1# Steps 6–7 — Optimize Prompt & Deploy New Version
2 
3## Step 6 — Optimize Prompt
4 
5> ⛔ **Guardrail:** When optimizing after a dataset update, do NOT remove dataset rows or weaken evaluators to recover scores. Score drops on a harder dataset are expected — they mean test coverage improved, not that the agent regressed. Optimize for NEW failure patterns only.
6 
7Use **`prompt_optimize`** with:
8 
9| Parameter | Required | Description |
10|-----------|----------|-------------|
11| `developerMessage` | ✅ | Agent's current system prompt / instructions |
12| `deploymentName` | ✅ | Model for optimization (e.g., `gpt-4o-mini`) |
13| `projectEndpoint` or `foundryAccountResourceId` | ✅ | At least one required |
14| `requestedChanges` | | Concise improvement suggestions from cluster analysis |
15 
16**Example `requestedChanges`:** *"Be more specific when answering geography questions"*, *"Always cite sources when providing factual claims"*
17 
18> Use the optimized prompt returned by the tool. Do NOT manually rewrite.
19 
20## Step 7 — Deploy New Version
21 
22> **Always confirm before deploying.** Show the user a diff or summary of prompt changes and wait for explicit sign-off.
23 
24After approval:
25 
261. Use **`agent_update`** to create a new agent version with the optimized prompt
272. Use **`agent_get`** to verify the updated version is `running`
283. If the updated version is not `running`, read and follow the [troubleshoot skill](../../troubleshoot/troubleshoot.md) before continuing
29 
30## Next Steps
31 
32When the new version is running → proceed to [Step 8: Re-Evaluate](compare-iterate.md).
33