Do Prompt ao Protocolo: construindo agentes com MCP, RAG e IA aplicada
A hands-on workshop moving from prompts to tool-using agents, retrieval, MCP services, collaborative patterns, and an executable Docker-based reference architecture.
field notes · talks · releases · experiments
Durable context from the systems lab: what was built, what changed, what failed, and which decisions were worth carrying into the next system.
The archive starts with public workshops and releases. Build notes, retrospectives, and deeper technical writing come next.
A hands-on workshop moving from prompts to tool-using agents, retrieval, MCP services, collaborative patterns, and an executable Docker-based reference architecture.
Why web extraction breaks, how LLMs can help interpret changing pages, and where deterministic validation still has to own the result.