> ## Documentation Index
> Fetch the complete documentation index at: https://agentheya.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Designer Chat

> The Designer Chat configures your agent through conversation. Describe what you want and it handles the setup.

The AI Helper is a chat assistant built into the agent editor. Instead of filling out forms, you describe what you want in plain language and the AI Helper writes the configuration for you.

## How it works

1. **You describe what you need** — Tell the AI Helper what your agent should do, how it should behave, or what you want to change.
2. **It proposes changes** — The AI Helper shows you exactly what it will configure as a diff card. By default nothing is saved until you approve it.
3. **You approve or refine** — Accept the changes, ask for adjustments, or reject them.

**Auto-apply.** The console's settings menu has a **Do not confirm changes** toggle. Turn it on and the AI Helper applies its edits immediately, skipping the diff-card approval step. Each applied change still appears in the chat log (marked "Auto-applied change to …"), and you can **reverse** any individual change from its entry there — so auto-apply speeds things up without losing the ability to undo.

## What it can do

The AI Helper can configure most parts of your agent:

* Write and refine the agent's purpose and guidelines
* Create rules
* Generate example conversations
* Set up pricing tiers
* Configure hooks and memory fields
* Write policy documents

## What requires the dashboard UI

A few actions need to be done manually in the dashboard:

* Renaming your agent
* Uploading files
* Setting up OAuth connections (connectors)
* Connecting your Stripe account (Stripe Connect) for owner payouts
* Installing plugins
* Generating API keys

***

## Example conversations

### Setting up a new agent from scratch

> **You:** I want a customer support agent for a SaaS product called Vaultly — it's a password manager for small teams. The agent should handle billing questions, account access issues, and feature how-tos. It should be professional but friendly, and always offer to escalate to a human for anything account-security related.
>
> **AI Helper:** Here's a proposed purpose and guidelines for Vaultly Support:
>
> *You are the Vaultly support assistant — a friendly, professional helper for small teams using the Vaultly password manager...*
>
> Proposed rules include: always offer human escalation for account security issues, never ask for master passwords, stay within Vaultly-related topics.
>
> **You:** Good. Add a rule that it should also escalate if a user mentions they've been locked out for more than 24 hours.
>
> **AI Helper:** Added. Updated rule: "If a user mentions being locked out of their account for more than 24 hours, always offer to escalate to the support team immediately rather than continuing to troubleshoot."

***

### Generating example conversations

> **You:** Generate three examples showing how the agent should handle a user who is frustrated about a charge they don't recognise.
>
> **AI Helper:** Here are three examples:
>
> **Example 1 — charge identified as a plan upgrade:**
>
> User: "I was charged $49 last week and I have no idea what it's for."
> Agent: "I'm sorry to hear that — unexpected charges are stressful. Let me help you figure this out. The $49 charge is most likely your monthly Pro plan renewal. You can see a full breakdown of your billing history in Settings → Billing → Invoices. Does that match what you're seeing, or would you like me to walk you through it?"
>
> **Example 2 — charge from a team member:**
>
> User: "There's a charge for an extra seat I didn't authorise."
> Agent: "Got it. It looks like an additional seat was added to your team — that sometimes happens when a team member accepts an invite. I can walk you through how to check who was added in Settings → Team, or if you'd like a refund for an unauthorised seat, I can connect you with our billing team directly. Which would you prefer?"
>
> **You:** These are good. Apply them.

***

### Iterating on behaviour

> **You:** The agent is giving answers that are too long. Make it more concise.
>
> **AI Helper:** I'll add a guideline: "Keep responses short — 2-4 sentences unless the user explicitly asks for more detail. Lead with the answer, then offer to expand." Want me to also add an example showing the desired response length?

***

### Asking for a review

> **You:** Review my current rules and tell me if anything is missing for a healthcare information agent.
>
> **AI Helper:** Looking at your current rules, here are gaps I'd suggest filling:
>
> 1. **No medical diagnoses** — Add: "Never diagnose conditions or interpret specific symptoms as evidence of a particular disease."
> 2. **Emergency referral** — Add: "If a user describes symptoms that sound like a medical emergency (chest pain, difficulty breathing, signs of stroke), immediately direct them to call emergency services."
> 3. **Jurisdiction disclaimer** — Add: "Note that information may not apply to all countries or healthcare systems; recommend the user confirm with a local provider."
>
> Want me to add these?

***

## Tips

* **Be specific.** Instead of "make it friendly," say "greet users by name and use casual language, but stay professional when discussing account issues."
* **Build in stages.** Start with purpose and rules, then add tools, then refine with examples.
* **Ask it to review.** "Review my current rules and suggest what's missing for a legal compliance agent."
* **Use it for examples.** Describe the conversation pattern you want: "Add an example where the user asks for a refund and the agent collects their order number before responding."
* **Iterate freely.** Unless you've turned on **Do not confirm changes**, every change is proposed before it's applied — you can reject anything and ask for a different approach. Auto-applied changes can still be reversed from the chat log.