Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Help Center
✏️

Editing messages and branching

Found this helpful? Share it:

Made a typo, or want to try a different approach? You can edit any message you sent and regenerate any reply. Each change creates a branch, so nothing is ever overwritten and you keep a full history ✏️

Two kinds of branches

A conversation branches in two different places, and knowing which is which clears up most of the confusion:

  • Editing your own message creates a new version of that message. Its versions show as arrow controls on your message.

  • Regenerating a reply creates another answer to the same message. Its versions show as tabs above the assistant's reply.

Edit a message

  1. Hover over one of your messages to reveal its actions.

  2. Click the edit icon. The message hoists back into the composer with an Editing message pill so you know you are revising, not sending fresh.

  3. Change the text and press Enterto resubmit.

The assistant answers your edited message, and the new version appears as a sibling of your original. Your first message and its reply stay intact on the other branch.

Regenerate or reprompt a reply

If a reply is not quite right, hover over it and click regenerate to get a fresh answer to the same message. The assistant tries again with the same context.

You can also reprompt with a different model. Either way the new answer arrives as another model tab above the reply, so you can compare versions side by side. See Comparing models side-by-side.

Regenerating is the quickest way to get a second take without touching your original message.

Navigate branches

Where you edited a message, arrow controls ( ◀ ▶) appear on that message with a counter such as 2 of 3. Click the arrows to move between your versions. Replies you regenerated use the model tabs above them instead.

Branch controls only appear where you actually created alternatives. Most messages in a conversation have none.

How branching works

Think of a conversation as a tree, not a straight line. The first message is the trunk, and every edit or regeneration grows a new branch from that point. Each branch is a complete path you can explore, back out of, and revisit without losing any other work.

The branch you are viewing is the active one, and switching branches updates the whole conversation below that point. Exporting a chat captures only the branch you are currently on, so switch to the path you want before you export. See Managing conversations.

Related articles

🔀

Comparing models side-by-side

Get multiple AI responses to the same message and compare them in tabs.

💬

Managing conversations

Pin, rename, archive, export, share, and delete your conversations.

Up next

Managing conversations

Pin, rename, archive, export, share, and delete your conversations.

Was this helpful?