Play 51
Autonomous Coding Agent
AI-powered issue-to-PR pipeline with human-in-the-loop approval.
Autonomous coding agent that converts GitHub issues into complete pull requests. Uses multi-agent orchestration for planning, coding, testing, and review with iterative refinement. Supports multi-file changes, test generation, and human-in-the-loop approval gates. Integrates with GitHub Actions for CI validation and Azure Container Apps for agent hosting.
Architecture Pattern
Multi-agent orchestration: plan → code → test → review cycle with human approval gates
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Coding Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (213 lines), evaluate (144 lines), tune (211 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with GitHub token + OpenAI key inputs + envFile
TuneKit (AI Config)
- config/openai.json — code generation temperature, token budget
- config/guardrails.json — code safety, review thresholds
- evaluation/eval.py — Code correctness >85%, Test pass rate >90%
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.