Iterative control patterns in which an AI system acts, observes outcomes, evaluates progress, revises, and terminates under defined conditions.
Tagged articles
28 articles in this tag.
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 prompt fix that passes the demo and fails two weeks later is not a bad prompt. It is an improvement process with no memory.
Read tutorial
An agent that has run forty steps and produced an answer no better than step three is not stuck. It is broken in a specific, nameable way.
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
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 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
An evaluator is only as useful as the set of distinct repair actions its output can select.
Read tutorial
"Self-improving agent" is three different mechanisms wearing one coat. Pull the coat off and you find a memory that accumulates, a skill file that gets…
Read tutorial
The demo works. The agent reaches a consequential step, pauses, and asks a human to approve. The human clicks approve. Then the resumed run re-executes the…
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
An agent processes 200 units of work over four hours, dies on unit 201, and restarts from zero. The crash is not the failure. The failure is that nothing…
Read tutorial
A goal-based agent that never terminates is not a model failure. It is a contract failure.
Read tutorial
An agent that plans beautifully and then executes a stale plan into a wall is not a planning failure. It is a state failure.
Read tutorial
A plan that reads like a clean numbered list can still deadlock at runtime, because the list never told the scheduler which steps actually depend on which…
Read tutorial
An agent that acts without reasoning is not reasoning. It is guessing with a tool schema.
Read tutorial
A coding agent is handed a fixed training script and a fixed success metric: make it run faster without breaking correctness. It rewrites, runs, times, and…
Read tutorial
You add a critique-and-revise step. The output gets longer, more confident, more padded with caveats. Your eval score does not move.
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
A linear agent loop is a commitment device. It commits to one trajectory, and every later step inherits the consequences of the earliest mistake.
Read tutorial
You ask the model to critique its own draft. It returns: "The response is clear and well-structured, but could be more specific." You ask it to revise. The…
Read tutorial
The loop that improves the harness can also edit the evaluator, the permissions, and the rollback path. That is the whole problem in one sentence.
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
Two teams run the same model on the same task. One ships reliably. The other drowns in tool-call latency, context bloat, and incidents nobody can explain…
Read tutorial
A scheduled agent that opens two pull requests for the same dependency bump is not a model problem. It is a delivery-semantics problem wearing a model…
Read tutorial
Two teams ship the same model, the same prompt, the same tool list. One agent finishes a multi-step task. The other stalls, loops, and quietly corrupts its…
Read tutorial
A prompt is a spark, not an engine. The spark still matters — it just cannot carry the machine.
Read tutorial