15% of exam score

Context Management & Reliability

Smallest weight. Failures cascade everywhere.

Context window management, RAG and retrieval, multi-pass and independent review, prompt caching, cost/latency tradeoffs, escalation logic.

Key insight

Progressive summarization silently CORRUPTS transactional data — amounts, dates, and order numbers become vague paraphrases. A persistent 'case facts' block that is never summarized and always included verbatim in every prompt is the correct fix.

The exam rewards

  • Extract transactional specifics (amounts, dates, IDs) into a persistent case-facts block and include it verbatim in every prompt — never let it be summarized
  • Three valid escalation triggers: customer explicitly requests a human, a policy gap exists, unable to make meaningful progress. Sentiment and self-reported confidence are NOT reliable triggers
  • The 'lost in the middle' effect is real — place key summaries and findings at the beginning or end of long inputs, not buried in the middle
  • When propagating errors in multi-agent systems, include: failure type, what was attempted, partial results obtained, and alternative approaches
  • Never silently suppress failures or terminate the full pipeline on one error — annotate, continue, report

Common anti-patterns

  • Using progressive summarization on conversations containing transactional data
  • Escalating based on customer frustration or detected sentiment
  • Escalating based on the model's self-reported confidence score
  • Terminating an entire pipeline workflow because a single tool failed

Lessons

Start sprint quiz for this domain
  1. 5.1 · Context window fundamentals
    5 sections
  2. 5.2 · RAG and retrieval patterns
    4 sections
  3. 5.3 · Multi-instance & multi-pass review
    4 sections
  4. 5.4 · Cost, latency, and reliability
    5 sections