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.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
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.
Why it matters
Factory built a probe-based evalA 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.Full definition → to test whether context compactionSummarizing an agent's earlier conversation to free room in the context window so a long session can keep going.Full definition → actually preserves what an AI agentAn 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.Full definition → needs, and found structured summarization beat comparable approaches from OpenAI and Anthropic without hurting compression efficiency.
