tags/ai-agents-explained.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [customer](<https://devfeed.tech/tags/customer.md>), [days](<https://devfeed.tech/tags/days.md>), [fail](<https://devfeed.tech/tags/fail.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [how-do-ai-agents-work](<https://devfeed.tech/tags/how-do-ai-agents-work.md>), [jacket](<https://devfeed.tech/tags/jacket.md>), [loyalty](<https://devfeed.tech/tags/loyalty.md>), [order](<https://devfeed.tech/tags/order.md>), [policy](<https://devfeed.tech/tags/policy.md>), [return](<https://devfeed.tech/tags/return.md>), [table](<https://devfeed.tech/tags/table.md>), [types-of-ai-agents](<https://devfeed.tech/tags/types-of-ai-agents.md>), [what-is-an-ai-agent](<https://devfeed.tech/tags/what-is-an-ai-agent.md>), [window](<https://devfeed.tech/tags/window.md>)

### AI overview

AI agents use an LLM to choose steps, call tools, and adapt toward a goal, so they can act across systems rather than only reply. Compared with chatbots, they take actions; compared with code-defined LLM workflows, they are more flexible but harder to test and less predictable. The text recommends using the least autonomy needed, since fixed workflows can be cheaper and easier to debug. Production failures often stem from stale or irrelevant context, incorrect tool use, behavior drift, or excessive permissions. Suggested safeguards include tracing model and tool calls, monitoring source data, evaluating live outputs and tool paths, limiting permissions, requiring human approval for some actions, and assigning an owner. Multi-agent systems can divide larger tasks among specialists, but add failure points and require tracing across agents.

### Source excerpt

A customer asks whether they can still return a jacket. A chatbot would answer from what it was trained on. An AI agent looks up the order, checks the return policy table, sees the purchase was 34 days ago, notices the customer is a loyalty member with a 45-day window, and starts the return. Nobody ...

## Perplexity Computer Adds Multiagent: Up to 16 AI Agents That Cross-Check Work

DevFeed: [Perplexity Computer Adds Multiagent: Up to 16 AI Agents That Cross-Check Work](<https://devfeed.tech/articles/perplexity-computer-adds-multiagent-up-to-16-ai-agents-that-cross-check-work-139437.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/17/perplexity-computer-multiagent-effort-level/>)

Author: Michal Sutter

Published: 2026-11-17T22:52:04Z

Content type: article

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.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>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [claude](<https://devfeed.tech/tags/claude.md>), [computer](<https://devfeed.tech/tags/computer.md>), [cross](<https://devfeed.tech/tags/cross.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [effort](<https://devfeed.tech/tags/effort.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [harness](<https://devfeed.tech/tags/harness.md>), [lead](<https://devfeed.tech/tags/lead.md>), [models](<https://devfeed.tech/tags/models.md>), [multiagent](<https://devfeed.tech/tags/multiagent.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [other](<https://devfeed.tech/tags/other.md>), [perplexity](<https://devfeed.tech/tags/perplexity.md>), [perplexity-computer](<https://devfeed.tech/tags/perplexity-computer.md>), [post](<https://devfeed.tech/tags/post.md>), [share](<https://devfeed.tech/tags/share.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>), [up](<https://devfeed.tech/tags/up.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Perplexity Computer's Multiagent effort level lets a lead agent handle part of a task and coordinate up to 16 supporting agents. Agents can share findings, challenge assumptions, flag discrepancies and edit shared files; users interact with the lead, which combines results and updates affected agents when work changes. The described default team uses Claude Opus 5.5, GPT 6.1 Sol and Gemini 4 Carbon, with other models available when requested or needed. Unlike Ultra, where supporting agents report only to the lead, Multiagent allows direct agent-to-agent collaboration; Model Council instead gathers independent answers for comparison. It is available on the web to Perplexity Max subscribers. The excerpt reports no benchmarks, accuracy or speed figures, context length, or per-task credit cost.

### Source excerpt

Perplexity added Multiagent to Computer, an effort level above Ultra where a lead agent runs up to 16 agents on Claude, GPT and Gemini models that share findings and check each other's work. The post Perplexity Computer Adds Multiagent: Up to 16 AI Agents That Cross-Check Work appeared first on MarkTechPost.

## Building an Agent Factory for Data Migrations: a Small Test with Snowflake

DevFeed: [Building an Agent Factory for Data Migrations: a Small Test with Snowflake](<https://devfeed.tech/articles/building-an-agent-factory-for-data-migrations-a-small-test-with-snowflake-139492.md>)

Original publisher: [Read original article](<https://medium.com/snowflake/building-an-agent-factory-for-data-migrations-a-small-test-with-snowflake-9d4622c8f2c7?source=rss----34b6daafc07---4>)

Author: Eylon Steiner

Published: 2026-11-17T18:01:03Z

Content type: article

Language: en

Sources: [Snowflake Builders](<https://devfeed.tech/sources/snowflake-builders.md>)

Topics: [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [ai-experiments](<https://devfeed.tech/topics/ai-experiments.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [audit](<https://devfeed.tech/topics/audit.md>)

Tags: [agent-factory](<https://devfeed.tech/tags/agent-factory.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>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-migration](<https://devfeed.tech/tags/data-migration.md>), [data-migrations](<https://devfeed.tech/tags/data-migrations.md>), [database-migration](<https://devfeed.tech/tags/database-migration.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [proof-of-concept](<https://devfeed.tech/tags/proof-of-concept.md>), [snowflake](<https://devfeed.tech/tags/snowflake.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

A small Pagila proof of concept migrated PostgreSQL views and functions to Snowflake using parallel AI translators, scripted comparisons, and an independent AI verifier. Scripts handled dependency waves, deployed translations only in throwaway schemas, and compared results on real data and edge cases; human decisions were logged for reuse. All 15 tables passed 352 profile checks after a timestamp-precision bug in the check was fixed. Among 12 proven logic objects, repeated runs and one run with a cheaper translator passed, while planted-bug trials showed data diffs missed 3 of 5 bugs and edge tests caught all 5 (a small sample tested once). The author stresses that matching real data can be accidental, empty results prove little, and harness errors caused many apparent failures--so checks themselves need scrutiny.

### Source excerpt

Building an agent factory for data migrations: a small test with Snowflake How I moved a PostgreSQL database's views and functions to Snowflake with parallel AI agents, scripted checks and an independent AI reviewer, and what broke along the way. The short version I built a small proof of concept (PoC) of an "agent factory" for SQL migration: AI translators working in parallel, scripts that test every translation against the real data, and a second, independent AI whose only job is to find what the tests missed. The test case: Pagila, a public PostgreSQL sample database, moved to Snowflake. The goal of this architecture is to migrate a database's logic (views, functions, procedures), not just its data, at a scale where "one AI plus one human reviewer" stops working, and without ever letting an AI grade its own work: Scale: many objects translated in parallel, in dependency order. Trust: scripts prove every translation against the real data and edge cases, then an independent reviewer looks for what the scripts missed. Human time only where it matters: people answer clear questions the factory can't decide, and each answer is reused. Why a PoC: before using this on a real migration, I wanted to learn on something small and public which parts work, where the agents fail, and what the scripts must catch. The most useful lesson: matching data is not the same as correct logic. Some translations "matched" PostgreSQL on the real data purely by luck. If you have never built anything with AI agents, this post is for you. I explain every part. 1. The problem: copying tables is easy, copying logic is not A database migration has two halves: Data: tables and rows. Boring, mechanical, solved by tools. Code: views, functions and procedures written in the source's SQL dialect. Every one must be rewritten for the target and checked. The code half is where projects stall. A common setup today is "one AI assistant plus one human": the AI translates an object, the human reviews it, re

## Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation

DevFeed: [Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation](<https://devfeed.tech/articles/multi-llm-agentic-ai-at-the-edge-joint-agent-scheduling-and-resource-allocation-137630.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20915>)

Author: Yuanyan Song, Kezhi Wang, Xinmian Xu, Yongmin Li

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

Content type: article

Language: en

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

Topics: [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Operations research and optimization](<https://devfeed.tech/topics/operations-research-and-optimization.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.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-workflows](<https://devfeed.tech/tags/agentic-workflows.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-architecture](<https://devfeed.tech/tags/ai-architecture.md>), [ai-at-the-edge](<https://devfeed.tech/tags/ai-at-the-edge.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [approximation](<https://devfeed.tech/tags/approximation.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [edge](<https://devfeed.tech/tags/edge.md>), [energy](<https://devfeed.tech/tags/energy.md>), [llm](<https://devfeed.tech/tags/llm.md>), [resource](<https://devfeed.tech/tags/resource.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>)

### AI overview

The paper proposes an edge architecture in which a supervisor splits user requests into subtasks and dispatches them to worker agents through parallel or serial workflows, with a two-level retry mechanism. To reduce energy use while meeting latency and QoS constraints, an alternating-optimization scheme jointly handles agent selection and resource allocation. The parallel workflow allocates bandwidth; the serial workflow allocates service time using KKT conditions. Both address retrieval and agent selection, using SCA, Lagrangian relaxation, and Gale-Shapley or LLM-based algorithms. Simulations report lower energy consumption than benchmark schemes, and experiments using Qwen and Llama report improved task success rates.

### Source excerpt

arXiv:2611.20915v1 Announce Type: new Abstract: In this paper, an edge-enabled multi-large language model (LLM) agentic AI architecture is proposed, where one supervisor AI agent and multiple worker AI agents cooperatively execute users' requests at the edge. The supervisor AI agent decouples the user request into a series of sub-tasks and dynamically dispatches them to LLM-equipped worker AI agents via two agentic workflows, i.e., parallel and serial workflows, with a two-level retry mechanism to enhance execution reliability. To prolong the service duration of worker AI agents, the energy minimization problems are formulated by jointly considering AI agent selection and resource allocation, subject to task execution latency and quality of service (QoS) constraints. A resource allocation scheme based on alternating optimization (AO) is proposed. Specifically, for the parallel workflow, the scheme decouples the original problem into bandwidth allocation, retrieval selection and AI agent selection sub-problems, which are iteratively solved by the proposed successive convex approximation (SCA), Lagrangian relaxation (LR), and Gale-Shapley (GS) or LLM-based algorithms, respectively. For the serial workflow, the problem is similarly decoupled into service time allocation, retrieval selection and AI agent selection sub-problems; the optimal service time allocation is obtained via Karush-Kuhn-Tucker (KKT) conditions, while the latter two sub-problems are addressed by extending the proposed algorithms to the serial scenario. Simulation results show that the proposed resource allocation scheme can reduce system energy consumption compared with other benchmarks, while experiments on a multi-LLM agentic AI system based on Qwen and Llama demonstrate improved task execution success rates.

## WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection

DevFeed: [WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection](<https://devfeed.tech/articles/wevisforensics-self-evolving-agent-for-omni-ai-generated-video-detection-137688.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21373>)

Author: Yipeng Du, Yuxi Li, Ying Zhang, Chong Sun, Chen Li, Jing Lyu, Ying Tai

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

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>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Video Analytics](<https://devfeed.tech/topics/video-analytics.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-generated-video](<https://devfeed.tech/tags/ai-generated-video.md>), [annotations](<https://devfeed.tech/tags/annotations.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [audio](<https://devfeed.tech/tags/audio.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [call](<https://devfeed.tech/tags/call.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [detection](<https://devfeed.tech/tags/detection.md>), [domain](<https://devfeed.tech/tags/domain.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

WeVisForensics detects AI-generated videos by coordinating a main investigator with visual and audio forensic inspector agents. The investigator selects which artifact to inspect, the time window, and when to stop; shared feedback also helps refine the inspectors. Its dual-timescale policy optimization trains the investigator faster and improves inspectors more gradually using annotated artifact intervals. ForenCue-30K provides role-specific annotations, interaction trajectories, and a reinforcement-learning pool. The abstract reports 95.2% average detection accuracy across in-domain, out-of-domain, and agentic benchmarks, 9.0% above the strongest prior detector, with verdicts grounded in localized evidence.

### Source excerpt

arXiv:2611.21373v1 Announce Type: cross Abstract: Recent advances in video generation call for reliable detection grounded in explicit forensic evidence. However, current methods primarily depend on single-pass chain-of-thought reasoning that overlooks brief or localized artifacts, or on predefined multi-agent workflows that offer limited flexibility in selecting relevant inspections. Even with adaptive investigation, optimizing the investigation policy alone does not directly improve the forensic capabilities of fixed experts. We introduce WeVisForensics, an agentic framework in which a main investigator agent coordinates a self-evolving library of forensic inspector sub-agents spanning visual and audio cues. The investigator learns which artifact type to examine, over which window, and when to conclude, and these interactions provide shared feedback for both levels of agents. Our dual-timescale policy optimization strategy, DTPO, closes this loop through fast reinforcement learning of the investigator and slower refinement of the inspectors, guided by annotated artifact intervals, to report subtle artifacts they once dismissed. Furthermore, we curate ForenCue-30K, combining role-specific forensic annotations and interaction trajectories to supervise individual inspections and their coordination, with an accompanying reinforcement-learning pool. Experiments show that WeVisForensics averages 95.2% detection accuracy across in-domain, out-of-domain and agentic benchmarks, 9.0% above the strongest prior detector, while grounding its verdicts in localized evidence.

## Taxonomy of multi-agent design patterns, anti-patterns, and lessons from manufacturing

DevFeed: [Taxonomy of multi-agent design patterns, anti-patterns, and lessons from manufacturing](<https://devfeed.tech/articles/taxonomy-of-multi-agent-design-patterns-anti-patterns-and-lessons-from-manufacturing-136364.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/taxonomy-of-multi-agent-design-patterns-anti-patterns-and-lessons-from-manufacturing/>)

Author: Malini Sethi

Published: 2026-11-16T21:53:46Z

Content type: article

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Parallel reasoning](<https://devfeed.tech/topics/parallel-reasoning.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-loops](<https://devfeed.tech/tags/agent-loops.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automotive](<https://devfeed.tech/tags/automotive.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [aws](<https://devfeed.tech/tags/aws.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [cost](<https://devfeed.tech/tags/cost.md>), [design](<https://devfeed.tech/tags/design.md>), [design-patterns](<https://devfeed.tech/tags/design-patterns.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [distributed-systems](<https://devfeed.tech/tags/distributed-systems.md>), [framework](<https://devfeed.tech/tags/framework.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [taxonomy](<https://devfeed.tech/tags/taxonomy.md>)

### AI overview

The post recommends starting with deterministic Tier 1 workflows and using autonomous multi-agent coordination only when subtasks emerge during the work, since flexibility adds token cost, latency, and debugging burden. It distinguishes pipelines, conditional workflows, routers, and parallel workflows from plan-based orchestration, handoffs, shared conversations, and debate. It advises hard retry and token limits, schema-based handoffs, bounded agents, and approval gates for actions affecting customers or equipment. For manufacturing, it emphasizes p99 latency budgets and deterministic fallbacks, keeping PLC/SCADA/MES control deterministic, validating recommendations against current OT state before approved actuation, processing time-sensitive sensor data at the edge, and structuring agent memory and handoffs around shifts. AWS IoT Greengrass is named for edge monitoring; the supplied text does not detail the promised broader service mapping.

