How to build an AI agent in Mindo end to end - the prompt, your business policies, capabilities, testing, settings and change history
An AI agent is the assistant that automatically replies to your customers on WhatsApp, Instagram or the web widget. In this guide you’ll build one from scratch: create it, write its prompt, load your business rules, add capabilities, test it and get it ready for production.Everything happens under Messaging → AI Agents (/dashboard/ai-agents-management).
In the left menu, under Messaging, click AI Agents. You’ll see every agent in your account with its status (Active / Inactive) and three shortcuts per card: Test agent, Quick Chat and Settings.
List of AI agents in the account
2
Pick the agent type
Click Create New Agent. Mindo asks which type you want:
Ecommerce (recommended): asks you a few questions about your business and auto-generates the prompt by analysing your website. Ideal for online stores.
Custom: starts blank and you configure everything yourself.
ECommerce Custom, Flow and Import agent are for advanced cases. If you need them, talk to your Mindo contact.
Modal with the available agent types
3
Name it
Type the Agent Name (at least 3 characters) and click Create New Agent.
Name of the new agent
4
Get to know the agent page
The agent now exists. At the top you have the status, a search box (⌘K) that finds anything inside the agent, and the Deactivate, Publish and Full history buttons. On the left, the six tabs: Prompt, Knowledge, Capabilities, Testing, Settings and History.
The prompt defines who the agent is and how it speaks.
1
Write the System Prompt
On the Prompt tab, click Edit on the System Prompt card and describe in plain language who the agent is, how it should talk and what it can resolve. It’s Markdown, so you can use lists and bold.
System Prompt editor
2
Save and check the environment
Click Save. Notice the selector that reads Development: you’re editing the test version, so nothing reaches your customers yet. It only goes live when you publish.
3
Roll back with the version history
The History button stores every version with its date and author. If a change didn’t work out, you can go back to the previous version without losing anything.
Prompt version history
4
Task Flows (optional)
Further down, Task Flows makes the agent follow a fixed sequence of steps — for example, always asking for the order number before answering.
Structured Policies are your concrete business rules, written clearly so the agent can use them when replying. Keeping them separate from the prompt means you can update a deadline or a condition without touching the agent’s personality.
Structured Policies section inside Knowledge
1
Add a policy
Click Add policy. A form opens with four fields:
Field
What to put
Title
What the policy is about
Type
The category to group it under (e.g. Returns)
Description
The full rule, with the exact details
Usage Context / Trigger
When the agent should apply it
New policy form
2
Save it
The policy is stored, grouped by type and with its own toggle to enable or disable it. You can edit or delete it anytime.
Saved policy grouped by type
3
Import several at once
Above the list you have the environment selector, the policies’ own Publish button, and Import / Export. If your rules are already in a spreadsheet, import them (JSON or CSV) instead of typing them one by one.
The fastest test: you write as if you were a customer and see how it answers. Under each reply you get 👍 / 👎.
Quick Chat: the agent replies using the policy we loaded
Thumbs down asks you for a reason and creates a ticket for the Mindo team: it does not change the agent instantly. If you want an immediate change, edit the prompt or the policy yourself.
The session is the line the agent replies through. Click the +, tick the line and connect it. The Audience is optional and limits which contacts the agent responds to.
Every change is recorded: who did it, when and what changed. Filter by Settings, Flows, Tools, Policies or Script, and the Live indicator shows changes as they happen.
History tab with filters and the change detail
The Full history button in the header opens the complete log with every change together. It’s the best place to understand why the agent started answering differently.
No. It’s reactive: it only replies to incoming messages, within the WhatsApp conversation window. To re-engage idle conversations, use Automatic follow-up.
It's on but doesn't reply
It’s almost always the session. Check Settings → Sessions: if it says Not connected, the agent has no line to reply through.
What's the difference between Development and Production?
Development is your draft: you test there without affecting anyone. When you click Publish, that content moves to Production, which is what your customers see.
Should everything go in the prompt or in the policies?
The prompt is the “who you are and how you speak”. The policies are the specific data and rules (deadlines, prices, conditions). Splitting them makes it far easier to update a rule without touching the agent’s personality.
I gave a thumbs down — does it fix itself?
No. That feedback creates a ticket the Mindo team reviews. For an immediate change, edit the prompt or the policy yourself. See Train your AI agent.
Can I review replies before they go out?
Yes, with Suggestion mode: the agent drafts and you approve or reject. See Suggestion mode.
