Context & Reliability — Curriculum
Context Management & Reliability · 15% of the exam. 6 lessons.
1. Context Windows and Token Budgeting
The context window is a shared, finite budget for input and output tokens, not just the visible chat text.
2. Prompt Caching Mechanics
Prompt caching reuses a stable prefix server-side, but only the content before the first change stays cacheable.
3. Compaction and the Summarization Trap
Compaction frees context space by condensing history, but over-compacting drops details the model still needs.
4. Idempotency and Error Propagation
Idempotent tool calls survive retries safely; error handling should match response severity to failure criticality.
5. Escalation on Ambiguity
Escalate to a human only when a decision is high-stakes, hard to reverse, and confidence is genuinely low.
6. Evals and Information Provenance
Evals catch regressions systematically, and provenance tracking prevents misplaced trust in conflicting context.