You're right when the agent starts with a plan and no file list and the files only exist after edit, but the way I designed Foremerge to work, it works anyway. The initial intent does not have to be complete, it just has to be right about any destructive parts. That is why Foremerge works by declaring intent as prose, not as a file list or methods. The agents them selves determine if something conflicts based on the signals Foremerge returns. It only asserts a HIGH warning on declared scope and only a HIGH signal blocks acceptance (to avoid false possitives based on prose alone). The declaration can change at any point and the auto installed skills into the agents encourage such (the initial intent is released by the agent and the new intent is committed)
You might be surprised, it works exceptionally well. If you decide to give it a shot and run into any issue feel free to reach out to me with any feedback.
... and Jev is a sore point for me right now lol we have been training our own decision intelligence model, Corgen, for the last year and a half. We're already using it in GPTree but havn't released it to the public yet. Im actually in the process of running it against JevBench right now to see how it stacks up.
I'm curious to know what's everyone custom solution to this problem ? Before AI and with AI.
It was already a problem for me before agentic AI coding : multiple developers can work on overlapping code and you always need someone to merge everything properly. Even if the overlap is very small it does add a burden to development. Not an issue anymore in 95% of cases if that person uses AI to solve conflicts, but now that "others developers" are swarm of AI agents, this problem isn't trivial to solve.
I think before AI was writing most of the code and with small teams the solution was probably just ownership and talking (and meetings about meetings). Things moved at a pace where it was more possible to have someone oversee this, though I agree on larger teams it has always been a problem. I think Foremerge solves that too even without agents but the manual overhead outweighs more of the cost that it does with agents.
Even if you can use AI to resolve the conflicts at PR time, you need the right context and you've already burned through tokens building and now even more fixing. Scale that across 10's or 100's of agents and you have a mess of each one running in its own direction.
The custom solution for us became one worktree per task, and before an agent writes a line of code they lease/commit their intent and scope into an immutable log and verify drift as the acceptance check...thats now Foremerge
We’ve been taking a different path to this author, albeit to solve a similar problem. Rather than thinking agents diminish the value of code ownership, we think it stays level or potentially increases. To that end, teams are responsible for managing the agent model, harness, instructions, local skills or other config for their areas. When work needs to be done across areas we allow it, but via an orchestration layer where agents operate via adversarial negotiation, with escalations and explanations to engineers when decisions are hard to make.
We find giving the agents independent remits makes them significantly better at challenging problematic requirements, because they aren’t all automatically aligned on the same goals.
The agents from each area then having queues and messaging subsystems to coordinate their work when there are multiple streams happening, although concurrency is less of an issue than we expected. Generally will detect and flag competing requirements, which has saved us from some subtle issues. We don’t always require code owners to review every PR in their area, but they do at least always have a log of what work was done and why, which is separate from the noise of the parent work.
This does all work out a bit slower than just letting each agent get on with its job, but it’s working pretty well for us.
France, 1658 <-> World, 2026. AI can also do the reverse : for example very few in the world know that the term midwit was originally coined in french by Blaise Pascal (« demi habiles ») centuries ago.
Yes, that bell curve meme, he wrote about it. It’s not explained anywhere because of the language and culture separation between
french and english. But if you ask enough questions to AI, the AI will eventually find about Blaise Pascal and tell you about this unknown link. It’s magic.
There used to be a meme on Slashdot: "In Soviet Russia, X Ys you!" It came from a joke by Russo-American comedian Yakov Smirnoff: "What a country! In LA, everybody is looking for a party; in Russia, the Party comes looking for you!" But I long wondered if Smirnoff was influenced by his countryman Leon Trotsky who observed: "You may not be interested in the Dialectic, but the Dialectic is interested in you."
I dont think the helpdesk / webmail space is saturated, I was looking into this and most of them don’t have the features I need such as automatic LLM assistance, automated translation, sharing tickets among multiple accounts etc.
The only listed feature here I've not got is the automated translation. It will currently draft responses in the incoming language right now – though that's not terribly useful if you don't speak that language.
I'd been considering mostly an English speaking audience at launch. To be more accurate, I was generally thinking about users physically local to me initially, so I could meet with them for customer onboarding and feedback etc.
Your post has got me thinking on an approach to making translation work in an open and honest way, so that is something I will experiment with and hopefully get in quite quickly.
If you'd be interested in helping me test that, please feel free to reach out to hello@stayupfront.com
reply