Live view of sprint system as I work tonight: http://37.27.135.206

Thank you. Moo looks really cool.

I did some prototype games, one thing that worked really well for me was having a deterministic replay system where the agents could drive the gamestate via recorded inputs. Kept me from having to do any playtesting or debugging in the main agentic loop.

You'll like this too then

https://github.com/mas-bandwidth/fixed3d -- port of box3d to fixed point :)

https://github.com/mas-bandwidth/fixed -- fixed point math library

Cool! I’d forgotten until now, but I had that exact idea back in the stone age, 10 or 15 years ago, and started working on it but got bogged down. It was clearly feasible but a huge amount of work, too much to justify the cost. So it’s a perfect job for coding agents now. Nice one!

I do you think now need to watch out for the opposite problem. These things become so easy to build that the temptation is just to go ahead and build. But unless you really do need them, all that new code just goes to waste. The cost to produce has become very low, but sometimes the value can end up being negative.

This is so true. At the end of the day you just have to have good taste to know what is worth creating.

You are right!

Big fan of RDF, your sexpr notes are hilarious https://github.com/mas-bandwidth/fixed/blob/main/docs/roadma...

What tooling do you have around this?

I have some stuff inside nova-sprint that uses lisp sexpr to store issues, roadmaps and various things as primary structures. Basically, anything that is free-form structured tree data it's a great fit.

And then the AIs can easily write tooling in lisp to manipulate these structures, and you can talk to them from some golang program in a verb like way, sort of like a redis client.

I was planning on doing this to effectively replace issues/PRs in git, and have my entire future work set that I import into sprints stored inside this lisp sexpr.

It's implemented in nova-sprint as a tracer bullet (search for "roadmap" scripts in lisp...), but I definitely see this as something I want to keep pushing harder on.

It's a really effective thing, storing all your work in a data structure, and then being able to manipulate that data structure. beats having to hammer the GitHub API when you ask questions like "OK so what else can we bring into the sprint now?"

=)

I totally agree, I have been moving to XML and custom formats inside of markdown. I only use github as a dumb datastore, keeping all issues, todos, etc inside the repo itself (where it belongs). Github should have made issues a branch of the repo.

Here is the roadmap tool that uses lisp sexp: https://github.com/mas-bandwidth/nova-roadmap

I find it really useful to track future work, and then bring it in the current session or sprint. It also regenerates nice roadmap tables in markdown that people can read like these ones:

https://github.com/mas-bandwidth/schema/blob/main/ROADMAP.md

Interesting. Are you also targeting WebTransport for both reliable and unreliable transport?

Yes! Once again, some drudgery that I'd rather not do in the past is pretty easy to implement with AI coding :)

Thanks for sharing. Really interesting.

At what point do you think you tip over from getting away with a handful of agents working on different things in one repo, to needing a comms/coordination system for your tasks?

I think there must be a burden to run this and I'm guessing it only pays off when you get to some kind of scale. What is that scale? Other human team members? Sheer workload?

Great question. It's really the number of different things you are working on at the same time.

Past a certain number of things, you can have a conversation with Claude in one session but even in Fable 5.1 or Opus 5.5 it's going to forget some and they just scroll out of context and get compacted away. Once enough things are in flight they start getting forgotten, or half-started, then the next thing is in flight and so on. When I start noticing this, I know it's time to switch over to the sprint system.

The other thing is simply I want to go really wide and work on something and it's too slow when working with traditional child agents per-model. The LLMs generally won't "work to width" naturally (for whatever reason) and the sprint system is really good at pushing and ensuring that each model involved in the sprint not only works, but works at whatever particular width they are assigned (16, 32, 64 cards...) and stays working that way.

If you work without a sprint system, you'll find yourself continually reminding the AIs manually "hey, can you please work to width?", "hey, you have 10 cards ready can you please work on them now?". These things are "squishy" when worked on in LLM space, they'll kinda do it, then a few hours later forget, and by morning they're puttering along at a few cards each.

But by putting everything into mechanical structure (sprint system that drives all the LLMs via push notifications), they will more reliably remember to work at width, they will not forget anything they were assigned to work on (this is stored in redis cards, not in their memory that compacts), and the whole system can work much wider and you get done a lot faster!

Thanks. What do you mean by faster here? Wall clock time?

I can't.see myself specifying 60 bits of work to work on in parallel. So I guess you're doing some kind of task decomposition.

But I'm not convinced that this is that much more efficient, given the complexity of the coordination overhead.

E.g. in my mental model, 3 big tasks takes about the same amount of time as 60 small tasks after planning and coordination.

What's your experience?

Faster = working in || to reduce wall clock time.

I appreciate the discussion. Thanks.