Never do this. The most efficient way of working with an agent is to get it to succeed at it's task with 0 further follow up prompts. We have gotten their with our own orchestrator now, and the failure rate is very low. We have worked on and in this 100% since July 2025. I still review at the end, and if all good, that is it. I also have no need to check the agents regularly, and hide them in the background and they only expose when done. That means this compaction would be redundant work being done, and something I also turned off instantly as soon as I saw Claude implement it.

Looks really awesome!!! Nice work! Couple of those SFX tilt me these days though, the ones AI uses. Def get some SFX packs your AI can use, makes it alot better :D (all were fine, just those whiney kinda ones, I hear one near the end for example).

Double Edge sword! Can do alot in parallel, but start alot of work but not finish! That is the thing you must counter with ADHD!

We have been building games 100% with AI coding for over 2 years, they are very out of date in their knowledge. Only getting more insane by the week! As usual, obvious call at this point, but many still heads in the sand.

Yeah that is awesome :)!!! Did you talk about your techniques? We got our own agent workspace setup which can kick off prompts and land them very easily, and also self healing infrastructure etc. How many PRs does the commits represent? What about the 'size' of them? Again ours also can be minor small changes, to insane huge features...and the prompts might be 1 sentence to a 40 min voice to text xD I am trying to be careful not to worry about metrics, although they are important, if they become a 'measure' you can easily introduce bad incentives u know?

Last 7 days for me, over 1000 PRs Our Agent Workspace really makes it easier and easier each day!

Nice :D! I shipped 1000 in the last 7 days 🫡

The $200 is still on the old 20x for now, but will lose it soon. Unfortunately will likely need to upgrade end of month ~ when it happens. Ultra fast is likely over-rated except for very specific workflows, but 99% TPS is not the bottleneck.

Amazing :D What is your policy on data/code/assets, do you use/train on the code if the users bring their own/use their own agents?

Thanks, I didn't know that :)!

It's purely a website, vibe coded effectively. You prompt in the UI, and it builds it 'live'. It's pretty good tbh, and they have some powerful stuff they are building. Although I prefer my own stuff still, far more flexible...but it's prob the easiest way to test out game dev + AI I think. If they get alot of users, it could also help, but other platforms still better like steam/roblox for now.

The AI TPS is not the bottleneck, when you can run multiple in parallel, humans still are the bottleneck. The $500 plan also is really not good, the Ultra fast will burn your credits in a few decently sized convos, only for PURE emergencies OR really important things where near instant feedback is needed.

Haha, good one xD We have done it over and over, as long as 'vibe' means not writing the code, not a single line.

Are you really typing? No voice to text??

Slow mode/Batch mode.

The Bottleneck is no longer TPS for myself, and I imagine various power users. Please offer a /Slow mode for those that are happy to go slower (as long as no cache issues that result in more costs), so that we can get more usage :D! Even happy to delay the 'start' of the agent also, a bit like 'batch' mode, although yeah might be a bit more thought needed.

Felt like only a matter of time till google and facebook would do something good :)

I will never go back , my voice = work

Yeah pace has been really nice with opus 5.5 and sol 6 today! Was feeling the pressure last few weeks, this hopefully is the unlock, at least for a month or so till they hit their limits again xD

Really Awesome :D!