Last updated: 2026-08-31 · 2 min read
Troubleshooting Agent Studio
When something is not right, check the goal, target Room, evaluation, deployment, and run result in that order. Do not add more permissions or connections before you know which stage differs from your expectation.
| State | Check first | Next action |
|---|---|---|
| The design is not what you meant | Does the goal say when, what to read, and what to return? | Make the ジャーニー (Journey) request more specific |
| Evaluation is insufficient | Did you include realistic materials and exceptions? | Adjust the draft and evaluate again |
| Approval is unavailable | Is the expected version and evaluation result selected? | Review シミュレーション (Simulation) reasons |
| A run cannot start | Is the Room selected, deployed, and runtime-ready? | Check 配備と実行 (Deploy & Run) |
| Output is unexpected | Which version and sources were used? | Open 実行レビュー (Run Review) |
| A webhook does not run | Is signature testing complete and the trigger active? | Ask a Workspace administrator to check the webhook configuration |
Make the goal specific
Vague request:
Check the deals.
Specific request:
Every business day at 9:00, review my stalled deals, propose the next action and evidence as a draft for each owner, and require review before external contact.
The second request makes the scope, timing, output, and boundary easier to verify.
Ask a Workspace administrator before enabling a new MCP connection, an external send, a Room update, a webhook, or any runtime setting you cannot change yourself.
Related articles
- Create your first read-only AgentUse plain language to create a safe first Agent that organizes meeting notes without changing anything
- Evaluate, approve, and deployCheck expected results in simulations before deploying an Agent to a Room
- Rooms, sources, connections, and permissionsUnderstand what an Agent can reference and what to check before enabling MCP or write actions