Play 31
Low-Code AI Builder
Medium✅ Ready
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
Azure OpenAI (gpt-4o)Container AppsCosmos DBStatic Web Apps
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
Pipeline templatesDeployment targetsEvaluation thresholdsNode model selectionTemplate gallery config
Estimated Cost
Dev/Test
$80–200/mo
Production
$1K–4K/mo