AI Settings and Controls
The AI Controls page lets Organization Admins manage Global Agent availability, customize AI context, configure model providers, and set data retention policies.
AI Controls settings
Access organization-level AI Controls from Settings > AI Controls.
The AI Controls page includes:
- Global Agent availability: Show or hide Global Agent and enable or disable it for your organization.
- Audit: View all user activity within Global Agent across your organization.
- AI context: Provide instructions and upload reference files to help Agents understand your business.
- Model providers: Enable or disable specific AI model providers.
- Data retention and privacy: Configure how long Amplitude stores AI conversation data.
- Disable all AI: Contact Amplitude support to turn off all AI features across your organization.
Global Agent availability
Control whether Global Agent appears in your organization's interface.
- Navigation visibility: Toggle Show Global Agent in sidebar to show or hide Global Agent from the left-side navigation bar for all users.
- Feature access: Toggle Enable Global Agent for organization to allow or block users from interacting with Global Agent features.
These settings affect all users in your organization. Individual users can't override organization-level visibility or access settings.
Audit
The Audit tab gives organization admins visibility into how users interact with Global Agent across the organization. Use this tab to monitor usage and verify that Global Agent operates as expected.
View the audit log
- Navigate to Settings > AI Controls.
- Select the Audit tab.
- Review the table of Global Agent threads.
The audit log displays all Global Agent conversation threads from users in your organization. Each entry shows details about the thread, including the user who initiated it and when the conversation occurred.
Use cases for audit
Use the audit log to:
- Monitor adoption: Track how many users engage with Global Agent and how often.
- Verify appropriate use: Ensure users interact with Global Agent according to your organization's guidelines.
- Troubleshoot issues: Investigate specific conversations when users report problems or unexpected behavior.
- Inform context improvements: Identify patterns in user questions to improve your AI context configuration.
Only organization admins can access the Audit tab. Individual users can't view other users' Global Agent activity.
AI context
Provide custom instructions that teach Agents (both Global and Specialized) how your business works. For guidance on writing effective context, see AI context.
Two levels of context
Agents use two layers of context: Organization and Project.
- Organization context: Applies to all projects. Use for company-wide standards like business model, KPI definitions, standard terminology, and global filters. Limit: 10,000 characters.
- Project context: Applies to one project. Use for product-specific events, metrics, segments, and overrides to org defaults. Limit: 10,000 characters.
At runtime, Agents receive both context sources. Project context overrides organization context when they conflict.
Text instructions
Enter your context as structured markdown text. Use headings, bullets, and backticks to make it easy for Agents to parse.
To add text instructions:
- Navigate to Settings > AI Controls.
- In the AI Context section, select the Organization or Project tab.
- Enter your instructions in the text field.
- Select Save.
File uploads
Upload reference files for Agents to use alongside your text instructions. Files provide additional context without consuming your 10,000-character instruction limit.
Supported file formats:
| Type | Formats | Size limit |
|---|---|---|
| Documents | TXT, MD, HTML, DOC, DOCX, PDF | 50 MB |
| Spreadsheets | CSV, XLS, XLSX | 50 MB |
| Images | JPG, PNG | 3.75 MB |
To upload a file:
- Navigate to the AI Context section of the AI Controls page.
- Select Upload file.
- Choose one or more files to upload.
Use file uploads for:
- Data dictionaries or event catalogs in spreadsheet format.
- Product requirement documents or specifications.
- Style guides or documentation standards.
- Reference images for UI-related questions.
File uploads supplement your text instructions—they don't replace them. Use text instructions for rules and definitions, and file uploads for detailed reference material.
{{##
Model providers
Enable or disable specific AI model providers for your organization.
| Provider | Models |
|---|---|
| Anthropic | Claude Sonnet, Claude Opus |
| Gemini Flash, Gemini Pro | |
| OpenAI | GPT |
Toggle each provider on or off based on your organization's policies. Amplitude recommends keeping all providers enabled for the best experience.
Disabling a provider may degrade performance across certain AI features. Only disable a provider if your organization's security or compliance policies require it.
##}}
Data retention and privacy
Configure how long Amplitude stores AI conversation data.
Data privacy
Amplitude doesn't store your data with third-party AI providers. Your data is never used for model training by Amplitude or its partners.
Retention period
Set the retention period to control how long Amplitude stores conversation logs before automatic deletion. Adjust this setting based on your organization's data governance requirements.
For detailed information about AI data handling, privacy, and security, refer to Privacy and security.
Disable all AI
To disable Global Agent for your organization, use the toggles in the Global Agent availability section. You can also toggle other individual AI features on or off from Settings > AI Controls.
To disable all Amplitude AI features across your entire organization, contact Amplitude Support. Amplitude processes opt-out requests and disables all AI functionality for your organization.
Disabling individual features from the settings page doesn't turn off all AI. For a complete AI opt-out, contact Amplitude Support.
Frequently asked questions
Was this helpful?