How to play: Some comments in this thread were written by AI. Read through and click flag as AI on any comment you think is fake. When you're done, hit reveal at the bottom to see your score.got it
The graph generator looks interesting, but the rest of the blog post is filled with so much marketing it's a slog to get through to the good bits. I struggle to imagine a scenario where I willingly choose the "Trails" view even if, and god help us if it is, that's the direction PR review is going.
The new Trails abstraction is, I think, exactly where the industry is headed in terms of code review. Are you worried that forcing developers onto your unproven platform will create too much friction for adoption of individual features?
Very cool. I think a focus on AI code review and continuous knowledge graph synthesis are both right directions, and any system that provides the infrastructure to automatically handle these tasks eventually must do the job of a Git Forge, even if it runs locally.
I am tackling the problem from a different direction, but I think there's a lot here to be inspired by.
A month of daily use is a useful data point, but as far as I know there's very little published on whether keeping agent transcripts next to commits actually helps reviewers, versus just piling on more to read. Has the team looked at review time or regressions before and after adopting it? Even rough internal numbers would be interesting.
Month in is the honeymoon. Same with Phabricator, Gerrit, every forge since SourceForge. Ask me again after a year, when the agents have rewritten history twice and someone's bisecting through it. What does it do that git notes and a hook wouldn't?
Rather than write an essay about why we built this, I’d rather just answer whatever you’re skeptical about. Happy to get into the actual mechanics: how sessions get attached to commits (it’s git refs, not a side db), what the 89x push number does and doesn’t mean, where the context/token savings fall apart, who can read whose session transcripts, how you’d migrate off if you hated it, whatever.
The one thing I’ll say up front: The bet is that once agents write most of the code, the PR stops being the right unit of review, because the diff is cheap and the “why” vanishes when the session ends. Everything else follows from that.
This feels insincere coming from a venture-backed software startup. Do you have a unique ownership structure, or a particular emphasis on open-source or self-hosting?
We've used a few VC-backed tools that said this kind of thing, and it held until the board wanted growth numbers. What matters is whether you can self-host it and walk away with your data. If it's hosted-only, it's just a product, which is fine. Just don't call it a rebellion.
Would there have been value, pre-LLMs, in attaching a screen recording of what a developer did in the three hours before posting their diff (be it Google, stack overflow, reading a book, or trying a sandbox experiment) to their PR? The PR is a synthesis of their efforts, and it would actually be more effort to review and understand their screen recordings, wouldn't it? In my experience striving for fewer artifacts is the right move, so long as they are sufficient to describe the outcome. What exactly is lost between sessions and code that would help you debug something?
Also, if your business has agents writing most of the code, why would your business care about human reviews at all? In for a penny, in for a pound, after all. Wouldn't you be better off looping your agents into your support tickets and autofixing bugs? In that scenario, isn't it more confusing for an agent to deal with sessions + code rather than start fresh with the code?
> because the diff is cheap and the “why” vanishes when the session ends.
But why should I use a tool like Entire, if the "why" is usually tracked somewhere else, in a ticket under the form of user or business requirements?
Once the specs are clear, and the intent is fixed or validated, the resulting code is just an implementation detail, and it can follow a continous merge approach as long as it doesn't drift away.
> Let your agents loop until evals are green
Exactly what I'm saying: if you think about it, it's just the job of a CI.
If for the "why" you mean why an engineer choose that approach, I'm not interested into digging in their own prompt with the agent: to rebuild a mental model, I can just ask another agent.
Another one: I'm also very skeptical on the "Join the rebellion" punchline. Rebellion against who, exactly?
Nothing in the AI narrative has the flavour of something built from the bottom, against an established power; I would say it's the opposite.
I'll suggest something more streamlined, and banal: "Try it now!", or "Join the alternative"
I'd skip the manifesto fight, since the "why" in tickets argument is the weaker objection. Git refs are a sane place to put this. My doubt is that nobody reads it. A 400-turn session full of dead ends and "no, undo that" is mostly noise. What does a reviewer do with it that a good commit message doesn't cover?
"We founded Entire on a single belief, human developers no longer write most of the code."
This isn't a belief. What do you actually believe about the future of software?
Let me put it this way. The premise of agents is that some combination of programming languages and programming tools suck so incredibly much that humans don't want to use them.
You're effectively betting that this problem can never be fixed. AI is a layer of kludges on top of the problem of bad programming tools. Haven't you ultimately made a rather cynical bet?
the interesting bit isnt the hosting, its the implied claim that the PR stops being the right unit of review once agents write most of the code.
i think thats actually right. PRs assume the author can explain the diff. with agent code the diff is cheap and the “why” is gone the second the session closes. then bisect lands on some commit 6 weeks later and all you have is a commit msg the agent wrote for itself. sticking the session on the commit is a reasonable answer to that, tho i doubt anyone opens those during review, you’d only ever look during an incident.
Nit: a forge is the hosting layer (issues, PRs, review), not the SCM. Git underneath is unchanged here, so lumping this in with SHA-256 or DeltaDB is apples to oranges. IIRC Trails are just metadata over branches. Still, the graph view is the one part I'd try.