Python blueprints
Reference language for most code samples here. Official site: https://www.python.org/
Agent Tracing and Evaluation Setup
Capture structured traces of every LLM and tool call and run a small regression eval suite on each change.
Human-in-the-Loop Approval Gate
Let agents draft freely but require explicit human approval before any irreversible or external action.
Planner-Executor Agent
Split a task into an explicit plan, execute steps one at a time, and re-plan only when a step fails.
RAG Agent with Grounded Citations
Retrieval-augmented answering that cites source chunks and refuses when the context does not support an answer.
ReAct Tool-Calling Agent Loop
A minimal, provider-agnostic reason-act-observe loop with a step budget, tool registry, and safe termination.
Supervisor Multi-Agent Router
A supervisor agent delegates sub-tasks to specialist agents with narrow tools and merges their outputs.
Complexity-Based Cheap/Strong Model Router
Route easy requests to a cheap model and hard ones to a strong model using a lightweight classifier plus escalation.
Local-First Routing with Ollama and Cloud Fallback
Serve requests from a local Ollama model, falling back to a cloud model only when local fails or the task needs it.
Semantic Response Cache in Front of LLM Calls
Reuse prior answers for near-duplicate prompts using embedding similarity with a strict threshold and TTL.
Reliable Structured JSON Output Pattern
Get valid, schema-conforming JSON from any model using native structured outputs where available, and validate-and-repair otherwise.
Build a Custom MCP Server in Python (MCPServer, formerly FastMCP)
Expose your own functions as MCP tools and resources using the official Python SDK in about 20 lines.
Get one fully built blueprint a week
A weekly email: one blueprint with config, cost, setup time and failure modes, plus a vote on what we build next.