Methods and architectures for finding, ranking, routing, and preparing external information for AI-system use.
Tagged articles
13 articles in this tag.
Your recall metric looks healthy. Your answers are still wrong. That gap is the whole reason advanced retrieval patterns exist.
Read tutorial
Hop three. The context window is full. Half of it is plausible garbage — passages that matched the query, ranked well, and turned out to be useless. The…
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 vector search returns its nearest neighbors whether or not those neighbors answer the question. The pipeline reports no error, the generator receives…
Read tutorial
You have seen the failure. A research agent returns a polished report, the citations look real, and the first URL you check resolves to a page that does…
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
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
The demo worked. Then the corpus grew, the questions started requiring synthesis across documents, and the same pipeline that felt magical last month now…
Read tutorial
Ask a system to synthesize five documents into one answer. It does the work. Ask the same question tomorrow, and it does the work again, from scratch, with…
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
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
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 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