Type-safe AI workflows with flows, agents, RAG, and multi-model support across TypeScript, Go, and Python.

Supports Gemini, OpenAI, Anthropic, Ollama, and Vertex AI with pluggable model providers; deploy to Firebase Cloud Functions or Cloud Run
Define type-safe flows with Zod schemas for inputs/outputs; includes streaming, tool calling, and agentic loops with auto-execution
Built-in RAG with vector database integrations (Pinecone, pgvector, Firestore, Chroma, LanceDB) and retrieval-augmented generation
Developer UI at localhost:4000 provides flow runner, trace inspector, prompt playground, and model comparison tools
Manage prompts as versioned .prompt files with Dotprompt; coordinate multi-agent systems by composing specialized flows

When to use this skill

AI workflow orchestration: Building multi-step AI pipelines with type-safe inputs/outputs

Flow-based APIs: Wrapping LLM calls into deployable HTTP endpoints

Tool calling / agents: Equipping models with custom tools and implementing agentic loops

RAG pipelines: Retrieval-augmented generation with vector databases (Pinecone, pgvector, Firestore, Chroma, etc.)

Multi-agent systems: Coordinating multiple specialized AI agents

Streaming responses: Real-time token-by-token output for chat or long-form content

Firebase/Cloud Run deployment: Deploying AI functions to Google Cloud

Prompt management: Managing prompts as versioned .prompt files with Dotprompt

genkit

Firebase Genkit