pranny

Great question. It usually never happens. Our system is based on an adoption of Domino (systematic error/slice discovery), AgentBoard (trajectory/progress evaluation), τ-bench (goal/outcome correctness), MAST (failure taxonomies) and process mining (recurring session paths).

It surfaces issues at trace, session, and systemic levels by tracking user goals/constraints, progress and failure sequences, then grouping recurring high-impact failure modes rather than just clustering similar conversations.

The chances of a wrong fix is very low. However, even if it happens, the devs have the final say at "Merge the PR" stage. If it seems wrong, you can reply in the Github PR and selfship will improve upon it. If it's still going nowhere, the PR can be closed.

A bad fix never lands.

Ah I see it now. Maybe because I am not a claude code user. I use cursor and hermes mostly. Is it useful there also?

What does it do exactly? I am sorry, but I spend a few minutes on your website and I am unable to understand why would I need this, or what value if the energy drink giving to my agents? It seems like a bunch of skills that does _Something_. But what?

Yes, this is a very interesting use case. We are working with a fintech startup and a manufacturing enterprise to deploy this on premise. Would love to understand your use case better and work towards it. Please schedule a call with me at https://calendly.com/pr4n

So far, our early design partners have been running this on (a) AI Based Ads creation and optimisation product [Multi Modal] (b) Customer Support for eCommerce [Text Based] and (c) our own AI trading system.

We’re actively looking for more use cases because we want to understand where the approach breaks down.

We haven't seen a clear domain specific sweet spot yet. What surprises us is that it becomes seems to get better as the complexity / turn count increases.

It adopts very well to multi turn sessions, scheduled runs and even trigger based Agentic systems that don't involve human in the loop.

We don’t yet have enough data to say something like “10–20 turns is optimal,” though. That’s one of the things we’re hoping to learn as we get it into more production systems.

I absolutely loved this concept. I was surprised to some extent that this rubygem name is still available. Appreciated !!

this is exciting. Only Chrome24 supports it, but sooner all browsers will.