# Agent Experience Published articles for Agent Experience. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How sandbox boundaries affect AI coding agent evaluations DevFeed: [How sandbox boundaries affect AI coding agent evaluations]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-09-16T09:09:51Z Content type: opinion Language: en Sources: [Developer Blogs]() Topics: [AI-assisted coding](), [Testing](), [Artificial Intelligence](), [coding]() Tags: [agent-experience](), [ai](), [ai-coding](), [ax](), [coding](), [developers](), [eval](), [evaluation](), [measurement](), [sandbox]() ### AI overview The article explains that an AI coding agent evaluation can produce misleading scores when the agent retrieves answers from its prompt, environment, or other accessible resources. It argues that evaluators should define the capability being tested and set information boundaries accordingly, including restricting access to evidence when measuring internal model knowledge. ### Source excerpt Your AI coding agent passed the eval. But did the model know the answer, or did it find it somewhere on your machine? A correct answer can still invalidate your measurement. The post Your AI coding agent evaluation is only as good as its sandbox appeared first on Microsoft for Developers. ## Rails Hyperdrive: supercharged agentic development for Rails DevFeed: [Rails Hyperdrive: supercharged agentic development for Rails]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-09-15T00:00:00Z Content type: tutorial Language: en Sources: [Evil Martians]() Topics: [Ruby on Rails](), [AI-assisted coding](), [Model Context Protocol]() Tags: [agent-experience](), [ai](), [ai-coding-agents](), [claude-code](), [mcp](), [open-source](), [rails](), [ruby-on-rails](), [ruby-on-rails-consulting]() ### AI overview This tutorial introduces Rails Hyperdrive, a development-only Rails engine that gives AI coding agents live answers from a booted Rails application and lets gems provide agent guidance through Gemfile-gated knowledge. It covers installation, MCP server setup, skills, sub-agents, slash commands, upgrades, and integration for gem authors. ### Source excerpt Introducing Rails Hyperdrive: a development-only Rails engine that gives AI coding agents live answers from your booted app and lets any gem in your bundle ship guidance gated to your Gemfile. Convention over configuration, applied to agent knowledge. ## Evaluating Model Cost and Quality for Developer Workflows DevFeed: [Evaluating Model Cost and Quality for Developer Workflows]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-09-09T09:14:04Z Content type: comparison Language: en Sources: [Developer Blogs]() Topics: [Claude](), [GitHub Copilot](), [Visual Studio Code](), [Testing](), [upgrade](), [Code]() Tags: [agent-experience](), [ai](), [ax](), [claude](), [comparison](), [cost](), [evaluation](), [github-copilot](), [model](), [testing](), [upgrade](), [visual-studio-code](), [windows]() ### AI overview This article compares GPT-6 Astra with Claude Sonnet 4.6 across code upgrade scenarios in GitHub Copilot Chat for Visual Studio Code on Windows. It argues that teams should evaluate models on their own repositories and workflows because higher cost did not consistently produce better results in the reported tests. ### Source excerpt The smartest model can cost five times more and deliver the same result, or even a worse one. See how evaluating your own work helps you get more value from your agent budget. The post Your work might not need the smartest model appeared first on Microsoft for Developers. ## Checks for safer review of rapidly generated TypeScript and React frontend code DevFeed: [Checks for safer review of rapidly generated TypeScript and React frontend code]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-09-01T00:00:00Z Content type: tutorial Language: en Sources: [Evil Martians]() Topics: [Front end](), [React](), [TypeScript](), [Artificial Intelligence](), [OpenAPI Specification](), [API](), [mutation-testing](), [Testing](), [Code]() Tags: [agent-experience](), [agentic-development](), [agents](), [ai](), [api](), [code](), [continuous-integration](), [dx](), [frontend](), [llms](), [mutation-testing](), [openapi](), [react](), [testing](), [typescript]() ### AI overview This article presents ten checks for making rapidly generated TypeScript and React frontend code safer to trust and cheaper to review. It covers API contracts, generated types, boundary validation, mutation testing, dead-code detection, and mandatory checks. ### Source excerpt Ten checks that catch what AI-written frontend code hides: contract codegen, boundary linting, mutation testing, and dead-code detectors. ## Ship agent skills like packages: discovery index, digests, and install