Back office ops · Production

Faire uses swarm-coding with multiple GitHub Copilot background agents to accelerate large-scale engineering workflows

The problem

Faire engineers spent countless hours on tedious but essential maintenance tasks like cleaning up expired feature flags and migrating test infrastructure, with no scalable way to parallelize or automate this work.

Workflow diagram · grounded in source
1
Issue assigned to Copilot
trigger
“GitHub Copilot's background agent is an autonomous workflow that will generate a pull request when you assign it to a GitHub issue”
2
Expired setting finder
ai_action
“ExpiredSettingFinderAgent: An agent that can find expired settings to clean up, and manage allocation of the cleanup tasks”
3
Cleanup readiness assessment
ai_action
“SettingCleanupReadinessAgent: An agent that determines the stage of clean up, and generates instructions for the next step”
4
Background agent executes changes
ai_action
“a specialized GitHub action to run in the background, which will put up a placeholder pull request that it incrementally updates with a TODO list and the progress towards it”
5
Build failure feedback to agent
validation
“Summarize the build failures for Copilot — automatically surfaces problems to Copilot to iterate”
6
Two-human review required
human_review
“Require two reviews on PRs authored by Copilot — the assignee's initial review, plus another human”
7
Time saved reported via Slack
feedback_loop
“When a PR is merged, we ping the assignee on Slack to ask how much time it saved them”
Reported outcome

Within just over a month, 18% of the engineering team adopted GitHub Copilot, over 500 Copilot pull requests were merged, Copilot users saw a 25% increase in PR volume, and the average reported time saved was 39.6 minutes per PR.

Reported metrics
Engineering team Copilot adoption18%
Copilot pull requests mergedover 500
PR volume increase for Copilot users25%
Average time saved per PR39.6 minutes
Reported stack
GitHub CopilotMCP (Model Context Protocol) serversCursorMockoloNxYarnts-morphFaireyNotionSlackJiraBuildkite
Source
https://craft.faire.com/swarm-coding-agentic-development-with-multiple-background-agents-3549adc7460d
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Within just over a month, 18% of the engineering team adopted GitHub Copilot, over 500 Copilot pull requests were merged, Copilot users saw a 25% increase in PR volume, and the average reported time saved was 39.6 min…

What tools did this team use?

GitHub Copilot, MCP (Model Context Protocol) servers, Cursor, Mockolo, Nx, Yarn, ts-morph, Fairey, Notion, Slack.

What results were reported?

Engineering team Copilot adoption: 18%; Copilot pull requests merged: over 500; PR volume increase for Copilot users: 25%; Average time saved per PR: 39.6 minutes (source-reported, not independently verified).

How is this back office ops AI workflow structured?

Issue assigned to Copilot → Expired setting finder → Cleanup readiness assessment → Background agent executes changes → Build failure feedback to agent → Two-human review required → Time saved reported via Slack.

Related back office ops cases