Flows workflow logoFlows
Prompt-Cache-Aware Conversation Design
0/3 steps0%

Step 1 of 3

Audit context stability

Find every byte that changes between turns - each one is a cache killer.

First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.

Prompt Capsule
Audit my agent's context assembly for cache hostility. Capture the exact assembled context for three consecutive turns and diff them. Classify every difference: EXPECTED GROWTH (new turns appended at the end - fine), PREFIX MUTATIONS (anything changing before the append point - cache killers), and VOLATILE INJECTIONS (timestamps, counters, randomized ordering, per-turn IDs inside stable sections). Common culprits from harness analyses: current-time in the system prompt, re-rendered plan blocks at the top, tool definitions re-serialized in unstable order. Produce the diff report with each mutation's source located in code.
Paste into EmergentFull Build: complete implementation prompt with explicit requirements

Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.

Actual change check

Expected after this step

A three-turn diff report locating every prefix mutation.

Should NOT happen

  • An existing feature broke
  • A button only logs to console
  • Data disappears after refresh
  • Errors fail silently with no visible state

This is what should exist before you continue. If reality does not match, do not move on.

Track what changed, failed, or needs follow-up. Notes export with the flow.

Made with Emergent