sources DevFeed: [Ship agent skills like packages: discovery index, digests, and install sources]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-08-12T00:00:00Z Content type: tutorial Language: en Sources: [Evil Martians]() Topics: [Agent Skills](), [Agent Skill](), [ai-coding](), [Publishing](), [GitHub](), [make](), [rubygems]() Tags: [agent-experience](), [agent-skill](), [agent-skills](), [ai](), [coding](), [coding-agents](), [dx](), [github](), [jamstack](), [json](), [llms](), [npm](), [rubygems](), [sha-256](), [skills]() ### AI overview This tutorial explains how to publish agent skills so AI coding agents can discover and install them. It covers a .well-known/agent-skills/index.json discovery index, SHA-256 integrity digests, single-file, multi-file, and bundle packaging, multiple install commands, and hosting skills from a GitHub repository while re-hosting the served files on the publisher's domain. ### Source excerpt How to publish agent skills so any AI coding agent can find and install them: the .well-known/agent-skills/index.json discovery index, SHA-256 integrity digests, single-file vs multi-file vs bundle packaging, and every install command. Worked from the catalog we just open-sourced. ## How to test agent experience changes without shipping them DevFeed: [How to test agent experience changes without shipping them]() Original publisher: [Read original article]() Author: Waldek Mastykarz, Garry Trinder Published: 2026-07-21T07:15:12Z Content type: tutorial Language: en Sources: [Developer Blogs]() Topics: [AI Agent](), [Documentation](), [API](), [MCP](), [Command-line interface](), [upgrade]() Tags: [agent-experience](), [ai](), [ai-agent](), [api](), [ax](), [cli](), [developers](), [documentation](), [how-to](), [mcp](), [mcp-server](), [upgrade]() ### AI overview This Microsoft for Developers article explains how to test changes intended to influence AI agent behavior before shipping them. It describes validating documentation, API, and MCP server changes locally, using evaluations and controlled hypotheses, and reports that a warning stating an existing plan would fail changed the agent's behavior in five out of five runs. ### Source excerpt Most changes you think will improve AI agent behavior won't. We tested a dozen hypotheses on a real project upgrade scenario and the majority failed. Learn how to emulate documentation, API, and MCP server changes locally so you can validate what works before shipping anything to production. The post How to test agent experience changes without shipping them appeared first on Microsoft for Developers. ## Which AI actually reads your site? Two months of LLM traffic, measured DevFeed: [Which AI actually reads your site? Two months of LLM traffic, measured]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-07-21T00:00:00Z Content type: article Language: en Sources: [Evil Martians]() Topics: [Large Language Model](), [Artificial Intelligence](), [Claude Code](), [ChatGPT](), [Google Analytics](), [Netlify](), [Back end]() Tags: [agent-experience](), [agents](), [ai](), [backend](), [chatgpt](), [claude-code](), [dx](), [google-analytics](), [jamstack](), [llm](), [llms](), [logs](), [measurement](), [netlify]() ### AI overview Evil Martians measured two months of server-side LLM traffic to its website. The study found that ChatGPT primarily fetches rendered HTML, while Claude Code requests Markdown most of the time through content negotiation. Most llms.txt requests came from bots other than the intended AI assistants, and a hidden AI hint received no measurable hits. ### Source excerpt We told you to measure. So of course we did it ourselves too: two months of server-side LLM traffic to evilmartians.com. Find out which agents read HTML, which read Markdown, what llms.txt actually does, and the one technique that got zero hits. ## How to test agent skills without hitting real APIs DevFeed: [How to test agent skills without hitting real APIs]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-07-17T09:27:50Z Content type: tutorial Language: en Sources: [Developer Blogs]() Topics: [Agent Skills](), [API](), [Testing]() Tags: [agent-experience](), [agent-skills](), [ai](), [apis](), [ax](), [evals](), [how-to](), [microsoft](), [testing]() ### AI overview This tutorial explains how to evaluate agent skills that call APIs without incurring external API costs or mutating live data. It introduces transparent API mocking to support isolated, repeatable evaluation runs without changing the skill or contacting real endpoints. ### Source excerpt Your agent skill calls an API. The moment you start evaluating it, every run either costs money or mutates production data. Learn how to mock APIs transparently so you can run evals without changing your skill or hitting real