### Source excerpt

Multi-agent coordination is a distributed systems problem, not a model problem. This post gives a field-tested taxonomy of multi-agent design patterns and anti-patterns, a framework for deciding when multiple agents are warranted, and how to build cost-efficient, reliable systems on AWS.

## Making open models work for long-horizon agentic workloads

DevFeed: [Making open models work for long-horizon agentic workloads](<https://devfeed.tech/articles/making-open-models-work-for-long-horizon-agentic-workloads-141159.md>)

Original publisher: [Read original article](<https://ollama.com/blog/open-models-long-horizon-agents>)

Published: 2026-11-16T00:00:00Z

Content type: article

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>)

Tags: [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [cache](<https://devfeed.tech/tags/cache.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [prefix-caching](<https://devfeed.tech/tags/prefix-caching.md>), [prompts](<https://devfeed.tech/tags/prompts.md>), [routing](<https://devfeed.tech/tags/routing.md>)

### AI overview

Long coding-agent sessions repeatedly resend the full conversation while producing short tool calls, so preserving prefix-cache hits can reduce repeated prompt processing. The harness should keep early prompt content stable, place changing session details in the task message, choose reasoning effort at the start, disclose when tool output is truncated, and avoid giving subagents irrelevant history. Loading tools at the end can preserve the cached prefix, but some model templates do not support it. The inference engine must route turns to a node holding the cache and keep idle caches available; routing may choose a cache miss if the warm node is overloaded. The article describes offloading idle caches to CPU memory, paged cache allocation, continuous batching, and separate prefill and decode clusters. Caching reduces recomputation but is not free: cached tokens still consume memory and attention work.

### Source excerpt

Prefix caching helps coding agents stay fast as conversations grow. Prompts, tool calls, and inference routing determine how much work the model can reuse.

## Introducing groundcover Investigations - collaboration ground for your agents and engineers

DevFeed: [Introducing groundcover Investigations - collaboration ground for your agents and engineers](<https://devfeed.tech/articles/introducing-groundcover-investigations-collaboration-ground-for-your-agents-and-engineers-134507.md>)

Original publisher: [Read original article](<https://www.groundcover.com/blog/introducing-groundcover-investigations>)

Author: Anais Dotis

Published: 2026-11-15T10:00:00Z

Content type: article

Language: en

Sources: [Ground Cover](<https://devfeed.tech/sources/ground-cover.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Slack](<https://devfeed.tech/topics/slack.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [about](<https://devfeed.tech/tags/about.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [alert](<https://devfeed.tech/tags/alert.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [away](<https://devfeed.tech/tags/away.md>), [branch](<https://devfeed.tech/tags/branch.md>), [but](<https://devfeed.tech/tags/but.md>), [call](<https://devfeed.tech/tags/call.md>), [can](<https://devfeed.tech/tags/can.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [faster](<https://devfeed.tech/tags/faster.md>), [groundcover](<https://devfeed.tech/tags/groundcover.md>), [incidents](<https://devfeed.tech/tags/incidents.md>), [investigations](<https://devfeed.tech/tags/investigations.md>)

### AI overview

groundcover Investigations gives engineers and agents one shared, structured record for incident work. Investigations organize hypotheses, telemetry findings, and assessments as supported, refuted, or open, so teams can see what has been checked, what remains unresolved, and what evidence supports conclusions. Its investigator researches issues and can query telemetry or split work into sub-investigations; a separate moderator checks whether findings support proposed conclusions, and only the moderator can resolve a hypothesis. Teams can also use their own agents through MCP, with contributions attributed to their source. Slack carries concise progress updates and accepts team input, while the full investigation tree, queries, and visualizations remain in groundcover. Investigations can currently start from a groundcover monitor issue or Slack; automatic starts when selected monitors fire are described as planned.

### Source excerpt

Meet groundcover Investigations, a shared workspace where engineers and AI agents collaborate, investigate incidents, validate evidence, and resolve issues faster.

## Google adds multi-model Orchestrator, Gemini 4 Hydrogen, to Antigravity

DevFeed: [Google adds multi-model Orchestrator, Gemini 4 Hydrogen, to Antigravity](<https://devfeed.tech/articles/google-adds-multi-model-orchestrator-gemini-4-hydrogen-to-antigravity-132376.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4248403/google-adds-multi-model-orchestrator-gemini-4-hydrogen-to-antigravity.html>)

Author: Anirban Ghoshal

Published: 2026-11-13T12:37:34Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Model Routing](<https://devfeed.tech/topics/model-routing.md>), [code security](<https://devfeed.tech/topics/code-security.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-powered-development](<https://devfeed.tech/tags/ai-powered-development.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [argon](<https://devfeed.tech/tags/argon.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [builds](<https://devfeed.tech/tags/builds.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [combines](<https://devfeed.tech/tags/combines.md>), [configure](<https://devfeed.tech/tags/configure.md>), [consulting](<https://devfeed.tech/tags/consulting.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [google](<https://devfeed.tech/tags/google.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [orchestrator](<https://devfeed.tech/tags/orchestrator.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Antigravity's Orchestrator automatically hands coding work between a planning model and Gemini 4 Hydrogen within one response. Carbon or Argon first explores the codebase, identifies dependencies, resolves ambiguities, and plans; Hydrogen edits files, writes code, and runs builds and tests. If it hits repeated test failures or unexpected behavior, it returns control to the planner to revise the plan. Unlike conventional routing that assigns an entire task to one selected model, Orchestrator transfers control as work progresses without manual switching or configuration. The excerpt says Carbon planning is available to Google AI Ultra subscribers and Argon planning to Pro and Ultra subscribers; Hydrogen can also be selected alone. Hydrogen has a 1-million-token context window and costs $1.50 per million input tokens and $7.50 per million output tokens. Analysts suggest task-specific model use could improve productivity and token efficiency, while raising questions about model-level attribution, auditability, credential access, human approval, and handling of source code and intellectual property. The excerpt does not establish measured productivity or cost savings.

