# ISE Developer Blog

Solving global tech challenges, sharing insights, and empowering developers

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

## Documentation Is the New Source Code

DevFeed: [Documentation Is the New Source Code](<https://devfeed.tech/articles/documentation-is-the-new-source-code-59239.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/documentation-is-the-new-source-code/>)

Author: Liza Shakury

Published: 2026-09-24T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Documentation](<https://devfeed.tech/topics/documentation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [building-with-ai](<https://devfeed.tech/tags/building-with-ai.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cse](<https://devfeed.tech/tags/cse.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developer](<https://devfeed.tech/tags/developer.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [hve](<https://devfeed.tech/tags/hve.md>), [ise](<https://devfeed.tech/tags/ise.md>), [mcp](<https://devfeed.tech/tags/mcp.md>)

### AI overview

A field guide to layered, AI-readable documentation--such as instruction files, skills, technical guides, ADRs, and tests--for repositories used with coding assistants and agentic engineering workflows. It argues that explicit conventions improve how AI tools handle multi-step software changes and reduce incorrect inferences.

### Source excerpt

A field guide to building a layered, AI-readable documentation system -- instruction files, skills, ADRs, and tests -- that turns your repo into a reliable substrate for Copilot, agents, and high-velocity engineering workflows. The post Documentation Is the New Source Code appeared first on ISE Developer Blog.

## Building a Japanese LLM Evaluation Pipeline: Lessons from a Two-Day Hackathon

DevFeed: [Building a Japanese LLM Evaluation Pipeline: Lessons from a Two-Day Hackathon](<https://devfeed.tech/articles/building-a-japanese-llm-evaluation-pipeline-lessons-from-a-two-day-hackathon-50205.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/japanese-llm-evaluation-pipeline-hackathon/>)

Author: Jaein Tak, Akihiro Inui, Kohei Saito

Published: 2026-09-14T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [For the Love of Code](<https://devfeed.tech/topics/for-the-love-of-code.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [dataset](<https://devfeed.tech/topics/dataset.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [ci](<https://devfeed.tech/tags/ci.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [cse](<https://devfeed.tech/tags/cse.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [hackathon](<https://devfeed.tech/tags/hackathon.md>), [ise](<https://devfeed.tech/tags/ise.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-evaluation](<https://devfeed.tech/tags/llm-evaluation.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>)

### AI overview

This article explains how a two-day hackathon produced a reusable pipeline for evaluating Japanese LLMs in customer-facing voice and conversational AI. The multi-provider, multi-turn benchmark uses facet-based scoring to assess qualities such as naturalness, emotional awareness, and persona consistency, while automation and CI/CD support faster model selection and iteration.

### Source excerpt

ISE hackathon produced a reusable Japanese LLM evaluation pipeline with multi-turn, facet-based scoring, cross-provider model support, and publication-ready benchmarking outputs. The post Building a Japanese LLM Evaluation Pipeline: Lessons from a Two-Day Hackathon appeared first on ISE Developer Blog.

## Building a Multimodal LLM Pipeline for Structured Visual-Asset Metadata

DevFeed: [Building a Multimodal LLM Pipeline for Structured Visual-Asset Metadata](<https://devfeed.tech/articles/teaching-a-vision-model-to-see-like-a-human-annotator-and-catching-it-when-it-lies-50201.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/ai-asset-enrichment-pipeline/>)

Author: Deeptanil Saha, Kartheek Palepu

Published: 2026-07-17T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [cognitive-services](<https://devfeed.tech/tags/cognitive-services.md>), [cse](<https://devfeed.tech/tags/cse.md>), [developer](<https://devfeed.tech/tags/developer.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [hallucinations](<https://devfeed.tech/tags/hallucinations.md>), [ise](<https://devfeed.tech/tags/ise.md>), [llm](<https://devfeed.tech/tags/llm.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [structured](<https://devfeed.tech/tags/structured.md>), [vision](<https://devfeed.tech/tags/vision.md>)

### AI overview

This article describes a multimodal LLM pipeline that extracts structured metadata from visual assets for production search. It uses constrained values, image-first grounding, preprocessing, and evaluation to reduce hallucinations and improve trust in the resulting metadata.

### Source excerpt

A multimodal LLM enrichment pipeline that extracts structured metadata from visual assets, constrains output to predefined values to minimize hallucinations, and uses a ground truth evaluation template to measure quality--all as a plug-and-play module. The post Teaching a Vision Model to See Like a Human Annotator--and Catching It When It Lies appeared first on ISE Developer Blog.