endpoints. The post How to test agent skills without hitting real APIs appeared first on Microsoft for Developers. ## Building AX evals that actually work DevFeed: [Building AX evals that actually work]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-07-15T12:53:13Z Content type: tutorial Language: en Sources: [Developer Blogs]() Topics: [AI-assisted coding](), [Loop Engineering](), [Prompt Engineering]() Tags: [agent-experience](), [ai](), [ai-coding-agents](), [article](), [ax](), [coding-agents](), [evals](), [evaluation](), [how-to](), [microsoft](), [microsoft-for-developers](), [quality]() ### AI overview This eighth and final article in a series about Agent Experience explains how to build meaningful evaluations for AI coding agents. It identifies representative prompts, accurate and unambiguous criteria, and other structural decisions needed to produce useful signal rather than misleading scores. ### Source excerpt This is the eighth and final article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can't control in the agent stack, how to measure whether your extensions are helping or hurting, and how to iterate toward better [...] The post Building AX evals that actually work appeared first on Microsoft for Developers. ## The hidden variables in your agent eval DevFeed: [The hidden variables in your agent eval]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-07-08T12:11:17Z Content type: article Language: en Sources: [Developer Blogs]() Topics: [AI-assisted coding](), [context](), [Operating system](), [Shell]() Tags: [agent](), [agent-experience](), [ai](), [ai-coding-agents](), [ax](), [benchmarks](), [context](), [reproducibility]() ### AI overview This seventh article in Microsoft's Agent Experience series examines hidden environmental variables that can make the same AI coding-agent evaluation produce different results. It discusses context such as operating system, shell, diagnostics, build errors, file paths, and workspace details. ### Source excerpt This is the seventh article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can't control in the agent stack, how to measure whether your extensions are helping or hurting, and how to iterate toward better outcomes. You [...] The post The hidden variables in your agent eval appeared first on Microsoft for Developers. ## Using Storybook Workbench to audit AI-generated UIs for dead components and accessibility bugs DevFeed: [Using Storybook Workbench to audit AI-generated UIs for dead components and accessibility bugs]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-07-08T00:00:00Z Content type: tutorial Language: en Sources: [Evil Martians]() Topics: [Storybook](), [Agent Skills](), [agentic-coding](), [AI-assisted coding](), [Accessibility](), [Design system]() Tags: [accessibility](), [agent-experience](), [agent-skills](), [agentic-coding](), [agentic-development](), [ai](), [bugs](), [design](), [design-engineering](), [design-for-devtools](), [design-system](), [dx](), [storybook]() ### AI overview The article presents Storybook Workbench, a bundle of Agent Skills that audits AI-generated web applications by rendering components as Storybook stories. It describes finding dead components, coexisting design systems, conditional component states, and accessibility bugs, based on an internal audit of an agent-coded app. ### Source excerpt Storybook Workbench is a bundle of Agent Skills that turn Storybook into an audit layer for AI-generated UIs: find dead components, design-system drift, and hidden accessibility bugs. ## Don't rewrite your CLI for agents DevFeed: [Don't rewrite your CLI for agents]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-07-07T13:52:06Z Content type: article Language: en Sources: [Developer Blogs]() Topics: [Command-line interface](), [JSON](), [test](), [GitHub]() Tags: [agent-experience](), [ai](), [ax](), [cli](), [developers](), [github-copilot](), [json](), [microsoft]() ### AI overview This article examines whether developer CLIs should replace conventional arguments with a single JSON payload for use by coding agents. It describes a controlled comparison using synthetic multi-service deployment CLIs, identical prompts, and several coding models; in the supplied results, every tested args profile achieved perfect correctness across five runs. ### Source excerpt There's advice making the rounds: replace your CLI args with a single --json payload so agents can use your tool more effectively. The thinking being, that agents already think in structured formats, and nested data maps cleanly to JSON. Flat args on the other hand, force awkward conventions like repeating --service-name to delimit multi-value groups, [...] The post Don't rewrite your CLI for agents appeared first on Microsoft for Developers.