> For the complete documentation index, see [llms.txt](https://help.pickyassist.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.pickyassist.com/setting-up-guide/ai-agent/faq.md).

# FAQ

#### What is the difference between Collect and Extract fields?

Collect fields are information the agent asks customers to provide. Extract fields are information the agent identifies automatically from messages, documents, or images.

#### How many Knowledge Base documents can I add?

You can upload up to two PDFs per AI Agent. Each document can be up to 15 MB.

Supported formats include PDF, DOC, DOCX, XLS, XLSX, PPT, PPTX, and TXT. Text topics have no fixed count limit, but each topic should stay below approximately 2,500 characters.

#### Which AI models can I use?

Available models depend on the AI providers enabled in your Picky Assist account. Choose from the models shown for your selected provider in **Settings**.

#### Should I enable reasoning?

Enable reasoning for complex, multi-step, or conditional decisions. Leave it disabled for basic questions and data collection to reduce cost and response time.

#### How can I use collected data later in the flow?

Use the corresponding Attribute token in later flow steps. For example:

`{{AIAgents.collected.<field_name>}}`

If conversation summarization is enabled, use its summary Attribute as well.

#### Can I use more than one AI Agent in a flow?

Yes. For example, use one AI Agent for lead qualification and another for customer support.

Use distinct field names across agents to avoid Attribute confusion.

#### How can I test the AI Agent before publishing?

Use **Test Agent** in the Configure Agent window, or **Via TestBot** in Flow Builder.

#### What happens if a customer stops responding?

Configure Follow-up messages for inactive customers. You can also configure conversation limits and timeout behavior in **Settings**.

#### What happens when I change the AI Agent persona?

Your customized instructions remain unchanged unless you choose the new persona template. Other configuration tabs remain unchanged.

#### How is AI Agent cost calculated?

Cost depends on input tokens, output tokens, reasoning tokens, customer file or image processing, and the selected provider and model.

#### Can AI Agent respond in the customer's language?

Yes. The agent can respond in the customer's language. Add explicit language requirements in **Instructions** when needed.


---

# 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://help.pickyassist.com/setting-up-guide/ai-agent/faq.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.
