Play 31
Low-Code AI Builder
Visual AI pipeline design — drag-and-drop agent workflows, template library, one-click deploy.
Visual agent workflow builder with drag-and-drop pipeline design, a pre-built template library, one-click Azure deployment, and an integrated evaluation dashboard. Enables citizen developers to build production AI without writing code. Azure OpenAI powers the intelligence, Container Apps hosts the runtime, Cosmos DB stores pipeline definitions, and Static Web Apps delivers the visual builder frontend.
Architecture Pattern
Low-code visual builder: drag-and-drop pipelines, template library, one-click deploy
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Low-Code Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (105 lines), evaluate (105 lines), tune (101 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Power Platform + OpenAI key inputs + envFile
TuneKit (AI Config)
- config/openai.json — model selection for pipeline nodes
- config/templates.json — pre-built pipeline templates
- config/guardrails.json — safety, deployment validation
- evaluation/ — pipeline output quality scoring
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.