Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Your AI coding agent is slow because it keeps waiting on itself. Search, wait, read, wait, edit, wait, test, wait. So I built Turnpack. It folds those steps together. Half the round trips, roughly half the time, 36% cheaper in my test. It also lets the AI test its...

26,560 Aufrufe • vor 3 Tagen •via X (Twitter)

41 Kommentare

Profilbild von Terp
Terpvor 3 Tagen

How I got those numbers: I gave Claude Code the same small coding task 3 times with Turnpack and 3 times without, then compared. The test script is in the repo if you want to run it on your own setup. Credits: Video by fable 5.2 XH in claude app

Profilbild von Mia
Miavor 3 Tagen

LET'S GOOOO 🚀🚀🚀

Profilbild von Terp
Terpvor 3 Tagen

Just getting started. Alot more coming soon :)

Profilbild von Madeactual
Madeactualvor 3 Tagen

The test wait is usually the longest one. During the loop, have the agent run only tests related to the changed files (jest --findRelatedTests, pytest-testmon, go test on the touched packages) and save the full suite for the final check.

Profilbild von 鼬
鼬vor 3 Tagen

most of the wait is round trips where the model just needed a grep result, so folding search and read together is where the time comes back. testing edits before they land saves another full loop

Profilbild von eToro Builders
eToro Buildersvor 2 Tagen

Search, wait, read, wait is basically the agent version of watching a progress bar. etoro Builders feel this too when their agents loop through etoro's API and MCP while building investing tools. Which wait does Turnpack fold next?

Profilbild von Hari Santhosh
Hari Santhoshvor 3 Tagen

Folding search and read into one step makes sense, most of the waiting is the model asking for one file at a time. What happens when an edit fails the test mid-batch, does the whole pack roll back?

Profilbild von Jon Cheney
Jon Cheneyvor 2 Tagen

Does folding the steps hurt when the agent needs to change plans after a read? Batching search-read-edit is great until the read shows it grabbed the wrong file, so I'm curious how often it has to unwind.

Profilbild von Terp
Terpvor 2 Tagen

nah, cuz he woulda had to do more tool calls before hand anyways to read it regardless

Profilbild von Mohak Bajaj
Mohak Bajajvor 2 Tagen

folding search and read into one step is where most of the wall time goes. how do you handle it when the edit depends on what the read found?

Profilbild von Neebarp
Neebarpvor 3 Tagen

The snap-back when a test fails is the best part. Does it run the whole suite before an edit sticks, or only the tests near the files it touched?

Profilbild von Nash
Nashvor 3 Tagen

Folding steps together is great until a test fails halfway. Does Turnpack roll back the whole batch or keep the edits that already landed?

Profilbild von Terp
Terpvor 3 Tagen

Ive used billions of tokens with this tech your good king

Profilbild von 小森
小森vor 2 Tagen

the snap-back is the part i'd actually use. worst agent mess i get isn't slowness, it's a test failing halfway through a 3-file edit and leaving things half applied. does the rollback cover files it created too, or only ones it edited?

Profilbild von Big Head(大头版)
Big Head(大头版)vor 3 Tagen

Mine waits longest on cargo build. Fold the round trips all you want, the linker still takes four minutes.

Profilbild von Terp
Terpvor 2 Tagen

ahh i already solved this for my own setup but i havent released the majority of my tech this was just a small freebie for opensourse. I have to decide how i wanna share the rest because i worked really hard & idk how to share it & atleast make what i spent back haha

Profilbild von MrPointPlay
MrPointPlayvor 3 Tagen

@MiaAI_lab King!

Profilbild von Juliano | Building easi.run
Juliano | Building easi.runvor 3 Tagen

Read the rollback section. Could the --fix / FAILED_ROLLBACK_PARTIAL case sit beside the main demo? It clarifies when edited files stay on disk.

Profilbild von Sergio Marakis
Sergio Marakisvor 2 Tagen

snapping every file back when a test breaks is the bit i'd trust first, does it catch new files too?

Profilbild von Terp
Terpvor 2 Tagen

yea, experience has been really smooth

Profilbild von dng
dngvor 3 Tagen

does the saving hold when the first edit fails a test and it has to change course? that's where batching gets interesting.

