AI Agent Access

AI Agent Access lets your team connect approved assistants to CleanEstimate Pro without sharing a full user login. Each agent gets its own token, its own tool permissions, and a full activity trail.

What It Is

Agent access is designed for cases where you want an assistant to help with real work inside CE Pro, such as reviewing inbox activity, checking estimates, or supporting your team with fast answers.

Instead of giving the assistant broad account access, CE Pro creates a scoped token that limits what the agent can do.

Where To Set It Up

Go to Admin > AI > Agents.

From this page you can:

• Create a new agent token
• Choose which tools the token can use
• Keep the token read-only or enable guarded write actions
• Revoke a token at any time
• Review recent agent activity

Read-Only Access

New tokens should start as read-only. A read-only agent can help your team by retrieving information without changing customer records.

Common read-only use cases include:

• Reviewing inbox threads before a rep replies
• Looking up estimate status or customer history
• Summarizing lead activity for managers
• Answering internal questions about jobs, clients, or follow-ups

Guarded Write Access

If you enable write access, CE Pro still keeps the scope intentionally small. Guarded write tools are meant for low-risk workflow actions, not broad account edits.

Current guarded actions include:

• Adding an internal note to an inbox thread
• Updating whether a thread still needs a response

Every write requires a second confirmation step before CE Pro applies the change.

Activity And Audit Trail

Every agent request is logged. Your team can review:

• Which token was used
• Which tool the agent called
• When the action happened
• Whether it succeeded or failed

Use the activity log to confirm behavior, investigate mistakes, and decide whether an agent needs broader or narrower access.

Best Practices

• Start with read-only access and expand later only if needed.
• Create separate tokens for separate assistants or workflows.
• Revoke any token you no longer use.
• Review activity logs regularly, especially after enabling write access.
• Limit write access to trusted workflows with clear human oversight.