### Source excerpt

Google is adding a new feature, Orchestrator, to Antigravity, its AI-powered development environment, to help enterprises improve software development efficiency by automatically coordinating multiple Gemini models, including the newly introduced Gemini 4 Hydrogen. The new feature, which allows developers to delegate planning, coding, and review tasks to different models within a single coding session, combines a planning model, such as Gemini 4 Carbon or Argon, with Hydrogen, which the hyperscaler describes as a lighter execution model. While the planner models explore the codebase, identify dependencies, and develop an implementation plan, Hydrogen handles execution, including editing files, writing code, and running builds and tests, the hyperscaler wrote in a blog post. That execution differs from conventional model routing, which typically selects a model based on a prompt and assigns it the entire task. Orchestrator, instead, transfers control between the planning and execution models as work progresses, with the planning model first exploring the codebase, identifying dependencies, resolving ambiguities, and preparing an implementation plan before handing control to Hydrogen for execution, the hyperscaler explained in the feature's documentation. Hydrogen hands control back to the planner if it encounters problems, such as repeated test failures or unexpected behavior, allowing the latter to reassess the execution and revise the plan before Hydrogen resumes implementation, according to the documentation. These handoffs, the hyperscaler said, happen automatically within a single response, without developers having to manually switch models or configure the transitions. Improved developer productivity, reduced token consumption The new Orchestrator's ability to use different models for different tasks in a single coding session is likely to boost productivity for developers, according to Pareekh Jain, principal analyst at Pareekh Consulting. "This is like pairi

## Inside an enterprise AI agent: A governed, observable loop architecture

DevFeed: [Inside an enterprise AI agent: A governed, observable loop architecture](<https://devfeed.tech/articles/inside-an-enterprise-ai-agent-a-governed-observable-loop-architecture-132421.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/inside-an-enterprise-ai-agent-a-governed-observable-loop-architecture/>)

Author: Rushabh Lokhande

Published: 2026-11-12T19:31:28Z

Content type: article

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [set up event-driven architecture AWS](<https://devfeed.tech/topics/set-up-event-driven-architecture-aws.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-runtime](<https://devfeed.tech/tags/agent-runtime.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-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [api](<https://devfeed.tech/tags/api.md>), [api-gateway](<https://devfeed.tech/tags/api-gateway.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [avoid](<https://devfeed.tech/tags/avoid.md>), [aws](<https://devfeed.tech/tags/aws.md>), [control](<https://devfeed.tech/tags/control.md>), [cross](<https://devfeed.tech/tags/cross.md>), [design](<https://devfeed.tech/tags/design.md>), [design-patterns](<https://devfeed.tech/tags/design-patterns.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [enterprise-ai-agents](<https://devfeed.tech/tags/enterprise-ai-agents.md>), [inside](<https://devfeed.tech/tags/inside.md>), [observable](<https://devfeed.tech/tags/observable.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

The article presents a five-layer AWS reference architecture for enterprise agents: an API gateway enforces identity and policy; a five-phase runtime understands, plans, retrieves, reasons, then acts and observes; knowledge and state provide RAG, memory, and session data; platform services supply models, tools, secrets, and events; and trust controls and governance span the system. Every tool call passes permission, input, policy, rate, and budget checks, while destructive actions can require approval. Step-level traces capture execution paths, tool status, latency, and token use; output gates check safety, groundedness, confidence, and human approval for high-risk actions. Recommended safeguards include least privilege, read-only starts with graduated autonomy, explicit tool schemas, model routing by task, and hard limits on iterations, time, and tokens with escalation paths. AWS service mappings are starting points to tune for workload, residency, latency, and cost; the article notes compliance remains the customer's responsibility under AWS's shared responsibility model.

### Source excerpt

This post lays out a five-layer reference architecture for governed, observable enterprise AI agents on AWS: an API gateway, a five-phase agent runtime, a knowledge and state tier, platform services, and a cross-cutting trust and control framework. Each layer maps to managed AWS services, with the design patterns worth copying and the mistakes to avoid.

## Build composable, interoperable multi-agent systems with A2A on AWS

DevFeed: [Build composable, interoperable multi-agent systems with A2A on AWS](<https://devfeed.tech/articles/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws-130561.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws/>)

Author: Amit Chaudhary

Published: 2026-11-12T15:42:21Z

Content type: article

Language: en

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

Topics: [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [Amazon GuardDuty](<https://devfeed.tech/topics/amazon-guardduty.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [build](<https://devfeed.tech/tags/build.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [framework](<https://devfeed.tech/tags/framework.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-system](<https://devfeed.tech/tags/multi-agent-system.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [systems](<https://devfeed.tech/tags/systems.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The reference architecture shows cross-organization agents collaborating through A2A without sharing secrets or depending on each other's framework: a LangChain orchestrator on ECS calls a Strands compliance agent on Bedrock AgentCore, which calls back to an enterprise context agent for account metadata. Agent Cards expose curated skills for discovery and routing; OAuth JWTs from separate Cognito user pools authenticate calls in both directions. The deployment uses three Jupyter notebooks across two AWS accounts, with synthetic compliance findings, an end-to-end test, and token rejection checks. The sample requires specified AWS accounts, model access and Jupyter setup, incurs resource charges, and is intended for sandbox use; production adaptations are outlined, including stronger client authentication and private connectivity.

### Source excerpt

Build a composable, interoperable multi-agent system on AWS with the Agent-to-Agent (A2A) protocol. A LangChain orchestrator on Amazon ECS communicates with a Strands agent on Amazon Bedrock AgentCore across organizational boundaries, using bidirectional, OAuth-authenticated calls, with neither side depending on the other's framework or SDK.

## Agentic Attribution of Cloud Resource Ownership

DevFeed: [Agentic Attribution of Cloud Resource Ownership](<https://devfeed.tech/articles/agentic-attribution-of-cloud-resource-ownership-126105.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11340>)

Author: Tiltan Gilat, Gal Engelberg, Ariel Zadok, Leon Goldberg

Published: 2026-11-10T05:00:00Z

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: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [ownership](<https://devfeed.tech/tags/ownership.md>), [resource](<https://devfeed.tech/tags/resource.md>)

### AI overview

The proposed architecture derives cloud resource ownership from organizational records instead of relying on manually maintained owner tags or CMDB entries. It first profiles an organization into tested signal procedures and an ownership playbook, then uses a coordinator and parallel investigator agents to trace relationships between resources and people or teams; rules calculate confidence. In an evaluation covering 100 resources across 50 AWS resource types at one organization, its candidates pooled with those from an unprimed general-purpose agent achieved 92.1% weighted recall and 86.6% weighted precision, compared with 54.8% and 77.4%, at 0.55 times the general-purpose agent's cost per unit of coverage. The reported improvement came from identifying people who build or change resources without an explicit owner, using work records and code history. The evidence is limited to this single-organization evaluation.

### Source excerpt

arXiv:2611.11340v1 Announce Type: cross Abstract: Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resource it concerns. Ownership is the organizational context that decides who that is. Where recorded, it is declared by hand in configuration management databases or owner tags and goes stale unless kept current; accounts are shared, and automation creates much of the infrastructure. The knowledge sits in work records, code history, audit logs and identity directories, encoded in each organization's own conventions. Recovering it poses four challenges: the signal is scattered across sources, none of them authoritative; the conventions that carry it differ between organizations; reaching an owner takes multi-hop links; and those related to a resource differ in the strength of their relation. We define ownership as a set of entities, people or teams, each related to the resource by one of five patterns ordered by strength. We present a reference architecture for agentic ownership attribution that derives ownership from these records instead of declaring it: it profiles an organization offline into tested signal procedures and an ownership playbook, then attributes each resource with a coordinator agent and parallel investigators, with confidence computed by rules. On 100 resources of 50 Amazon Web Services (AWS) resource types in one organization, we pool the architecture's candidates with those of an unprimed general-purpose agent and verify every evidence piece against the records. The architecture reaches 92.1% weighted recall and 86.6% weighted precision, against 54.8% and 77.4%, at 0.55 times the agent's cost per unit of coverage. The difference lies in people who build and change resources without an explicit owner, found through work records and code history.

