Play 37
AI-Powered DevOps
Intelligent SRE — incident triage, automated runbooks, deployment risk scoring, predictive scaling.
AI-assisted SRE and DevOps platform combining intelligent incident triage, automated runbook execution, deployment risk scoring, GitOps with AI review, and predictive scaling. Azure OpenAI analyzes incidents and generates remediation plans. Azure Monitor provides telemetry, Azure DevOps and GitHub Actions handle CI/CD, and Container Apps hosts the SRE agent. Reduces mean-time-to-resolution by automating first-responder investigation and runbook execution.
Architecture Pattern
AI SRE: incident triage, runbook automation, risk scoring, predictive scaling
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — DevOps Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (108 lines), evaluate (107 lines), tune (103 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with DevOps + Monitor key inputs + envFile
TuneKit (AI Config)
- config/openai.json — incident analysis prompts
- config/devops.json — severity rules, runbook triggers, scaling thresholds
- config/guardrails.json — blast radius limits, approval gates
- evaluation/eval.py — Resolution accuracy >85%, MTTR reduction >40%
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.