Control retrieval, memory, routing, compression, and the information reaching each model call.
Tutorials
Explore the mechanisms, tradeoffs, and implementation patterns within this AI engineering track.
The prompt you spent a week tuning is not what the model reads. It reads everything in the window — and everything else is quietly voting.
Read tutorial
The prompt tested clean. Then real users arrived, and the answers went stale, contradictory, and ungrounded.
Read tutorial
This is the debugging scene every agent builder eventually hits, and it usually ends the same way: you rewrite a sentence in the system prompt, the symptom…
Read tutorial
The right information was somewhere in the system. It just never reached the decision that needed it.
Read tutorial
A support agent applies a customer's refund policy correctly in turn 4. In turn 9, it violates the same policy. The logs show the policy was never lost. It…
Read tutorial
The request fits. It returns a worse answer than the shorter prompt you shipped last week.
Read tutorial
A retrieval system can only return what a chunk contains. Cut the answer in half, and no reranker will put it back together.
Read tutorial
A retrieval system fails in a specific, repeatable way. You ship a demo that answers paraphrased questions beautifully, then a user pastes an error code, a…
Read tutorial
Your recall metric looks healthy. Your answers are still wrong. That gap is the whole reason advanced retrieval patterns exist.
Read tutorial
Watch a real session. A user types: "Compare the latency and cost of the two reranking options we discussed, for our EU deployment." Your hybrid retriever…
Read tutorial
Always-on retrieval is a fixed policy applied to a variable question distribution. It over-retrieves on questions the model already knew, and it…
Read tutorial
The retriever found the right document. The answer is still wrong. Somewhere between the vector store and the prompt, the evidence got buried under five…
Read tutorial
The agent remembered everything and still got the user wrong. It recalled a preference the user had abandoned six months ago, re-derived a workflow it had…
Read tutorial
The agent ran clean for forty steps. Then it re-ran a migration it had already finished, forgot the constraint the user stated at turn three, and quietly…
Read tutorial
A RAG feature ships. The answers read well. Someone wires up a faithfulness evaluator, the number lands at 0.87, and within a week that single scalar is…
Read tutorial
The demo works on turn one. By turn five, the agent is answering a question you already answered, citing a document it retrieved three turns ago, and…
Read tutorial