> ## Documentation Index > Fetch the complete documentation index at: https://docs.verisoul.ai/llms.txt > Use this file to discover all available pages before exploring further. # AI Agent > Ask questions about a project in plain English and get answers, charts, files and list changes back The AI Agent answers questions about your Verisoul data. It writes and runs its own queries across accounts, sessions, verifications, rules and lists, and returns text, charts, tables or files. It can also draft rules and change list membership, and it asks for approval before any change that affects live decisions. It appears in three places: | Where | What it does | | - | - | | **AI Agent** in the sidebar | Full chats about a project, kept in your chat history | | **Analyze with AI** on an account, ID Check or Face Match session | An analysis of that record, with follow-up questions | | **Ask AI** in the Accounts and Sessions tables | Turns a sentence into filters and a sort | The agent works in a private sandbox for each project, and your data is never used to train models. ## Scope Each chat reads one project, chosen before the first message and fixed after it. The agent can use: * Accounts and sessions, with their scores, signals and list membership * Rules, their definitions, and every time each one fired * Verifications, including ID Check and Face Match photos * Live state from the Verisoul API, such as a list's current members * The Verisoul documentation, for product and integration questions Mention records with `@`, paste up to 1,000 IDs in one batch, or attach files (up to 20 per message, 25 MB each). Prompts worth trying: * *Pull all accounts linked to `{account_id}` at above 50% strength, three levels deep* * *Compare fake and suspicious users over the last 7 days against the prior 7. What is driving the change?* * *Here are 100 emails. Find their accounts and add them to the block list.* ## Outputs | Output | Notes | | - | - | | Charts and tables | Downloadable, and can be added to a [custom dashboard](/dashboard/dashboards), where they re-run on live data | | Files | CSV and Excel exports, slide decks, Word documents and PDFs | | Rule suggestions | Drafted from your data, with the number of accounts they would match today | The agent does not create or turn on rules. **Review in Rules** opens the [rule builder](/dashboard/rules) with the suggestion filled in and backtesting running, and you save it from there. ## Changing lists The agent can create lists and add or remove accounts, from pasted IDs, attached files, or its own findings. | Change | Behavior | | - | - | | Custom list, up to 1,000 accounts | Runs immediately | | **Allow**, **Block** or **Main Account** | Waits for approval | | Any list, more than 1,000 accounts | Waits for approval | An approval card lists the change. **Approve** runs it and **Reject** discards it. List changes through the agent need the **Change Allow and Block lists** permission (Editor and Admin). For other roles, chats are read-only. Analysts can still manage custom lists from the **Lists** page. ## Analyze with AI On an account, the analysis reads your project's scoring thresholds, the lists the account is on, and the rules it hit. On a verification session, it also reads the captured photos and the session video. **Open full chat** continues the conversation in **AI Agent**. Incomplete verification sessions cannot be analyzed. ## Memory The agent keeps notes between chats: * **Per person:** stated preferences, such as preferred chart types or recurring breakdowns * **Per project:** what it has learned about the project's data and fraud patterns, shared with everyone who uses the agent on that project Personal data and credentials are not stored in memory. ## Sharing Only the person who started a chat can share it. | Option | Who can see the chat | | - | - | | **Share with project** | Everyone with access to the project, read-only. They can continue in their own copy. | | **Share publicly** | Anyone with the link, without signing in, including files and messages added later | Turning off **Share publicly** disables the link immediately. Turning it on again creates a new link. ## Scheduled runs A prompt can run on a schedule through the [MCP server](/dashboard/mcp-access), using `agent_schedules_create` with a cron expression in UTC or as a manual schedule. Each run opens a new chat for the schedule's creator and uses that person's permissions. Creating schedules needs **Schedule agent runs** (Editor and Admin). ## Permissions | Action | Viewer | Analyst | Editor | | - | - | - | - | | Chat, **Analyze with AI**, **Ask AI**, share chats | ✓ | ✓ | ✓ | | Add charts and tables to dashboards | | ✓ | ✓ | | Change lists | | | ✓ | | Schedule runs | | | ✓ | Admins have every permission. See [Managing Users](/dashboard/managing-users) for custom roles. ## Need Help? If you have any questions about the AI Agent, please contact our support team at [support@verisoul.ai](mailto:support@verisoul.ai).