Collection

Make the agent loop finish, recover and stay inspectable

Turn current 2025-2026 agent engineering into practical controls for bounded loops, context, memory, checkpointing, evaluation and trajectory monitoring.

15 elements · Explore in any order.

1 checklist · 1 heuristic · 3 principles · 10 protocols

Narrow your search

15 elements

Protocol

Bound every autonomous agent loop before it starts

A loop without a hard edge is an outage waiting for a goal condition to fail.

Read the idea
Protocol

Write the completion condition before the agent starts iterating

An agent loop cannot finish reliably if 'done' exists only in the model's mood.

Read the idea
Protocol

Detect stagnation separately from completion

More motion is not the same thing as more progress.

Read the idea
Heuristic

Treat repeated state-action pairs as a loop alarm

If the state did not change, the same action is usually a retry—not a new strategy.

Read the idea
Principle

Retry after a state change; replan after the same failure

A retry is justified by changed conditions; otherwise it is often just repetition.

Read the idea
Protocol

Checkpoint meaningful progress before a long agent crosses a fragile boundary

Progress that exists only in the current context window is not durable progress.

Read the idea
Principle

Store durable task state outside the context window

Context is working memory, not a durable project database.

Read the idea
Protocol

Compact context by preserving decisions and unresolved work—not every tool result

Compaction should save the project, not the transcript.

Read the idea
Principle

Retrieve context just in time instead of preloading the whole project

Relevant context is valuable; irrelevant context taxes every token after it.

Read the idea
Protocol

Let subagents write durable artifacts instead of relaying everything through the coordinator

Every relay is another chance to lose detail.

Read the idea
Protocol

Evaluate the same agent task across multiple trials

A nondeterministic system needs more than one audition.

Read the idea
Protocol

Read eval transcripts before trusting the score

A score can fail because the agent failed—or because the eval did.

Read the idea
Protocol

Combine grader types instead of asking one LLM judge to decide everything

A flexible judge is useful; a monoculture of judgment is fragile.

Read the idea
Checklist

Track tool errors, tool calls, runtime and tokens as agent diagnostics

The path to the answer reveals inefficiency before users notice the bill or latency.

Read the idea
Protocol

Monitor the whole agent trajectory, not only individual allowed actions

A safe-looking step can participate in an unsafe-looking trajectory.

Read the idea