Names concrete failure modes to test for in Opus 5 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 → setups: edits without reads, injected agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → text mistaken for directory contents, and context compactionSummarizing an agent's earlier conversation to free room in the context window so a long session can keep going.Full definition → dropping earlier user messages. Treat as one user's anecdotal evidence, not a measured result.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
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.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
