Integrations
Connect Trefur to the platforms your team already uses. Trefur pulls activity via official admin APIs — no SDK install, no code change in the agents themselves.
How OAuth-based discovery works
- In the Trefur dashboard, open Integrations and pick a platform. You see a plain-English explanation of which OAuth scopes will be requested and what each scope grants access to.
- Pick the read-only access you want. Trefur asks for the minimum scopes needed to provide the selected visibility.
- You're bounced through the platform's OAuth consent screen. We never see your password.
- On success, Trefur stores a refresh token in a credential vault and kicks off an instant initial scan. Subsequent polls are incremental.
Supported platforms
| Platform | What you get | Setup |
|---|---|---|
| Google Workspace | Audit logs, Gemini activity, third-party OAuth-grant inventory | Walk-through → |
| Microsoft 365 | Audit logs, Copilot prompt counts | Walk-through → |
| OpenAI | Admin API: org + per-user usage | Walk-through → |
| Anthropic | Admin API: workspace + per-key usage | Walk-through → |
| Slack | Bot + integration activity | Walk-through → |
| Atlassian | Jira + Confluence agent activity | Walk-through → |
| Zendesk | Support-agent + AI macro activity | Walk-through → |
| HubSpot | Workflow + AI assistant activity | Walk-through → |
| Intercom | Fin AI + Custom Bot activity | Walk-through → |
| Salesforce | Einstein + Agentforce + Flow activity | Walk-through → |
| GCP | Vertex AI + Gemini API + Cloud Run agent visibility | Walk-through → |
| AWS | Bedrock + SageMaker + Lambda visibility | Walk-through → |
| Azure | Azure OpenAI + Cognitive Services + AI Foundry visibility | Walk-through → |
| Snowflake | Cortex AI + Snowpark agent visibility | Walk-through → |
| Databricks | MLflow + Mosaic AI Agents visibility | Walk-through → |
Privacy
Trefur uses read-only OAuth scopes wherever possible. Every credential carries a redaction level that cascades most-restrictive-wins through tenant default → OAuth credential → ingest key → individual request. You cannot accidentally broaden access at a deeper layer.
For prompt-level fidelity (the platform admin APIs don't return prompt + response bodies — that's a platform limitation), install the appropriate SDK or run the collector's LLM proxy in front of outbound model traffic.