Skip to content

Rework the app-building skills from measured agent behaviour - #111

Open
onelxj wants to merge 2 commits into
mainfrom
onelxj.reboot-2
Open

Rework the app-building skills from measured agent behaviour#111
onelxj wants to merge 2 commits into
mainfrom
onelxj.reboot-2

Conversation

@onelxj

@onelxj onelxj commented Jul 28, 2026

Copy link
Copy Markdown
Contributor

I've run the reboot agent on the same prompt a couple of times; the very first run (current main) cost $39 and took 45 min to build. Now we've removed the plan stage and started writing files early which produces still high-quality output (at least on the example I've used). The comparison was done against supabase project ($10 and ~16 min), but supabase didn't end up writing a backend servicer, only sql migration file + web, so arguably we are now on the same stage but with a much bigger skill-set.

With the skill changes I've been able to build the app in ~16 min and ~$12, which is a huge improvement already.

image

@aviator-app

aviator-app Bot commented Jul 28, 2026

Copy link
Copy Markdown

Current Aviator status

Aviator will automatically update this comment as the status of the PR changes.
Comment /aviator refresh to force Aviator to re-examine your PR (or learn about other /aviator commands).

This PR is not ready to merge (currently in state pending): this PR has not been approved.

Pending Status Checks


See the real-time status of this PR on the Aviator webapp.
Use the Aviator Chrome Extension to see the status of your PR within GitHub.

@onelxj
onelxj marked this pull request as draft July 28, 2026 10:47
@onelxj
onelxj force-pushed the onelxj.reboot-2 branch 3 times, most recently from 41cde96 to 264d846 Compare July 28, 2026 12:30
@onelxj
onelxj force-pushed the onelxj.reboot-2 branch from 264d846 to eee33a1 Compare July 28, 2026 21:13
@onelxj onelxj changed the title Onelxj.reboot 2 Rework the app-building skills from measured agent behaviour Jul 28, 2026
@onelxj
onelxj force-pushed the onelxj.reboot-2 branch from eee33a1 to 55333bc Compare July 28, 2026 21:28
Six headless builds of the same app, with every token in the transcript
attributed to what put it in the context. A third of the first run's
cost was the agent reading Reboot's own source — authorizers.py, the
pydantic compiler, idempotency.py, aborted.py, the codegen template —
to answer questions these skills didn't. That is the most expensive way
to learn anything: the request carries the whole context and adds more
source to it for every later turn.
@onelxj
onelxj force-pushed the onelxj.reboot-2 branch from 55333bc to 50224fa Compare July 28, 2026 21:31
@onelxj
onelxj marked this pull request as ready for review July 28, 2026 21:40
@onelxj
onelxj requested a review from benh July 28, 2026 21:40
@onelxj onelxj self-assigned this Jul 28, 2026
[`references/react-client.md`](references/react-client.md). Read it
at the frontend step; don't reconstruct it from memory here.

## Which References to Read, and When

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'll apply the same to chat-app as well.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant