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

# Improve flow prompts with AI

> Use prompt improvement and transition suggestions, then review the changed behavior.

AI assistance can improve a Conversation node's prompt and suggest outgoing conditions. Start with a specific task and review the proposed wording before publishing.

## Improve a prompt

1. Open a Conversation node in **Prompt** mode.
2. Write the task, the information to collect, and the action that marks completion.
3. Click **Improve prompt with AI**.
4. Read the replacement text. Remove invented business hours, prices, policies, promises, or actions your integrations cannot perform.
5. Test the node with a normal answer, an ambiguous answer, and an unrelated request.

For a booking enquiry, an appropriate instruction is “Collect the preferred date, then check availability.” A prompt alone should not invent available slots or claim an appointment has been booked.

## Suggest paths

Use the transition suggestion control to generate candidate conditions from the current prompt. Add only conditions that describe distinct outcomes, then connect each added path to its destination. A suggested condition without a connected destination does not create a complete journey.

## Revert a prompt change

After a successful improvement, **Revert to previous prompt** restores the prompt text held immediately before that improvement in the current editor session. It does not undo every flow edit, remove created external records, or replace a published version automatically.

For larger changes, keep a record of the original behavior and review version history before relying on a rollback. Publish only the version you have tested.

## When generation fails

Confirm model access and retry after reviewing the error state. Keep your existing prompt available. A returned prompt is an editing suggestion, not evidence that your business rule or integration works.

Continue with [conversation nodes](/v3/guides/flows/conversation-node) and [testing](/v3/guides/flows/test).

## AI editing controls

| Control | What changes and what to review |
| - | - |
| Improve prompt with AI | Replaces the selected Conversation node’s prompt text. Review business facts, tool assumptions, and conditions before publishing. |
| Revert to previous prompt | Restores the immediately preceding prompt held in the current editor session. |
| Suggest transitions | Produces candidate outgoing conditions. Add the useful conditions, dismiss others, and connect destinations yourself. |
| Generate with AI on a greeting, end message, or tool filler | Edits the selected field. Generation does not add runtime support to an otherwise unsupported field; see the [Conversation](/v3/guides/flows/conversation-node) and [End Convo](/v3/guides/flows/execution#end-convo-settings) references. |
| Flow AI drawer | Describe a complete flow or a change to the current flow. It can apply edits to the working flow and autosave them, rather than only returning suggested text. |
| Clarification options / Send answers | Supply business details requested by the flow assistant. Review its plan and the resulting nodes. |
| Follow-up message | A message sent while the assistant is working joins a queue. Remove an unwanted queued message before it runs. |
| Stop | Halts the active request and clears queued follow-ups. Changes already applied remain. |
| Version history | Recover a previous flow when a broader editing pass needs to be undone; test the restored draft before publishing. |

A flow assistant’s “verified” or “goal met” message describes its editing checks. It does not prove that an actual caller reached the correct destination or that an external booking succeeded. Run your own [test scenarios](/v3/guides/flows/test), then test the published channel.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.