## From Noisy Queries to Precise Frames: Query Decomposition for Media Asset Search

DevFeed: [From Noisy Queries to Precise Frames: Query Decomposition for Media Asset Search](<https://devfeed.tech/articles/from-noisy-queries-to-precise-frames-query-decomposition-for-media-asset-search-50204.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/from_noisy_queries_to_precise_frames/>)

Author: Kartheek Palepu, Deeptanil Saha

Published: 2026-07-09T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Query (disambiguation)](<https://devfeed.tech/topics/query.md>), [Parser](<https://devfeed.tech/topics/parser.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>), [data](<https://devfeed.tech/topics/data.md>), [processing](<https://devfeed.tech/topics/processing.md>)

Tags: [cognitive-services](<https://devfeed.tech/tags/cognitive-services.md>), [cse](<https://devfeed.tech/tags/cse.md>), [data](<https://devfeed.tech/tags/data.md>), [developer](<https://devfeed.tech/tags/developer.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [ise](<https://devfeed.tech/tags/ise.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [queries](<https://devfeed.tech/tags/queries.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [regex](<https://devfeed.tech/tags/regex.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [useful](<https://devfeed.tech/tags/useful.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

This article explains a query-decomposition approach for media asset search. It separates structured metadata such as episode, scene, and shot identifiers from natural-language visual intent, applies the metadata as filters, and uses semantic or vector retrieval to rank the filtered candidates.

### Source excerpt

How query decomposition separates metadata filters from visual intent to significantly improve media asset retrieval quality. The post From Noisy Queries to Precise Frames: Query Decomposition for Media Asset Search appeared first on ISE Developer Blog.

## Enabling MLflow OpenAI Autolog on PySpark Workers

DevFeed: [Enabling MLflow OpenAI Autolog on PySpark Workers](<https://devfeed.tech/articles/enabling-mlflow-openai-autolog-on-pyspark-workers-50207.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/mlflow-autolog-pyspark-workers/>)

Author: Jaya Kumar

Published: 2026-07-03T07:00:00Z

Content type: tutorial

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Apache Spark](<https://devfeed.tech/topics/spark.md>), [databricks](<https://devfeed.tech/topics/databricks.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [tracing](<https://devfeed.tech/topics/tracing.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [cse](<https://devfeed.tech/tags/cse.md>), [databricks](<https://devfeed.tech/tags/databricks.md>), [developer](<https://devfeed.tech/tags/developer.md>), [ise](<https://devfeed.tech/tags/ise.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [mlflow](<https://devfeed.tech/tags/mlflow.md>), [openai](<https://devfeed.tech/tags/openai.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [spark](<https://devfeed.tech/tags/spark.md>)

### AI overview

A practical guide to making MLflow OpenAI autologging work across PySpark workers in an Azure Databricks pipeline. It describes missing worker context, permissions, and asynchronous trace-export issues that can cause traces or detailed trace artifacts to be lost.

### Source excerpt

When distributing LLM calls across PySpark workers via mapInPandas, MLflow autolog silently fails. Here is how to fix it. The post Enabling MLflow OpenAI Autolog on PySpark Workers appeared first on ISE Developer Blog.

## Passing Context Between Agents in Multi-Agent A2A Systems

DevFeed: [Passing Context Between Agents in Multi-Agent A2A Systems](<https://devfeed.tech/articles/passing-context-between-agents-in-multi-agent-a2a-systems-50200.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/a2a-context-passing-multi-agent-systems/>)

Author: Olha Konstantinova, Scott Grosenick

Published: 2026-06-26T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>), [stateless](<https://devfeed.tech/topics/stateless.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [systems](<https://devfeed.tech/topics/systems.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-communication](<https://devfeed.tech/tags/agent-communication.md>), [agent-to-agent-communication](<https://devfeed.tech/tags/agent-to-agent-communication.md>), [agents](<https://devfeed.tech/tags/agents.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [backend](<https://devfeed.tech/tags/backend.md>), [context-passing](<https://devfeed.tech/tags/context-passing.md>), [cse](<https://devfeed.tech/tags/cse.md>), [ise](<https://devfeed.tech/tags/ise.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [stateless](<https://devfeed.tech/tags/stateless.md>)

### AI overview

This article explains how to pass conversational and domain-specific context between independently deployed agents in a multi-agent system using the A2A protocol. It describes the context-passing challenge created by stateless domain agents and introduces an embedded context pattern.

### Source excerpt

How we solved the challenge of passing conversational context between independently deployed agents using the A2A protocol's embedded context pattern, keeping domain agents stateless and secure. The post Passing Context Between Agents in Multi-Agent A2A Systems appeared first on ISE Developer Blog.

