Study guides / CCAO-F

Quick reference

One condensed cheat-sheet per domain - the tables and rules worth re-reading right before the exam.

Model Tiers: Haiku vs. Sonnet vs. Opus

The trade-off is always the same one: speed and cost on one side, depth of reasoning on the other. Match the tier to the task's volume, complexity, stakes, and autonomy length — don't default to either extreme.

TierSpeed / CostBest ForWatch Out For
HaikuFastest, cheapestHigh-volume, simple, well-defined work: ticket tagging, field extraction, quick factual lookupsReaching for it 'to save cost' on long, high-autonomy, high-complexity work — early mistakes compound
SonnetBalancedDefault all-rounder: drafting, editing, analysis, everyday coding, summarizingTreating it as always-correct-by-default even when a scenario clearly points to Haiku or Opus
OpusSlowest, most expensive per requestLong, high-autonomy runs or single highest-stakes decisions where accuracy matters far more than cost/speedReaching for it 'to be safe' on high-volume, simple jobs — adds cost/latency the task doesn't need

Effort Parameter vs. Model Choice — Which Lever?

Two separate, related decisions. Model tier decides which model family does the work at all. Effort decides how thoroughly that already-chosen model works on this particular request. Effort can't grant a tier capabilities it doesn't have; tier choice doesn't remove the value of tuning effort.

QuestionLeverExample
Does this task need a different level of reasoning capability?Model tier (3.1)50,000 tickets/day → Haiku; multi-hour codebase refactor → Opus
Is the model already right — should it just work more/less carefully on this request?Effort parameterQuick syntax sanity check → low effort; careful audit of interdependent formulas → high effort, same model

Which Claude Product Feature?

Work through these questions roughly in order — each solves a different problem.

NeedFeatureSignal
Available across many future conversationsClaude ProjectYou'd otherwise re-paste it into every new chat: style guide, client background, standing facts
Current info from multiple external sources, citedResearch modeAnswer requires finding and sourcing information Claude doesn't already know
Long-form, self-contained, or iteratively-edited outputArtifactA report, essay, or prototype the user will keep revising, not just read once
Fundamentally comparative or tabular outputStructured output (table)Rows/columns meant to be scanned side by side rather than read as prose
None of the abovePlain chat replySelf-contained answer read once — the lightweight default

Features layer together rather than being either/or: a Project conversation might use research mode, then place the synthesized findings into an Artifact for further editing.

Context Limit Signals: Restart, Summarize, or Persist?

Degradation signals: Claude forgets or misapplies an early rule, contradicts an earlier decision, re-asks something already answered, or mishandles a document pasted many messages ago. The fix is structural, not louder wording.

SignalResponseWhy
Most of the thread's content is irrelevant to what's nextRestart — brand-new conversationClean slate avoids dragging irrelevant baggage forward
Real decisions/facts still needed, but the thread has grown unwieldySummarize, then continue in a new conversation seeded with that summaryPreserves what matters while shedding the excess length causing degradation
Standing reference needed across many future, even unrelated, conversationsPersist to Project knowledge base or custom instructionsTest: would you otherwise re-paste or re-summarize it every time? If yes, persist it.

Long Documents Hit the Same Limit

Context limits aren't only about conversation length — a single very long document competes for the same limited attention as everything else in the conversation.