Selecting, organizing, compressing, persisting, and isolating information supplied to models across decisions and tasks.
Tagged articles
30 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
The demo agent works. It reads the file, runs the test, patches the bug. Then it ships to a second tenant, the session runs for six hours, the process dies…
Read tutorial
A user reports a wrong answer. You pull the trace. Every tool call succeeded, every span is green, latency is normal, and no error was logged anywhere. The…
Read tutorial
Every agent builder hits the same wall. The first working agent is small: a system prompt, a few tools, a loop. Then someone needs release notes. Someone…
Read tutorial
A team scaffolds an AGENTS.md with /init, the agent improves for a week, and then the file quietly becomes a 14k-token policy document that nobody reads…
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 demo works. The agent books the flight, summarizes the repo, files the ticket. Then you point it at a task with one extra branch, and it calls the same…
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
The agent writes the function, re-reads it, decides it looks correct, and stops. The code is wrong. This is the most common failure in autonomous coding,…
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 request fits. It returns a worse answer than the shorter prompt you shipped last week.
Read tutorial
The prompt tested clean. Then real users arrived, and the answers went stale, contradictory, and ungrounded.
Read tutorial
“Everything is a plugin” is a claim about architecture, not a feature list. It says the agent loop itself is replaceable — and that is expensive to mean.
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
The right information was somewhere in the system. It just never reached the decision that needed it.
Read tutorial
You tighten the system prompt. You add the word "always." You move the rule to the top. The model still ignores it, and you have no idea which part of the…
Read tutorial
The agent worked yesterday. Today it burns forty thousand tokens before it reads your first instruction, and the hook that used to register identity with 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
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 team wires up an MCP server, watches the tools appear in the client, and concludes the integration works. Then a tool gets renamed upstream, a resource…
Read tutorial
An agent that acts without reasoning is not reasoning. It is guessing with a tool schema.
Read tutorial
A team adds a "reflect" step to their agent. Scores tick up a few points. Encouraged, they bolt on a memory buffer so the agent can "remember its…
Read tutorial
That failure breaks the "bad answer means bad instruction" reflex. Sometimes the instruction is fine, and the bottleneck sits somewhere else: the model…
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
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 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
A prompt is a spark, not an engine. The spark still matters — it just cannot carry the machine.
Read tutorial