Edit Claude's work inline instead of re-prompting
Stop rewriting whole prompts when one paragraph is wrong. Select text inside an artifact, describe the change, and Claude edits just that piece.
What this looks like
One step on screen at a time. Read it, do it, tap Next.
Edit Claude's work inline instead of re-prompting
Step 1 of 7
Understand the problem this solves
The old loop: Claude writes 800 words, paragraph three is wrong, you reply "fix paragraph three", and get back 800 *different* words — the good parts rewritten along with the bad.
Checkpoint
You can explain why 'fix paragraph three' in chat is riskier than selecting paragraph three.
Before you begin
Tick these off as you sort them. Stopping halfway to create an account is how a fifteen-minute build becomes an hour.
0 of 5 ready
Ticks are saved on this device, so you can come back to them.
- Account
Any plan works — inline editing of artifacts isn't gated. You just need a chat where Claude has created a document or app artifact.
- Have ready
Ask Claude to 'write a one-page project proposal as an artifact' if you don't have one handy. Any document artifact works for learning this.
The basics — ticked once, remembered everywhere
- Account
Either the hosted version or a self-hosted install. Everything here works the same on both — the only visible difference is the shape of your webhook URLs.
Create a workspace - Know-how
Adding a node, connecting two of them, and pressing Execute. If any of that is new, the free primer covers it in about ten minutes.
- Credential
You will paste at least one secret during setup. A password manager beats a notes app, and it stops you pasting a live key into a chat window by accident.
The shape of the setup
The Claude features you will touch, left to right, in the order you use them.
What you will build
Jump straight to any step, or print the list and tick it off beside your Claude tab.
If something goes wrong
Everything ready?
Start walkthrough