## Separating Deterministic Extraction from AI Inference in Industrial Summarization

DevFeed: [Separating Deterministic Extraction from AI Inference in Industrial Summarization](<https://devfeed.tech/articles/separating-deterministic-extraction-from-ai-inference-in-industrial-summarization-50208.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/separating-deterministic-extraction-from-ai-inference/>)

Author: Viktor Ciroski

Published: 2026-06-19T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [JSON Schema](<https://devfeed.tech/topics/json-schema.md>), [reliability-engineering](<https://devfeed.tech/topics/reliability-engineering.md>), [Software](<https://devfeed.tech/topics/software.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [Responsibility & Safety](<https://devfeed.tech/topics/responsibility-safety.md>), [audit trail](<https://devfeed.tech/topics/audit-trail.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [cse](<https://devfeed.tech/tags/cse.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [ise](<https://devfeed.tech/tags/ise.md>), [json](<https://devfeed.tech/tags/json.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

The article explains how an LLM-based system for turning industrial shift logs into structured summaries produced valid JSON but failed to satisfy required data contracts. It describes separating deterministic extraction from AI inference and using a multi-pass pipeline with automated schema validation to improve contract reliability, while noting that the evaluation used synthetic logs and schema-based field analysis.

### Source excerpt

When 100% of our prototype outputs were valid JSON but 0% met the data contract, we discovered the LLM was doing work that software should own. A field classification exercise and 4-pass pipeline brought schema compliance from 0% to 100%. The post Separating Deterministic Extraction from AI Inference in Industrial Summarization appeared first on ISE Developer Blog.

## Orchestration Patterns for Multi-Agent Systems: Performance and Trade-offs

DevFeed: [Orchestration Patterns for Multi-Agent Systems: Performance and Trade-offs](<https://devfeed.tech/articles/orchestration-patterns-for-multi-agent-systems-performance-and-trade-offs-50203.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/coordinator-patterns-multi-agent-systems/>)

Author: Lily Jia

Published: 2026-06-12T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [modular-monolith](<https://devfeed.tech/topics/modular-monolith.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Chat Bot](<https://devfeed.tech/topics/chatbot.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [software-development](<https://devfeed.tech/topics/software-development.md>)

Tags: [agent-orchestration](<https://devfeed.tech/tags/agent-orchestration.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [chatbots](<https://devfeed.tech/tags/chatbots.md>), [cse](<https://devfeed.tech/tags/cse.md>), [development](<https://devfeed.tech/tags/development.md>), [ise](<https://devfeed.tech/tags/ise.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [microservices-architecture](<https://devfeed.tech/tags/microservices-architecture.md>), [modular-monolith](<https://devfeed.tech/tags/modular-monolith.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [scale](<https://devfeed.tech/tags/scale.md>)

### AI overview

A Microsoft ISE post describes evolving a production retail chatbot from a modular monolith with deterministic routing into a coordinator-based multi-agent architecture. It discusses agent reuse, independent services, organizational ownership, and performance trade-offs.

### Source excerpt

Real-world lessons from evolving a production chatbot into a coordinator-based multi-agent architecture, including performance trade-offs for enterprise-scale agent reuse. The post Orchestration Patterns for Multi-Agent Systems: Performance and Trade-offs appeared first on ISE Developer Blog.

## How we Decide Between Keyword and Hybrid Search: 5 Enterprise Evaluation Criteria

DevFeed: [How we Decide Between Keyword and Hybrid Search: 5 Enterprise Evaluation Criteria](<https://devfeed.tech/articles/how-we-decide-between-keyword-and-hybrid-search-5-enterprise-evaluation-criteria-50206.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/keyword-vs-hybrid-search/>)

Author: Beijie Zhang

Published: 2026-06-04T07:00:00Z

Content type: tutorial

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [data](<https://devfeed.tech/topics/data.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-adoption](<https://devfeed.tech/tags/ai-adoption.md>), [ai-evaluation](<https://devfeed.tech/tags/ai-evaluation.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [azure-ai](<https://devfeed.tech/tags/azure-ai.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [cse](<https://devfeed.tech/tags/cse.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [developer](<https://devfeed.tech/tags/developer.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [hybrid-search](<https://devfeed.tech/tags/hybrid-search.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [ise](<https://devfeed.tech/tags/ise.md>), [lancedb](<https://devfeed.tech/tags/lancedb.md>), [llmops](<https://devfeed.tech/tags/llmops.md>), [quality](<https://devfeed.tech/tags/quality.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [search-architecture](<https://devfeed.tech/tags/search-architecture.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-databases](<https://devfeed.tech/tags/vector-databases.md>)

### AI overview

This article presents a five-criteria, data-driven framework for choosing between keyword, vector, and hybrid search in enterprise deployments. It emphasizes measuring retrieval quality because accurate retrieval supports grounded answers, reduces hallucination risk, and helps maintain user trust. The framework also applies to retrieval-augmented generation systems.

