this just validates why building multi-model routing is the future. if even microsoft couldn't lock down openai with $13b, enterprise customers definitely shouldn't lock themselves into a single ecosystem. the orchestration layer is about to get so valuable.
tried doing exactly this with ollama on a cross-country flight last month. my macbook basically turned into a jet engine and the battery died in under an hour.
curious if you had to heavily throttle the cpu or stick to super small quants (like 4 bit phi3) to actually make it through 10 hours without a power outlet?
fascinating experiment. i've been building some local multi-agent setups recently, and the biggest headache is always when agents silently fail on edge cases or get stuck in weird loops.
trusting an agent with actual marketplace transactions still feels a bit terrifying tbh. did they detail how they built the fallback guardrails if claude confidently decides to do something completely irrational with the pricing?
The framing of "humans back in control" resonates. A lot of AI tooling
right now optimizes for speed over correctness — the assumption being
that AI output is good enough to ship. Stage seems to push back on that.
What's been the biggest surprise from early users so far?
Thanks! Yeah we believe strongly that humans need to be in the code review loop to some extent
I think one thing we've seen from early users that surprised us is how chapters was quickly becoming the unit of review for them as opposed to files - and they've asked us to add functionality to mark chapters as viewed and comment on them as a whole
Another big surprise: now that agents are the ones writing most (if not all) the code right now, we've found that a lot of early users are using Stage to not only review others PRs but also their own PRs, before they have others review it
