Squad: Human-led agentic teams that help you move faster with your code

Skip to main content

Skip to main content

Source

Signal blog<br>Official Microsoft Blog<br>Microsoft On The Issues<br>Asia<br>Canada<br>Europe, Middle East and Africa<br>Latin America<br>The Code of Us<br>Conexiones

What's new today

AI

Innovation

Digital Transformation

Sustainability

Security

Work & Life

Diversity & Inclusion

Unlocked

Microsoft 365<br>Azure<br>Copilot<br>Windows<br>Surface<br>XBOX<br>Deals<br>Small Business<br>Support

Windows Apps<br>Outlook<br>OneDrive<br>Microsoft Teams<br>OneNote<br>Microsoft Edge<br>Moving from Skype to Teams

Computers<br>Shop Xbox<br>Accessories<br>VR & mixed reality<br>Certified Refurbished<br>Trade-in for cash

Xbox Game Pass Ultimate<br>PC Game Pass<br>Xbox games<br>PC games

Microsoft AI<br>Microsoft Security<br>Dynamics 365<br>Microsoft 365 for business<br>Microsoft Power Platform<br>Windows 365<br>Small Business<br>Digital Sovereignty

Azure<br>Microsoft Developer<br>Microsoft Learn<br>Support for AI marketplace apps<br>Microsoft Tech Community<br>Microsoft Marketplace<br>Software companies<br>Visual Studio

Microsoft Rewards<br>Free downloads & security<br>Education<br>Gift cards<br>Licensing<br>Unlocked stories

View Sitemap

Search articles

Deep Dive

Share

in

Disposable agents, durable memory: The architecture behind Squad

Disposable agents, durable memory: The architecture behind Squad

What we learned building Squad: a file-backed, human-led agent team where memory is inspectable, orchestration is explicit, and governance moves from prompts into code.

By Brady GasterPrincipal PM Architect, GitHubGitHub &rarr; and Tamir DresherPrincipal Software Engineer, MicrosoftWebsite &rarr;

Make the agents disposable. Keep the memory in Git.

The interesting part of agentic development is no longer whether a model can write code. It can. The interesting part is what happens after the third agent, the seventh pull request, the first failed review, the first context compaction bug, and the first time two agents confidently write to the same file at once.

This is the story of Squad, but not as a product tour. It’s the architecture Brady and Tamir backed into while trying to make agent teams useful without making them mystical: Agents are disposable, memory is durable, Git is the coordination layer, and governance belongs in code whenever the prompt isn’t strong enough to be trusted. Which, as it turns out, is often.

Giving agents agency and watching them hack one another

Squad Places is our social media-style testing ground—a demo app where agent squads post, comment, and interact to stress-test multi-agent coordination at scale.

Brady went to get a seltzer after getting Places up and running, with four other squads happily making posts. Walking away was probably unwise. When he came back, the squads had implemented commenting in Squad Places.

That sounds like a magic trick. It wasn’t. A few hours earlier, Brady had pointed a handful of squads at the Squad Places API and told them to enjoy the social network he’d created for them. They created fake accounts, hammered endpoints, reposted garbage, flooded messages, and generally speedran the abuse patterns you discover five minutes after launch. Then the platform got a second kind of pressure: Other agent teams started posting structured product feedback inside Squad Places itself, and the Squad Places team started fixing what hurt.

This is the part worth paying attention to. The Wire (another Squad working on a marketing tool) audited all 11 API endpoints and called out missing pagination envelopes, rate-limit headers that only appeared on errors, and the lack of page and pageSize support. The same squad flagged feed organization problems, tag fragmentation, and documentation that was too vague for client generation. Breaking Bad (a third Squad working on some other project) pointed at a UX problem with raw Markdown rendering as plaintext. Those reviews didn’t disappear into a chat log. They turned into commits.

Feedback SourceWhat They FoundWhat We ShippedCommitThe Wire (ACCES)Feed has no sorting, filtering, or content discovery; raw Markdown not renderedSort controls (Latest/Most Discussed), squad filter dropdown, Markdown renderingb9746df, 246b01eThe Wire (ACCES)159 unique tags across 66 artifacts with inconsistent delimiters, casing mismatches, and fragmentationClickable tag filtering with /?tag= URL query support246b01eThe Wire (ACCES)API missing pagination envelope, rate-limit headers only on errors, no page/pageSize parametersPagination (20 per page with Primer CSS controls), query parameters, rate-limit headers on all responses246b01eBreaking BadRaw Markdown displayed as plaintext, content hard to scan and parseMarkdown rendering via Markdig with XSS sanitization246b01eThe Wire (ACCES)API endpoint descriptions too vague for TypeScript client generationEnriched all 11 endpoint descriptions with context, intent, and workflow97345d7

Within roughly two hours, the loop closed: feedback post → comment thread → commit → deployed feature. Additional infrastructure...