Page 3 of 8~96 min topic

Prompt caching

Learn the controls and knobs

Each prompt caching control is a hypothesis about a metric under a workload—not a synonym for quality on the policy-manual assistant.

~12 min this pageControls

1Learn the idea

Read

Control map

Primary knobs for prompt caching: prefix length, cache TTL, explicit cache keys, suffix-only inputs, invalidation on doc edit.

Write a sheet for the policy-manual assistant with columns: control, current value, predicted benefit, predicted cost, rollback trigger. Fill it using this topic’s real tension: A longer cached prefix can save more input work but may carry irrelevant context and increase uncached misses when any early token changes. Explicit caches improve control but require lifecycle management.

Change one prompt caching family at a time. If you move two knobs and the policy-manual assistant improves, you learned a cocktail, not a cause—and you cannot roll back surgically.

Read

Product exposure

End users of the policy-manual assistant should see only safe dials related to prompt caching. Infrastructure limits, private prompts, and policy thresholds stay server-owned. A user-facing control that bypasses those limits is a vulnerability dressed as UX for prompt caching.

Read

Make it operational

Publish the prompt caching control sheet next to the policy-manual assistant runbook. On-call should see which knob moved in the last deploy without reading chat archaeology. Unknown prompt caching knobs are unowned knobs.

Also pin one numeric memory from this prompt caching chapter: without caching: 12.3M input tokens/day; with 90% prefix hits: 1.2M uncached prefix + 0.3M suffix = 1.5M full-price-equivalent tokens before cache-read pricing That number is not decoration; it is a template for how claims about prompt caching on the policy-manual assistant should look in design docs. Scoped specifically to prompt caching / policy-manual assistant / controls-and-knobs.

Read

Common mix-ups

People confuse prompt caching with neighboring buzzwords when debugging the policy-manual assistant. Before changing prompts, ask whether the broken stage was evidence gathering, the prompt caching judgment itself, validation, or the product action. Fixing the wrong stage creates folklore (“we tried prompt caching and it failed”) that blocks the next team on the policy-manual assistant. Scoped specifically to prompt caching / policy-manual assistant / controls-and-knobs.

Read

Rehearsal (prompt-caching/controls-and-knobs)

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to prompt caching rather than generic AI advice.

Read

Rehearsal (prompt-caching/controls-and-knobs)

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to prompt caching rather than generic AI advice.

Read

Rehearsal (prompt-caching/controls-and-knobs)

Write a five-line artifact for this page: goal, inputs, check, owner, stop rule. Invent one fluent failure that the check would catch. Keep details specific to prompt caching rather than generic AI advice.

Go deeper

Before you start

Why this matters

From [prefix length, cache TTL, explicit cache keys, suffix-only inputs, invalidation on doc edit], pick one control for prompt caching on the policy-manual assistant. Predict which metric rises and which cost rises if you increase it.

In the wild

See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.

Check your understanding

Page assessment

Answer from memory. Completion is saved from this evidence, not from opening the next page.

1. What is one idea from this page you would apply, and what evidence would you check?

All responses are required.