Tauseef FayyazA to Z
Glossary
Every concept in this sheet, plus the smaller terms it uses. Select a concept to open its card.
A
- AI orchestrator
- The code that turns one user message into model calls: it loads memory, rewrites the query, retrieves, builds the prompt, runs the tool loop and applies guards.
- Auth and chat history in the UI
- The frontend holds a session or token and loads past conversations from the backend, never from local storage alone.
- Authentication and authorisation
- Authentication proves who the user is; authorisation decides which chats, documents and tools they may use.
B
- Business logic outside the prompt
- Plans, quotas, pricing, which documents a team owns and what an action may change are decided in normal code and data, then passed to the model as facts.
C
- Chat UI
- Message list, input box, stop button, retry, copy, citations shown as links and a thumbs up or down on each answer.
D
- Data stores in a GenAI app
- Usually four: the main database (users, chats, messages), a vector index (often inside Postgres), object storage for uploads, and a cache such as Redis.
F
- File uploads
- The browser uploads to object storage (often with a short-lived signed URL), then tells the backend the file id so a worker can parse and index it.
M
- Model client wrapper
- One small module that every model call goes through.
N
- No model keys in the frontend
- The browser never calls the model provider directly with your API key; every call goes through your backend.
R
- Rate limits and quotas
- Limits per user and per IP on requests per minute, plus a daily token or cost budget per user or team.
- Request flow end to end
- Frontend sends the message to your backend API.
- Request path vs background jobs
- Chat replies run in the request.
- Request validation
- Check message length, file ids, conversation ownership and allowed options with a schema before doing any work.
S
- Streaming to the browser
- The backend sends tokens as they arrive, usually over server-sent events, and the UI appends them to the last message.
- Structured logging
- Every request logs a request id, user id, route, status, latency, model, tokens and cost as structured fields, not free text.