## DeepSeek's Super-Agent Moves the Attention Bottleneck From Your Feed to Your Agents

DevFeed: [DeepSeek's Super-Agent Moves the Attention Bottleneck From Your Feed to Your Agents](<https://devfeed.tech/articles/deepseek-s-super-agent-moves-the-attention-bottleneck-from-your-feed-to-your-agents-124209.md>)

Original publisher: [Read original article](<https://hackernoon.com/deepseeks-super-agent-moves-the-attention-bottleneck-from-your-feed-to-your-agents?source=rss>)

Author: Doomscroll

Published: 2026-11-09T18:58:18Z

Content type: article

Language: en

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

Topics: [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [attention](<https://devfeed.tech/tags/attention.md>), [attention-economy](<https://devfeed.tech/tags/attention-economy.md>), [capability](<https://devfeed.tech/tags/capability.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [deepseek-attention-economy](<https://devfeed.tech/tags/deepseek-attention-economy.md>), [deepseek-harness-engineering](<https://devfeed.tech/tags/deepseek-harness-engineering.md>), [deepseek-super-agent](<https://devfeed.tech/tags/deepseek-super-agent.md>), [hackernoon-top-story](<https://devfeed.tech/tags/hackernoon-top-story.md>), [harness-engineering](<https://devfeed.tech/tags/harness-engineering.md>)

### AI overview

DeepSeek argues that human attention, rather than model capability, limits parallel agent work: a person can actively track only three to five sessions. Its Super-agent prototype uses a long-lived Router to dispatch isolated Worker sessions, run tasks continuously and proactively, and surface work without requiring users to track each session. In simulated workloads it completed tasks in a median 12.4 minutes versus 20.4 minutes for a single-session agent; DeepSeek says it is a research prototype, not an official product, and the tests do not establish performance in real multi-user settings. The essay's link to the attention economy remains a possibility, not a demonstrated shift: consumer platforms and ad markets remain dominant. The source also stresses that open harnesses can grant models access to files, commands, and other real-world actions, making human approval boundaries such as "do not merge or change anything on your own" a key safety choice.

### Source excerpt

DeepSeek's Super-agent essay says human attention, not model capability, now limits multi-agent work. Is it an obituary for the attention economy?

## How to Build Multi-Agent Systems with the OpenAI Agents SDK

DevFeed: [How to Build Multi-Agent Systems with the OpenAI Agents SDK](<https://devfeed.tech/articles/how-to-build-multi-agent-systems-with-the-openai-agents-sdk-122659.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/how-to-build-multi-agent-systems-with-the-openai-agents-sdk/>)

Author: Shuai Guo

Published: 2026-11-08T15:00:00Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [build](<https://devfeed.tech/tags/build.md>), [building](<https://devfeed.tech/tags/building.md>), [data](<https://devfeed.tech/tags/data.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [fan](<https://devfeed.tech/tags/fan.md>), [first](<https://devfeed.tech/tags/first.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-agents](<https://devfeed.tech/tags/openai-agents.md>), [openai-agents-sdk](<https://devfeed.tech/tags/openai-agents-sdk.md>), [post](<https://devfeed.tech/tags/post.md>), [python](<https://devfeed.tech/tags/python.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [support](<https://devfeed.tech/tags/support.md>), [systems](<https://devfeed.tech/tags/systems.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The excerpt distinguishes two OpenAI Agents SDK delegation patterns. With `specialist_agent.as_tool(...)`, a coordinating agent calls specialists for bounded subtasks, stays active, and combines their results; the EV purchase adviser uses vehicle, charging, and ownership-cost researchers this way. With `handoffs=[...]`, the initial agent routes a request and the specialist takes control and produces the final response; the EV support agent routes a public-charging question to a charging specialist. The excerpt presents fan-out/fan-in as centralized parallel work, pipelines as sequential chains, hierarchies as recursive agent-as-tool relationships, evaluator-optimizers as centralized loops, and swarms as dynamic peer-to-peer handoffs. These patterns combine delegation, topology, and execution choices.

### Source excerpt

Build an EV purchase adviser and a support agent in Python, then see how fan-out, pipelines, hierarchies, and swarms reuse the same building blocks. The post How to Build Multi-Agent Systems with the OpenAI Agents SDK appeared first on Towards Data Science.

## Why AWS wants developers to stop babysitting their AI agents

DevFeed: [Why AWS wants developers to stop babysitting their AI agents](<https://devfeed.tech/articles/why-aws-wants-developers-to-stop-babysitting-their-ai-agents-122221.md>)

Original publisher: [Read original article](<https://thenewstack.io/kiro-bots-agent-memory/>)

Author: Adrian Bridgwater

Published: 2026-11-07T15:30:00Z

Content type: news

Language: en

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

Topics: [Kiro](<https://devfeed.tech/topics/kiro.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [least privilege](<https://devfeed.tech/topics/least-privilege.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [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>), [automation](<https://devfeed.tech/tags/automation.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [aws](<https://devfeed.tech/tags/aws.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development](<https://devfeed.tech/tags/development.md>), [development-environment](<https://devfeed.tech/tags/development-environment.md>), [kiro](<https://devfeed.tech/tags/kiro.md>), [kiro-crew](<https://devfeed.tech/tags/kiro-crew.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [spec-driven](<https://devfeed.tech/tags/spec-driven.md>), [spec-driven-development](<https://devfeed.tech/tags/spec-driven-development.md>)

### AI overview

AWS introduced Kiro bots to manage ongoing development responsibilities and parallel agent sessions. Each named bot keeps editable memory in a notes file, uses only the tools and permissions granted for its role, and can redirect drifting sessions and combine their results. Developers can set routines and give bots ongoing direction. Bots may request more authority but cannot grant it themselves; a deployment bot can require approval before each change, while a research bot can be limited to reading and searching. Work that does not depend on a human decision can continue while the bot waits. Bots cannot delegate to one another, and developers define how their roles connect. The excerpt describes Kiro's launch and setup, but gives no independent evaluation of its performance.

### Source excerpt

AWS first introduced Kiro, its agentic, spec-driven development environment, in July 2025. It also introduced Kiro Crew in August of The post Why AWS wants developers to stop babysitting their AI agents appeared first on The New Stack.

## Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy Improvement

DevFeed: [Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy Improvement](<https://devfeed.tech/articles/learning-multi-agent-orchestration-higher-order-interactions-in-policy-improvement-120623.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07495>)

Author: Kaixuan Liu, Guojun Xiong

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [learning](<https://devfeed.tech/tags/learning.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-orchestration](<https://devfeed.tech/tags/multi-agent-orchestration.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [performance](<https://devfeed.tech/tags/performance.md>), [policy](<https://devfeed.tech/tags/policy.md>)

### AI overview

IAPO addresses a limitation in training LLM multi-agent orchestrators: the value of one decision depends on preceding decisions, so separate per-decision advantages can miss gains from joint updates. The framework decomposes policy performance differences into individual effects and interactions, then optimizes both from sampled trajectories while certifying each update as an improvement. The abstract reports that interactions can account for half of attainable gain. On long-input GSM8K, MATH, DROP, MBPP, and HumanEval, IAPO's deployed plans reached the strongest accuracy among 15 published multi-agent and workflow-search systems using the same 7B executor, with fewer tokens; removing the interaction term reduced code accuracy by 7-17 points.

### Source excerpt

arXiv:2611.07495v1 Announce Type: new Abstract: Learned orchestration has emerged as a promising paradigm for large language model (LLM)-based multi-agent systems, in which a central orchestrator selects agents and controls the information they receive throughout a task. Despite rapid empirical progress, existing methods train the orchestrator by crediting each decision with its own advantage, implicitly assuming that the other decisions in the episode stay fixed. This assumption fails in orchestration, where the contribution of each decision to the final outcome depends on the decisions preceding it, so the gain of a joint update is not the sum of its per-decision effects. To address this challenge, we introduce \textbf{IAPO}, an interaction-aware policy optimization framework that explicitly accounts for interactions among decisions. Specifically, IAPO exactly decomposes the performance difference between two policies into the effects of individual decisions and their interactions, which we prove can account for half of the attainable gain, and then optimizes both from sampled trajectories while certifying that every update is an improvement. On long-input versions of GSM8K, MATH, DROP, MBPP and HumanEval, against fifteen published multi-agent and workflow-search systems on the same 7B executor, IAPO's deployed plans reach the strongest system's accuracy with fewer tokens, and removing the interaction term costs 7 to 17 points of accuracy on code.

## Agents Are Going Async

DevFeed: [Agents Are Going Async](<https://devfeed.tech/articles/agents-are-going-async-119838.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/agents-are-going-async>)

Author: LangChain Accounts

Published: 2026-11-05T20:03:27Z

Content type: tutorial

Language: en

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

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [async](<https://devfeed.tech/topics/async.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [hierarchical agent systems](<https://devfeed.tech/topics/hierarchical-agent-systems.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>), [Langgraph](<https://devfeed.tech/topics/langgraph.md>)

Tags: [added](<https://devfeed.tech/tags/added.md>), [addition](<https://devfeed.tech/tags/addition.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-infrastructure](<https://devfeed.tech/tags/agent-infrastructure.md>), [agents](<https://devfeed.tech/tags/agents.md>), [also](<https://devfeed.tech/tags/also.md>), [api](<https://devfeed.tech/tags/api.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [async](<https://devfeed.tech/tags/async.md>), [background](<https://devfeed.tech/tags/background.md>), [deep](<https://devfeed.tech/tags/deep.md>), [let](<https://devfeed.tech/tags/let.md>), [notifications](<https://devfeed.tech/tags/notifications.md>), [responsive](<https://devfeed.tech/tags/responsive.md>), [run](<https://devfeed.tech/tags/run.md>), [subagents](<https://devfeed.tech/tags/subagents.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [work](<https://devfeed.tech/tags/work.md>), [workers](<https://devfeed.tech/tags/workers.md>)

### AI overview

Async subagents let an orchestrator stay available while long-running work proceeds in the background. In Deep Agents, `start_async_task` returns immediately; the orchestrator can check, update, cancel, or list tasks, and workers report results when they finish. Follow-ups either interrupt and restart a task (the default) or enqueue instructions for after it finishes. Notifications behave differently depending on whether the orchestrator is busy, idle, or awaiting approval; approval requests remain on the subagent's thread, and Managed Deep Agents on Slack posts them to the original thread. Async subagents are available in Deep Agents for Python and JavaScript and Managed Deep Agents. Task notifications are in beta, so the API may change.

### Source excerpt

Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.

## AWS launches Kiro bots to help devs coordinate AI coding agents

DevFeed: [AWS launches Kiro bots to help devs coordinate AI coding agents](<https://devfeed.tech/articles/aws-launches-kiro-bots-to-help-devs-coordinate-ai-coding-agents-119422.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4245120/aws-launches-kiro-bots-to-help-devs-coordinate-ai-coding-agents.html>)

Author: Anirban Ghoshal

Published: 2026-11-05T19:00:00Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Kiro](<https://devfeed.tech/topics/kiro.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bots](<https://devfeed.tech/tags/bots.md>), [coding-tasks](<https://devfeed.tech/tags/coding-tasks.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [kiro](<https://devfeed.tech/tags/kiro.md>), [kiro-crew](<https://devfeed.tech/tags/kiro-crew.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [memory](<https://devfeed.tech/tags/memory.md>), [notes](<https://devfeed.tech/tags/notes.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [persistent-memory](<https://devfeed.tech/tags/persistent-memory.md>), [software](<https://devfeed.tech/tags/software.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Kiro bots in Kiro Crew coordinate parallel worker-agent sessions for assigned development responsibilities: they monitor progress, redirect work, consolidate results, and can request approval while unrelated tasks continue. Each bot keeps editable or deletable Notes about project requirements, preferences, decisions, and constraints, and can use that context in recurring scheduled tasks. AWS also describes Dashboards for visualizing bot activity and reports. The excerpt says this orchestration may reduce developers' session-management burden, but parallel retries and tool calls can increase token and compute costs. It recommends evaluating bounded workflows by correctness, review time, and operating cost, and considering conventional automation where judgment is unnecessary. Analysts also raise traceability, inconsistent behavior as Notes evolve, and permission creep concerns, recommending scoped identities, budget guardrails, and centralized telemetry.

### Source excerpt

AWS on Thursday launched Kiro bots, generally available within Kiro Crew, its open-source multi-agent development environment, to help developers coordinate parallel coding tasks, maintain context across sessions, and automate recurring software development workflows. Kiro bots are designed to take responsibility for specific parts of a developer's workflow rather than execute isolated tasks within individual agent sessions, in turn addressing the growing coordination burden developers face as they increasingly rely on multiple AI agents to handle software development tasks in parallel, AWS said in a statement. Setting up bots and how do they work Developers can create a bot by opening the Customize section in Kiro Crew and selecting the "Add a bot" option, where they can choose either a default agent or an existing custom agent as its foundation. Each bot can be assigned a specific responsibility, such as issue triage, build monitoring, or release readiness, and customized with its own name, avatar, instructions, tools, and permissions based on the tasks it is expected to handle, the hyperscaler said. Developers can use each bot to launch multiple worker-agent sessions in parallel and have it monitor their progress, redirect those that deviate from the plan, and consolidate their results. If a task requires their input or a decision, the bot can seek their approval while continuing with other tasks that do not depend on it, it added. To maintain continuity across sessions, each bot also maintains its own persistent memory through a feature AWS calls Notes. These Notes capture a bot's understanding of projects, including developer preferences, previously made decisions, project requirements, and constraints gathered through its work and feedback from developers. The accumulated context helps each bot apply the same instructions and judgment to subsequent tasks without developers having to repeatedly explain their expectations, the hyperscaler said. This persistent c

## ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events

DevFeed: [ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events](<https://devfeed.tech/articles/elecload-adaptive-electricity-load-forecasting-guided-by-multiple-events-118477.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06508>)

Author: Huajian Zhang, Mingyue Cheng, Xingpeng Gao, Xiaoyu Tao, Zhiding Liu, Jiqian Yang, Zhi Li

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

Content type: article

Language: en

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

Topics: [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [electricity](<https://devfeed.tech/tags/electricity.md>), [events](<https://devfeed.tech/tags/events.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [load](<https://devfeed.tech/tags/load.md>)

### AI overview

ElecLoad uses event context to shape how electricity load forecasts are produced. It analyzes events' relevance, timing, and interactions, then chooses to forecast the full horizon at once or divide it into segments where event effects change. For segmented horizons, sub-agents forecast each segment; a main agent reviews their results and guides selective refinement. Tests on multiple electricity-load datasets reportedly achieved state-of-the-art performance in most evaluation scenarios. The supplied abstract does not specify datasets, metrics, or how often each forecasting strategy is selected.

