Back to index

Guides

Notes on setting up a RAG, an agent or n8n. Written for another engineer.

These pages are notes on how I set this up. They are not delivery case studies.

If you want me to leave it running, that is on RAG and agents. Madrid.

  1. Set up an internal RAG A bounded set of docs, search with a source, and a chat or API the team can use.
  2. Data and access for a private GPT What goes in, who may ask, and what stays out of a public model.
  3. Agent, chatbot or n8n How to pick the deliverable. Logs, a perimeter and an owner for the deploy.
  4. Why not to paste internal PDFs into ChatGPT The habit of pasting documents into a public chat, and the system that replaces it.
  5. From the wiki or Drive to answers with a source Ingestion, index and citations so each answer can be checked in the original document.
  6. n8n on email or CRM What the flow may read or write, and where a human confirms before sending or updating.

Contact

Email me

If you need an agent, a RAG or an n8n flow set up, email or call.