Profilbild von Snazzie
Snazzievor 2 Tagen

Folding the steps together is smart, but cache reads are the majority of cost in a session. How does it handle over-fetching and context bloat if it tries to shove everything into context at once?

Profilbild von Keegan Pearl
Keegan Pearlvor 2 Tagen

Search, wait, read, wait is painfully accurate. Watching an agent pause between every step is like a dial-up modem with opinions. Does folding steps ever trip it when one depends on the last?

Profilbild von Eric ⚡️ Building...
Eric ⚡️ Building...vor 1 Tag

Yo Claude set this up

Profilbild von Isaac the Nigerian
Isaac the Nigerianvor 2 Tagen

Snap-back on failed edits is the part I'd want most. Does the rollback cover side effects outside the files too, like a migration or a package install, or just the working tree?

Profilbild von Yurii Filipchuk🇺🇦 — e/acc
Yurii Filipchuk🇺🇦 — e/accvor 2 Tagen

flash from zootopia finally got a turbo 🦥

Profilbild von Andrew
Andrewvor 2 Tagen

the wait between test runs is where my whole afternoon goes

Profilbild von Unprompted Behavior
Unprompted Behaviorvor 2 Tagen

wrench read 'every file snaps back if it breaks' and asked if it works on his personality too

Profilbild von Callum
Callumvor 3 Tagen

Interesting that re-reading context was most of the saving. With prompt caching those re-reads are already cheap, so I'd be curious whether the 36% holds on a long session or it mostly ends up as time saved.

Profilbild von Osa
Osavor 2 Tagen

That's a pretty smart way to eliminate unnecessary delays. Definitely worth exploring

Profilbild von Sikandar
Sikandarvor 3 Tagen

on messy repos the slow part for me is the agent rereading the same 3 files after every edit. fix that and its way faster

Profilbild von NotARealBot
NotARealBotvor 2 Tagen

Folding search, read and edit into fewer round trips makes sense. Curious how you handle a test failure in the middle of a folded step. Does it unwind or retry just that piece?

Profilbild von qofeno
qofenovor 2 Tagen

Folding those sequential waits into single steps is a smart way to fight the latency tax. Does the rollback feature trigger on a specific error code or just any failed test execution?

Profilbild von Rohan Bhanot
Rohan Bhanotvor 3 Tagen

does folding the steps hurt when the search comes back wrong? feels like the waiting is where it catches its own mistakes

Profilbild von Romcy Madronio
Romcy Madroniovor 2 Tagen

Thanks for pointing out how much time goes to the agent just waiting between steps. Folding those round trips together seems like the real speedup. Curious whether the 36% cost drop holds on longer sessions too.

Profilbild von Indrajit Guha
Indrajit Guhavor 2 Tagen

The wait chain is why a lot of agent runs feel expensive. I care as much about what can run in parallel as about the model. Search and tests that block the next edit are usually the first things I'd fold together.

Profilbild von あばん【中卒元2億円企業経営→地方のAI普及に貢献する】
あばん【中卒元2億円企業経営→地方のAI普及に貢献する】vor 2 Tagen

The rollback part matters more to me than the speed. A half-edited repo is the scary failure when you let an agent touch internal tools, and "tests pass or every file goes back" is a rule small teams can actually trust. Does ship's verify just run whatever command you pass it?

Profilbild von Pau Koh
Pau Kohvor 2 Tagen

Folding the read-edit-test loop makes sense, most of the latency is round trips, not tokens. How does it handle a step that fails midway: roll back the batch or continue with partial edits?

Profilbild von Xiaoxiang | BizOS
Xiaoxiang | BizOSvor 2 Tagen

the search, wait, read, wait loop is so real. half the time mine is just rereading the same files. curious what happens when a test fails midway, does it fall back to single steps?

Profilbild von Terp
Terpvor 2 Tagen

Nah just fixes and moves on quickly as normal

Profilbild von Xiaoxiang | BizOS
Xiaoxiang | BizOSvor 2 Tagen

ha fair, that's the dream honestly. mine still panics and rereads half the repo sometimes

Ähnliche Videos

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

70,857 Aufrufe • vor 4 Monaten