Multi-tenant RAG: isolating client data in AI agents
The problem When you build an AI agent for one client, RAG is straightforward: embed their docs, store them, query them. But the moment you take a…
Notes
Real constraints, tradeoffs and things that broke while shipping AI, automation and web work — written in Pedro's voice, not a content calendar.
The problem When you build an AI agent for one client, RAG is straightforward: embed their docs, store them, query them. But the moment you take a…
The problem Every AI image model I've used mangles text. Quotes, numbers, names — they come out as gibberish far more often than not. For many uses…
The problem A dentist I work with spends half the consultation typing notes into a patient record. The other half, they're wrestling with the UI. The…
The problem LLM outputs are nondeterministic. The same prompt gives you a different answer every time. So how do you test a system whose core is a…
When a client's real estate site has 1,400 listings in four languages and Google is showing exactly three of them, the problem isn't translation.…
The first month of the Telegram bot was a lesson in model bills. Social Command Center turns one idea into four platforms of copy plus an AI image,…
When Cabarete Villas asked me to build their booking platform, they had a specific pain: guests booking the same villa on Airbnb and VRBO because the…