Front page

Ship real software by talking to it.

Prompts that fill themselves in with your project, guides that take a subject end to end, and fixes for the moment it breaks. Every page dated, checked, and free.

Start your first project Browse the prompts

Today’s clipping · No. 56

Stream the response

Same wait, completely different feel.

stream-response.txt

My model call waits for the whole response before showing anything,
and it feels broken: <paste the endpoint and the client code>

Add streaming end to end:
- Server: stream from the provider and forward to the client without
  buffering the whole thing.
- Client: render tokens as they arrive, scrolling only if the user is
  already at the bottom.
- A stop button that actually aborts the upstream request, so I'm not
  billed for output nobody sees.
- Handle the stream failing halfway: keep what arrived, show a clear
  error, offer retry.
- Handle the user navigating away mid-stream.

Tell me what changes for error handling, since headers are sent before
the model has finished.

The stop button must abort upstream, not just stop rendering. Otherwise you pay for every token of a response the user rejected two seconds in.

A different prompt every day. More from the Building with models desk

The desks

Prompt snippets

227 pages

Prompts you clip, fill in and paste, sorted by the job in front of you.

All prompt snippets

Guides

92 pages

Longer reads that take one subject end to end.

All guides

Playbooks

63 pages

One thing, built start to finish: tools, bots, games.

All playbooks

Fixes

20 pages

Something is broken now. Symptom, cause, fix.

All fixes

Latest from the desks

Models & costWhat a vibe-coded project actually costsWorked examples, from a weekend build to something with users.2 min Models & costWhat a really long prompt costsThe million-token window has no surcharge. It still has a price.2 min Models & costRate limits, and what to do when you hit oneNot a bug, not a bill. A queue.2 min Models & costUsing more than one model in a projectCascades and sub-agents work well. There's one cost you'll miss.2 min Models & costWhen the cheap model is the right modelHaiku and Sonnet do more than people give them credit for.2 min Models & costSubscription or pay as you go?Two ways of paying, with different failure modes.2 min

The one prompt to start every session

Paste this before you ask for any code. It stops the model inventing a stack you didn't ask for.

context-primer.txt

You are helping me build: <one sentence, what the thing does>

Stack I am already using: <languages, frameworks, hosting>
Files that already exist: <paste `ls` output or a short list>
What works right now: <the last thing you got working>
What I want next: <one change, not five>

Rules:
- Change the fewest files possible. Show me full file contents for anything you edit.
- Do not add new dependencies unless you say why and I agree first.
- If my request is ambiguous, ask one question before writing code.
- End with the exact command I run to see it working.

Why it works: most bad AI output comes from missing context, not a weak model. Nine lines of setup beats three rounds of "no, not like that".