AI made software cheap to build. Adaptl makes it easier to own.
Know what your product does, challenge each change before it's built, and try it as your customers. Keep your own coding agent.
Your idea
Let guests check out without an account
Product agent
Your Map says invoices need an account. What should a guest get?
- Email a receipt
- Company details
- You decide
Then
- You confirmed the plan
- Your agent built it
- Tried as a new customer: sent back to sign-in. Pinned.
- The agent fixed it
- Added to what your product does today
From idea to merge, in one place.
Talk it through
In your users' words. Adaptl knows your product and asks what's missing.
Confirm the plan
A plain-English plan. Nothing is built until a person says yes.
Your agent builds it
Claude Code, Codex, Aider, or any agent on a pull request.
Try it as your customers
Sign in as made-up customers, or describe it and AI tries it, on your own computer for now.
Pin it, the agent fixes it
Pin what's wrong on the screen. Clients can review by link, without joining your team.
Your team merges
Adaptl never merges by itself.
What makes it easier to own.
Map
What your product does, who it serves and how it's built, with evidence.
Lineage
How it got here and why, in plain English.
What changes for users
What's new, different or gone, before it merges.
Agents
Coding agents write the code. Adaptl's look after the product.
Product Working
Questions each idea before it's built.
Speed and memory Working
Shows if a change slowed your product. On your computer.
Coming
Code review, architecture, errors, cloud, cost
PMs ship. Engineers own the product. Everyone works from the same facts.
PMs who ship
Try changes and pin what's wrong, without reading code.
Engineers who own the product
Start from what it does and why, not a diff.
One change, both views
Product sees the preview. Tech sees what changed and its checks.
Questions
What is Adaptl?
Adaptl makes a product that AI builds easier to own. It shows what your product does and how it evolved, and questions each change before it's built. Once a person confirms the plan, your own coding agent builds it, and you try it in a preview full of realistic, made-up customers. You pin what's wrong, the agent fixes it, and your team merges when it works.
Which AI coding agents work with Adaptl?
Claude Code, Codex CLI and Aider running on your own computer, or any agent you can mention on a GitHub pull request. Adaptl writes the brief and checks the result; the agent writes the code. You keep the tools and AI keys you already use.
Do I have to write a spec first?
No. Describe the change in your users' words. Before it merges, Adaptl lists what it changes for users, each line based on the change itself, and your team corrects anything that's off. Merged changes build an up-to-date description of what your product does, so the spec writes itself as you ship.
Do I need to read code?
No. You describe changes in plain words, try them in the running app and pin feedback on the screen. Engineers can open the pull request and the code whenever they want.
Does Adaptl use my production data?
No. Adaptl reads your code and database structure, never your customers' records. Every person and record in a preview is made up, written through your app's own models so the rules in your code still hold.
Can I start a new app with Adaptl?
Yes. Bring an existing GitHub repository, or start a project from scratch and let your coding agent build the first version. Either way, every later change goes through the same loop: preview, pin, fix, merge.
What does it cost, and where does it run?
Signing up is free. Adaptl runs online at inloop.adaptl.ai, hosted in the EU, or on your own computer. You use your own AI key, so your AI provider bills you directly for the model.
Who merges the change?
Your team. Adaptl prepares a normal pull request on GitHub and never merges by itself.