Where to change it
Open your agent in the Suppio dashboard, then select Sandbox from the agent navigation. The intelligence controls appear in the Sandbox sidebar. If you are opening the page directly, use this dashboard URL format:{workspaceId} with your workspace ID and {agentId} with the agent ID from the agent URL.
1
Open the dashboard
Sign in to Suppio and choose the workspace that owns the agent.
2
Open the agent
Select the agent you want to configure.
3
Open Sandbox
Click Sandbox in the agent navigation.
4
Choose reasoning
In the sidebar, confirm Model intelligence and choose Reasoning effort.
5
Send a test message
Each sandbox message uses the reasoning value currently selected in the sidebar.
Sandbox intelligence controls are used for sandbox test runs. They are not a separate saved Intelligence tab.
Unified intelligence
Every plan uses Suppio Intelligence. The underlying model and provider are managed by Suppio, so you do not need to choose between model families or update an agent when Suppio improves its intelligence. This applies to support replies and supporting workflows such as safety checks, actions, summaries, images, analysis, and escalation.Plan access
Reasoning settings
Reasoning effort controls how much analysis Suppio performs before answering a sandbox message.- Standard maps to medium reasoning and balances answer quality, speed, and credit usage.
- High maps to high reasoning for complex requests that need more careful judgment. High is available on paid plans.
- Reasoning affects response quality, latency, and credits.
What this affects
The Sandbox reasoning control affects the test message you send from Sandbox. Use it to compare answer quality, speed, and credit usage while preparing the agent.Tips
- Start with Standard for most support questions.
- Ask the same sandbox question with Standard and High to compare results.
- Watch Usage after testing with High reasoning.
- If answers are wrong because information is missing, update Context before increasing reasoning.