Agent Blueprints
Ready-to-run AI agent implementations. Complete system prompts, tool definitions, and initialization code for research, code review, and content writing agents.
Agent Blueprints
Each blueprint is a self-contained agent — system prompt, tool definitions, initialization code, and a walkthrough of how it handles a real task. Designed to work with OpenAI and Anthropic APIs. Framework-agnostic.
Note:
Start with the Research Agent. It uses the simplest tool set and demonstrates the ReAct loop clearly. Then move to Code Review (file system tools) and Content Writer (multi-step pipeline).
Prerequisites
All blueprints expect Python 3.10+ and an API key (OpenAI or Anthropic). Install the client library:
pip install openai anthropic
Research Agent
Code Review Agent
Content Writer
All Blueprints
- Research Agent — Web search, extraction, fact-checking, and citations
- Code Review Agent — Lints, flags risky patterns, and suggests refactors
- Content Writer Agent — Multi-step outline → draft → edit pipeline
- Testing Agent — Finds coverage gaps and generates unit tests
- Contract Review Agent — Extracts clauses, flags risks, summarizes contracts
- File-Based ETL Agent — Infers schemas and builds documented pipelines from CSV/JSON
- SQL Agent — Natural language to validated SQLite queries
- Data Insights Agent — Stats, correlations, outliers, charts, and written insights
- Incident Runbook Agent — Severity classification, timelines, and postmortem drafts
- Multi-Agent Orchestrator — Manager-worker delegation across researcher/coder/writer
- HF Spaces Multi-Agent Chain — Chain hosted Hugging Face Spaces via agents.md
- Datasette Agent Tool Gating — Permission-gated write tools with user approval
- Autonomous Researcher (Firecrawl MCP) — Recursive crawling and dossier storage via MCP
Related Articles & Guides
#ai-agentsAI Agent Blueprints & Configurations
Ready-to-run AI agent blueprints, configurations, and local setup guides. Build research agents, code reviewers, and content writers with copy-paste implementations.
#agentsBuilding Autonomous Research Agents with Firecrawl & Brave Search
Production blueprint for building automated research agents using Firecrawl MCP, Brave Search API, and LLM synthesis with anti-bot resilience.
CodeAgents + Structure: Why Enforcing JSON Format on Code-Generating Agents Actually Works
HuggingFace's structured code agent approach combines constrained JSON output with executable Python code to fix the parsing failures, hallucinated tool calls, and malformed actions that plague both JSON-based and free-form code agent architectures.