### Source excerpt

arXiv:2611.06508v1 Announce Type: new Abstract: Accurate electricity load forecasting provides critical decision support for energy procurement, generation scheduling, and supply-demand balancing, contributing to the economic efficiency and operational reliability of power systems. However, future electricity demand can be affected by the complex interplay of multiple events described in Web notices, weather alerts, and event schedules. Their effects vary over time and can reinforce or offset one another, making electricity load difficult to forecast accurately. While existing methods can incorporate context as additional input, how to use the effects of multiple events and their interactions to guide the load forecasting process itself remains to be explored. To address this gap, we propose ElecLoad, a context-aware agent for multi-event electricity load forecasting that adaptively organizes the forecasting process. Specifically, we train ElecLoad to combine historical load with context to analyze each event's relevance to the target load, the timing of its effects, and potential interactions among events. Guided by this analysis, ElecLoad adaptively chooses to forecast the entire forecast horizon directly or to partition it into segments according to changes in event effects. When the horizon is partitioned, sub-agents independently generate initial forecasts for each segment. The main agent then reviews these forecasts, and the sub-agents perform selective refinement guided by its feedback. Experiments on multiple electricity load datasets show that ElecLoad achieves state-of-the-art performance in most evaluation scenarios. Code is available at https://github.com/zhjai/ElecLoad.

## Four layers of context engineering for production AI agents: How Deep Insight applies them in working code

DevFeed: [Four layers of context engineering for production AI agents: How Deep Insight applies them in working code](<https://devfeed.tech/articles/four-layers-of-context-engineering-for-production-ai-agents-how-deep-insight-applies-them-in-working-code-117737.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/four-layers-of-context-engineering-for-production-ai-agents-how-deep-insight-applies-them-in-working-code/>)

Author: Yoonseo Kim

Published: 2026-11-04T16:30:40Z

Content type: article

Language: en

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

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Code Modularity](<https://devfeed.tech/topics/code-modularity.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [context-management](<https://devfeed.tech/tags/context-management.md>), [data-analysis](<https://devfeed.tech/tags/data-analysis.md>), [framework](<https://devfeed.tech/tags/framework.md>), [layer](<https://devfeed.tech/tags/layer.md>), [layers](<https://devfeed.tech/tags/layers.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [production](<https://devfeed.tech/tags/production.md>), [production-ai](<https://devfeed.tech/tags/production-ai.md>), [strands-agents](<https://devfeed.tech/tags/strands-agents.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

The excerpt presents a four-layer approach to managing context in production AI agents, illustrated with Deep Insight, an open-source data analysis system built on Strands Agents SDK and Amazon Bedrock AgentCore. It isolates work in specialized agents that share compressed summaries, uses prompts to cap outputs and require self-contained code, and keeps code, results, and on-demand skill guides in files. A combined write-and-execute tool reportedly cuts script-related context tokens by about 95%, while loading a small skill catalog and fetching guides only when needed reduces startup prompt size by about 97%. Quality safeguards include independent calculation checks with a 0.01 tolerance, citation audits with up to two targeted retries, checklist tracking, and context summarization that preserves recent messages. Selective prompt caching is used to reduce costs on repeated calls. The figures and implementation details are presented as examples from the reference system.

### Source excerpt

In production AI agents, context management is the real bottleneck. This post presents a four-layer context engineering framework (architecture, prompts, file-based tools, and verification agents), implemented in working code from Deep Insight, an open source multi-agent data analysis solution on the Strands Agents SDK and Amazon Bedrock AgentCore.

## ReVi: Recursive Recap Video Generation

DevFeed: [ReVi: Recursive Recap Video Generation](<https://devfeed.tech/articles/revi-recursive-recap-video-generation-117353.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03674>)

Author: Kyrie You Wu, Chaozhuo Li, Songyang Liu, Xueyang Feng, Ziluowen Luo, Chenxu Wang, Ji Qi, Jinfu Zhu, Litian Zhang

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

Content type: article

Language: en

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

Topics: [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-framework](<https://devfeed.tech/tags/agent-framework.md>), [budget](<https://devfeed.tech/tags/budget.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [content](<https://devfeed.tech/tags/content.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-mm](<https://devfeed.tech/tags/cs-mm.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [events](<https://devfeed.tech/tags/events.md>), [film](<https://devfeed.tech/tags/film.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generation](<https://devfeed.tech/tags/generation.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [meta](<https://devfeed.tech/tags/meta.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [narration](<https://devfeed.tech/tags/narration.md>), [novel](<https://devfeed.tech/tags/novel.md>), [policy](<https://devfeed.tech/tags/policy.md>), [recap](<https://devfeed.tech/tags/recap.md>), [video](<https://devfeed.tech/tags/video.md>), [video-generation](<https://devfeed.tech/tags/video-generation.md>)

### AI overview

ReVi generates self-contained audiovisual recaps directly from novels within a fixed viewing-time budget. Its inner loop plans which story content to retain, how much narration time to allocate, and which shots to generate before video creation. An outer loop recursively improves both the editing policy and the policy for revising it across novels. The authors report better recap quality and duration compliance than representative baselines on two evaluation sets, with human ratings and multi-round results offering further support.

### Source excerpt

arXiv:2611.03674v1 Announce Type: cross Abstract: Novels tell rich stories, but their textual form cannot directly present the sights and sounds of the worlds they describe. Film adaptations offer an audiovisual experience but require substantial production effort and viewing time; film recaps are shorter but depend on existing footage. Neither route directly provides a concise audiovisual account of a novel. We therefore study novel-to-recap video generation: producing a self-contained, source-grounded audiovisual retelling directly from a novel within a fixed viewing-time budget. This task requires compressing the story while preserving causal connections, allocating sufficient time to retained events, and aligning narration with newly generated visuals. We propose ReVi, a dual-loop multi-agent framework guided by edit first, generate second. Its Inner Loop plans story content, narration time, and corresponding shots before video generation. Across novels, its Outer Loop performs recursive self-improvement by revising both the editing policy and the meta policy that governs its revision. Experiments on two evaluation sets show that ReVi improves recap quality and duration compliance over representative baselines, with human ratings and multi-round improvement results providing further support.

