> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/dapti.md).

# Dapti

- [Start here](https://docs.dapta.ai/dapti/dapti.md): Dapti is your AI assistant inside Dapta. What it can do, how to open it, and how to read what it gives you back.
- [Interface Guide](https://docs.dapta.ai/dapti/interface-guide.md): A field guide to every part of the Dapti chat interface: the home page, the chat input, conversation history, the activity panel, message actions, and the feedback form.
- [Capabilities](https://docs.dapta.ai/dapti/capabilities.md): An index of everything Dapti can help you with, grouped by area: build and improve agents, analyze performance, automate and schedule, manage your business, and research.
- [Voice Agents](https://docs.dapta.ai/dapti/capabilities/voice-agents.md): Use Dapti to create voice agents conversationally, improve prompts, and tune voice settings without ever leaving the chat.
- [Text Agents](https://docs.dapta.ai/dapti/capabilities/text-agents.md): Use Dapti to create text agents, improve prompts, and fine-tune chat behavior without leaving the conversation.
- [Call Analytics](https://docs.dapta.ai/dapti/capabilities/call-analytics.md): Ask Dapti to pull call stats, review individual calls, surface patterns across calls, and recommend what to improve next.
- [Flow Studio](https://docs.dapta.ai/dapti/capabilities/flow-studio.md): Ask Dapti to design, build, deploy, list, and modify Flow Studio automations from a conversation.
- [Account Evaluation](https://docs.dapta.ai/dapti/capabilities/account-evaluation.md): Ask Dapti to evaluate your whole account: scorecard your setup, diagnose what is blocking progress, and prioritize the single next thing to do.
- [Industry Benchmarks](https://docs.dapta.ai/dapti/capabilities/industry-benchmarks.md): Ask Dapti to compare your account against your industry on Dapta, surface what the best performers in your vertical do differently, and translate that into concrete improvements.
- [Sales Meetings](https://docs.dapta.ai/dapti/capabilities/sales-meetings.md): Ask Dapti about your sales meetings: list them, get structured summaries with action items, and surface patterns across multiple meetings.
- [Billing & Credits](https://docs.dapta.ai/dapti/capabilities/billing-and-credits.md): Ask Dapti about your credit usage, plan tier, what each plan includes, and how to estimate the cost of a sequence before you run it.
- [Scheduled Tasks](https://docs.dapta.ai/dapti/capabilities/scheduled-tasks.md): Use Dapti to schedule recurring tasks: daily reports, periodic flow runs, cron jobs, and one-time reminders, all set up from a conversation.
- [Web Research](https://docs.dapta.ai/dapti/capabilities/web-research.md): Ask Dapti to search the web, read external URLs, and generate downloadable research documents grounded in real sources.
- [Commercial Support](https://docs.dapta.ai/dapti/capabilities/commercial-support.md): Ask Dapti about plan upgrades, custom contracts, talking to sales, and the partner or affiliate programs.
- [Use Cases](https://docs.dapta.ai/dapti/use-cases.md): A cookbook of practical things you can ask Dapti, organized by intent and paired with concrete example prompts you can copy.
- [Privacy & Scope](https://docs.dapta.ai/dapti/privacy-and-scope.md): Understand what Dapti can and cannot see: workspace scope, account boundaries, industry benchmarks, and the privacy guarantees built in.
- [Tips & Prompting](https://docs.dapta.ai/dapti/tips-and-prompting.md): Tips to get more out of Dapti: how to phrase questions, attach images, switch languages, follow up effectively, and recover from a bad answer.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.dapta.ai/dapti.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.