• context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.

Context compaction is a measurable subagent job, not an implementation detail. The piece gives a probe-question eval design you can reuse to decide which model handles summarization in a long agent session.

• articleUltra Fast Apply Edit With Mercury Coder
• articleMercury Refreshed
• articleIntroducing Mercury
• articleMercury 2 The First Reasoning Model Fast Enough To Pick Up The Phone

• articleEvaluating Context Compression for AI AgentsFactory
• clipPrompt optimizer as reflect plus synthesize sub-agents with an agent storeAI Engineer
• clipAuto-compaction for long-running agentsAI Engineer

Checking sign-in…

Loading comments…