## Your Agent Works in the Demo. Now Make It Survive Monday.

DevFeed: [Your Agent Works in the Demo. Now Make It Survive Monday.](<https://devfeed.tech/articles/your-agent-works-in-the-demo-now-make-it-survive-monday-114138.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/your-agent-works-in-the-demo-now-make-it-survive-monday/>)

Author: Gursimar Singh

Published: 2026-11-03T12:30:00Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [artifical-intelligence](<https://devfeed.tech/tags/artifical-intelligence.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [blast-radius](<https://devfeed.tech/tags/blast-radius.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [business](<https://devfeed.tech/tags/business.md>), [bytedance](<https://devfeed.tech/tags/bytedance.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [checkpoint](<https://devfeed.tech/tags/checkpoint.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-harness](<https://devfeed.tech/tags/claude-code-harness.md>), [claude-md](<https://devfeed.tech/tags/claude-md.md>), [code](<https://devfeed.tech/tags/code.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llm](<https://devfeed.tech/tags/llm.md>)

### AI overview

Production agents depend on a harness that controls tools, permissions, memory, checks and human sign-off; the article's core guidance is to let models reason while enforcing boundaries in code. It contrasts rigid, code-defined pipelines with agents that choose steps inside safeguards, using DeerFlow 2.0, Claude Code and MiroFlow as examples. For data cleansing, it recommends deterministic code for testable normalization and exact matches, model proposals with reasons and confidence for ambiguous cases, and expert approval for costly or regulated decisions. The workflow stages writes, records changes and approvers, and supports replay and rollback; its review queue must be staffed to avoid delays or rubber-stamping. Practical steps include assigning each decision to code, a model or a person; limiting autonomy with hard scope and resource caps; checking actions before and after; logging traces; and making changes reversible. Benchmark claims should be checked for data split, subset, run aggregation, grading and comparable model/tool budgets.

### Source excerpt

The demo is the easy part The post Your Agent Works in the Demo. Now Make It Survive Monday. appeared first on Towards Data Science.

## Meet Paige, PagerDuty's SRE Agent: Faster Fixes Today, Fewer Incidents Tomorrow by PagerDuty

DevFeed: [Meet Paige, PagerDuty's SRE Agent: Faster Fixes Today, Fewer Incidents Tomorrow by PagerDuty](<https://devfeed.tech/articles/meet-paige-pagerduty-s-sre-agent-faster-fixes-today-fewer-incidents-tomorrow-by-pagerduty-115677.md>)

Original publisher: [Read original article](<https://www.pagerduty.com/blog/ai/meet-paige-sre-agent/>)

Author: PagerDuty

Published: 2026-11-03T11:00:27Z

Content type: release

Language: en

Sources: [PagerDuty](<https://devfeed.tech/sources/pagerduty.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [DevAIOps](<https://devfeed.tech/topics/devaiops.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [data](<https://devfeed.tech/tags/data.md>), [devops](<https://devfeed.tech/tags/devops.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-and-devops](<https://devfeed.tech/tags/engineering-and-devops.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [first](<https://devfeed.tech/tags/first.md>), [incidents](<https://devfeed.tech/tags/incidents.md>), [operational](<https://devfeed.tech/tags/operational.md>), [operations](<https://devfeed.tech/tags/operations.md>), [over](<https://devfeed.tech/tags/over.md>), [pagerduty](<https://devfeed.tech/tags/pagerduty.md>), [paige](<https://devfeed.tech/tags/paige.md>), [post](<https://devfeed.tech/tags/post.md>), [sre](<https://devfeed.tech/tags/sre.md>), [sre-agent](<https://devfeed.tech/tags/sre-agent.md>), [works](<https://devfeed.tech/tags/works.md>)

### AI overview

PagerDuty presents Paige as an SRE agent that uses incident history, telemetry, documentation, and team feedback to support incident response and prevention. It consolidates alerts, routes incidents, briefs responders, tests and ranks possible causes with visible reasoning, and suggests fixes based on similar past incidents. Paige can run specified workflows or apply resolutions with approval; autonomous handling of user-defined, well-understood incidents is described as coming soon. Teams set its data access and authority, can override its recommendations, and retain judgment over novel cases and stakeholder communications. Each incident can inform shared memory and a draft post-incident review. Deep Investigation and SRE Workbench are identified as PD Labs previews; the article also describes MCP connections and 750+ integrations.

### Source excerpt

Today, we're introducing Paige, PagerDuty's SRE Agent. Built on over 16 years of operational data, Paige works as a member of operations, engineering, and DevOps... The post Meet Paige, PagerDuty's SRE Agent: Faster Fixes Today, Fewer Incidents Tomorrow appeared first on PagerDuty.

## Apache Flink Agents 0.4.0 Release Announcement

DevFeed: [Apache Flink Agents 0.4.0 Release Announcement](<https://devfeed.tech/articles/apache-flink-agents-0-4-0-release-announcement-107667.md>)

Original publisher: [Read original article](<https://flink.apache.org/2026/10/30/apache-flink-agents-0.4.0-release-announcement/>)

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

Content type: release

Language: en

Sources: [Apache Flink](<https://devfeed.tech/sources/apache-flink-stateful-computations-over-data-streams-on-apache-flink.md>)

Topics: [Apache Flink](<https://devfeed.tech/topics/apache-flink.md>), [Release notes](<https://devfeed.tech/topics/release-notes.md>), [Event-Streaming](<https://devfeed.tech/topics/event-streaming.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [business logic](<https://devfeed.tech/topics/business-logic.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [announce](<https://devfeed.tech/tags/announce.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-flink](<https://devfeed.tech/tags/apache-flink.md>), [community](<https://devfeed.tech/tags/community.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [events](<https://devfeed.tech/tags/events.md>), [execution](<https://devfeed.tech/tags/execution.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [flink](<https://devfeed.tech/tags/flink.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [processing](<https://devfeed.tech/tags/processing.md>), [production](<https://devfeed.tech/tags/production.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

Apache Flink Agents 0.4.0 adds sub-agent delegation, a unified Decision Model API for TypeSafe, OpenAI, and Alibaba Cloud Model Studio, model routing through the Java API, multimodal messages, and broader structured output support. New `ctx.chat` actions combine model calls with business logic; conditional event triggers, tool parameter injection, and Java asynchronous execution on JDK 11 and 17 extend application control. Trace Log records execution steps and call lineage, while new metrics cover processing, queues, latency, and component calls. This remains a preview, and APIs and configuration may change. Upgrading from 0.3 requires broad migration work: Action State Store data is incompatible; retries now default to zero; message, event, tool, and logging formats have changed; and stricter validation applies to settings and inputs. Pending Action snapshot restoration may fail, so validate representative state before upgrading.

### Source excerpt

The Apache Flink community is excited to announce the release of Apache Flink Agents 0.4.0. Apache Flink Agents brings AI agents into Flink streaming pipelines. Applications can continuously respond to real-time events, combine AI processing with business logic, and use Flink for distributed execution and fault recovery. Shaped by feedback from early production adopters and advances in the agent ecosystem, Flink Agents 0.4 marks the final planned step toward a production-ready 1.

[Next page](<https://devfeed.tech/topics/supervisor-agent-pattern.md?cursor=WyIyMDI2LTEwLTMwVDAwOjAwOjAwKzAwOjAwIiwgIjlkZGZmZWJlLWZmMWItNDM1YS1iMjMxLTg2MDdjYWM0YjViMyJd>)