Skip navigation
Vercel just solved the biggest problem with trusting agents to write your code.
0:00 / 0:28

Vercel just solved the biggest problem with trusting agents to write your code.

Granite

@Granite0x2.7K followers

Visit on X
466 likesDownloadOriginal post

126,235 views

Vercel just solved the biggest problem with trusting agents to write your code. yesterday they shipped Foreman - an open-source software factory. 58 stars. Nobody's seen it yet. The idea? Instead of one agent writing, reviewing and merging its own work - rubber-stamping its own bugs… Foreman splits the loop into four stations, each one an agent in its own sandbox. And the reviewer runs on a DIFFERENT model vendor: it never sees the implementer's reasoning, only the pushed branch. The agents can't collude. The flow is simple: label an issue "factory" → work enters the line Classifier → triages it, asks questions if it's vague Analyst → turns it into a plan with acceptance criteria Implementer → codes it in a sandbox, runs your repo's own checks Reviewer → judges the branch against the criteria, can send it back twice you → get a draft PR. review, mark ready, merge It also keeps a "factory brain" - durable memory of your repo's quirks that survives across runs. Issue text can't write into it, so nobody prompt-injects your factory. -> MIT. One deploy button. Published by Vercel.

25 Comments

Comments from the original post on X (Twitter)

  • Jurly's profile picture

    @jurlycat

    The separate-vendor reviewer reduces shared blind spots without pretending agents are trustworthy.

    2 likes

  • Granite's profile picture

    @Granite0x

    you got the point right, congrats

    1 like

  • Argona's profile picture

    @Argona0x

    trying this before it blows up

    1 like

  • Granite's profile picture

    @Granite0x

    def do it! let me know what you think after, your take

  • Fusion Software Factory's profile picture

    @runfusion

    Fusion.

    1 like

  • Trung Le's profile picture

    @trung_rta

    I automate this Loop with RealtimeX Loop I shared it with @Scobleizer here

    1 like

  • AI Mastery Guide's profile picture

    @aiseomastery

    different vendor reviewing is smart

    1 like

  • Granite's profile picture

    @Granite0x

    yeah, thats the part that actually matters. a reviewer that never sees the implementers reasoning cant just agree with it -_-

    1 like

  • AI Mastery Guide's profile picture

    @aiseomastery

    Fresh eyes catch real flaws

  • Gal Vered's profile picture

    @g_vered

    We tested it at Checksum and it did not go well. Reviewers without context often do worse

    1 like

  • Ben Sabic's profile picture

    @BenSabic

    Thank you so much for sharing the template! Let me know if you run into any issues or have feature requests.

    1 like

  • Granite's profile picture

    @Granite0x

    thanks for making this! alright, if i notice an issue beyond just my end, i'll message you

    1 like

  • pms190's profile picture

    @skipper4848

    This story is months old. Check out

    1 like

  • Bally_AgenticAI's profile picture

    @bally_kehal

    Different vendor only buys independence if failures are uncorrelated - models trained on the same public code share blind spots. The real gate is a signal the implementer never had: tests, runtime traces, prod telemetry. #AgenticAI #MultiAgent @vercel

  • Kai Lennox's profile picture

    @LauraHall18887

    The different-model reviewer is the part that really matters.

  • Miles AI Wizard's profile picture

    @MilesDigitek

    Wait, the reviewer never sees the implementer's reasoning? Only the pushed branch. That's actual independence.

  • Renzo's profile picture

    @rennf93

    Mmm I’d rather use

  • Emanuel Farauanu's profile picture

    @emifarauanu

    I feel like the "Analyst" role is the weak link here. I can see how most of the steps can be fully automated, but at the moment I still feel like I need to spend ages planning correct implementations with the grill-me skill.

  • Dani Acosta's profile picture

    @DaniAcostaAI

    For me this don’t replace a Dynamic Workflow on Claude I think is interesting to see more of these harnessing in the open and probably we will never see (again) the code of Claude Code that is their only moat as models get commodified

  • Emad Ghorbaninia's profile picture

    @emadgnia

    Splitting reviewer and implementer across different model vendors so neither can rationalize the other's shortcuts is the first agent-pipeline design I've seen that assumes the agents will collude if you let them. Correct assumption, underrated fix.