### Source excerpt

A data-driven framework we use in enterprise deployments to decide between vector-only keyword and hybrid search, based on five measurable evaluation criteria. The post How we Decide Between Keyword and Hybrid Search: 5 Enterprise Evaluation Criteria appeared first on ISE Developer Blog.

## Verification-driven tooling prompts for fast-moving codebases

DevFeed: [Verification-driven tooling prompts for fast-moving codebases](<https://devfeed.tech/articles/verification-driven-tooling-prompts-for-fast-moving-codebases-50209.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/verification-driven-tooling-prompts/>)

Author: Dexter Williams

Published: 2026-05-28T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [Code](<https://devfeed.tech/topics/code.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Script](<https://devfeed.tech/topics/script.md>), [Repository](<https://devfeed.tech/topics/repository.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>), [Maintainability](<https://devfeed.tech/topics/maintainability.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Python](<https://devfeed.tech/topics/python.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [code-coverage](<https://devfeed.tech/tags/code-coverage.md>), [cse](<https://devfeed.tech/tags/cse.md>), [detection](<https://devfeed.tech/tags/detection.md>), [devops](<https://devfeed.tech/tags/devops.md>), [eslint](<https://devfeed.tech/tags/eslint.md>), [genai](<https://devfeed.tech/tags/genai.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [internal-tooling](<https://devfeed.tech/tags/internal-tooling.md>), [ise](<https://devfeed.tech/tags/ise.md>), [parsing](<https://devfeed.tech/tags/parsing.md>), [prompt-engineering](<https://devfeed.tech/tags/prompt-engineering.md>), [repository](<https://devfeed.tech/tags/repository.md>), [static-analysis](<https://devfeed.tech/tags/static-analysis.md>), [tooling](<https://devfeed.tech/tags/tooling.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

A practical pattern for using GenAI research agents to produce reliable internal tooling by verifying assumptions with detection classes and a final checklist.

### Source excerpt

A practical pattern for using GenAI research agents to produce reliable internal tooling by verifying assumptions with detection classes and a final checklist. The post Verification-driven tooling prompts for fast-moving codebases appeared first on ISE Developer Blog.

## Coordinating AI-Assisted Development with AGENTS.md and Skills

DevFeed: [Coordinating AI-Assisted Development with AGENTS.md and Skills](<https://devfeed.tech/articles/coordinating-ai-assisted-development-with-agents-md-and-skills-50202.md>)

Original publisher: [Read original article](<https://devblogs.microsoft.com/ise/ai-assisted-development-agents-skills-copilot-cli/>)

Author: Jimmy Kurian, Destiny Hillis

Published: 2026-05-21T07:00:00Z

Content type: article

Language: en

Sources: [ISE Developer Blog](<https://devfeed.tech/sources/ise-developer-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [monorepo](<https://devfeed.tech/topics/monorepo.md>), [FastAPI](<https://devfeed.tech/topics/fastapi.md>), [Next.js](<https://devfeed.tech/topics/next-js.md>), [React](<https://devfeed.tech/topics/react.md>), [Terraform](<https://devfeed.tech/topics/terraform.md>), [Azure](<https://devfeed.tech/topics/azure.md>)

Tags: [agents-md](<https://devfeed.tech/tags/agents-md.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted-development](<https://devfeed.tech/tags/ai-assisted-development.md>), [azure](<https://devfeed.tech/tags/azure.md>), [backend](<https://devfeed.tech/tags/backend.md>), [cli](<https://devfeed.tech/tags/cli.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cse](<https://devfeed.tech/tags/cse.md>), [fastapi](<https://devfeed.tech/tags/fastapi.md>), [frontend](<https://devfeed.tech/tags/frontend.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot-cli](<https://devfeed.tech/tags/github-copilot-cli.md>), [ise](<https://devfeed.tech/tags/ise.md>), [monorepo](<https://devfeed.tech/tags/monorepo.md>), [next-js](<https://devfeed.tech/tags/next-js.md>), [skills](<https://devfeed.tech/tags/skills.md>)

### AI overview

This post describes how a team coordinated AI-assisted development with repository-level AGENTS.md guidance and reusable task-level skills consumed by GitHub Copilot CLI. It explains how shared project context can reduce inconsistent generated code, tests, imports, and conventions across engineers.

### Source excerpt

How to move AI-assisted development from ad-hoc experimentation to a coordinated team-wide capability using AGENTS.md and reusable skills with GitHub Copilot CLI The post Coordinating AI-Assisted Development with AGENTS.md and Skills appeared first on ISE Developer Blog.