> For the complete documentation index, see [llms.txt](https://docs.spara.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.spara.com/solutions-engineer/practice/ai-prospect.md).
# AI Prospect and practice calls
Create an AI Prospect agent that plays a buyer from a persona you write, then run a practice call with it, with Samantha's cards alongside.
An **AI Prospect agent** plays a buyer from a persona you write, so you can rehearse a call, test Samantha, or demo her without a real prospect on the line. It joins the meeting as its own participant, and it works on its own or alongside Samantha.
## Create an AI Prospect agent
{% stepper %}
{% step %}
### Create the agent
On the [**AI Prospect agents**](https://app.spara.co/meeting-agents/ai-prospect-agents) tab, click **New AI Prospect agent**, give it a name, and click **Create**. The list and its menu work like the Live Assistant agents tab in [Set up Samantha](/solutions-engineer/getting-started/set-up-samantha.md).
{% endstep %}
{% step %}
### Write the persona
The AI Prospect agent editor
1. **Name in the meeting**: The participant name everyone in the meeting sees. A new agent joins as "AI Prospect" until you change it.
2. **Persona**: Who it plays: their role and company, what they need, what they push back on, and how long they have. Your Spara account is the seller, and whoever sends the agent is the rep. Up to 4,000 characters.
3. **Voice**: Click to pick from the voice catalog. A new agent starts on a default voice, shown by its ID until you pick another.
4. **Video Avatar**: Optional, as on Samantha's agent. Without one, its camera tile shows an "AP" badge labeled "AI Prospect".
{% endstep %}
{% step %}
### Save and publish
**Save draft**, **Publish** and **Version history** work as they do for Samantha. Spara won't save, publish or send an AI Prospect agent without a persona. A new agent starts with none, so write one before you publish.
{% endstep %}
{% endstepper %}
## Run a practice call
1. Start a meeting and copy its link.
2. On [**Dispatch**](https://app.spara.co/meeting-agents), paste the link and pick an AI Prospect agent. Add Samantha too if you want answer cards while you practice.
3. Click **Send to meeting**, admit the participants, and run the call as the rep.
With both in the call, Samantha answers the AI Prospect's questions on her cards like any prospect's. The AI Prospect can't wake her: only a person saying her wake phrase does that.
When you're done, click **Leave** next to each agent under **Recent meetings**. **Leave meeting** on Samantha's live session screen removes only her; the AI Prospect stays until you remove it.
---
# 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.spara.com/solutions-engineer/practice/ai-prospect.md?ask=&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.
