Refused at commit.
This change removes tests that cover a live path. Restore them, or record in the plan why they no longer apply.
The trust layer for AI coding agents · Invite only
Hardrails™ is the trust layer for AI coding agents. Every change is challenged, proven and bound to its evidence before it merges. That is what lets you hand them the whole lifecycle.
The tension
The failures aren't loud. They look like progress.
Tests deleted. Suite green. Bug shipped.
Too big to review. Approved anyway.
One forgotten clause. Another customer's data.
Advice the agent may ignore.
The fix
Hardrails™ assumes the agent is wrong until the evidence says otherwise.
01
Rules live in code. If a check can't run, nothing ships.
02
Reviewers hunt for the flaw. Authors never approve themselves. A deadlock goes to a fresh arbiter with no prior vote.
03
Approval covers exactly what was reviewed. Change one byte and it's void. No change can rewrite its own grader.
BUILT FOR AGENTS
Every SDLC you've used assumes the author is a person who can be trusted to follow it. Agents can't be. So we rebuilt it.
Human SDLCs assume
The author follows the process.
Hardrails™ assumes
No agent approves its own work. Ever.
A reviewer read it.
Every approval is bound to the exact bytes it saw. Change one byte and it's void.
The judge is neutral.
The judge runs rules the change cannot touch.
One process fits every change.
Gates set the weight of the process by risk.
Humans gate each step.
You hold the constitution. Agents run everything inside it.
How it holds
Every edit, every commit, every CI run, and the running product. Each agent command runs sealed, with no credentials, no network and no way out of its project.
From Hardrails™' own development
This change removes tests that cover a live path. Restore them, or record in the plan why they no longer apply.
This query reads tenant data without a tenant scope. Open it inside a tenant context.
The submitted change differs from the reviewed change. Request a fresh review.
Proof
Our own agents plan, build and review this product under the same gates.
From Hardrails™' own development
A nested repository can rewrite its own metadata and escape the sandbox.
Fix submitted.
A symlinked file is invisible to the cross-check.
Fix submitted.
Both holes closed. Evidence attached.
From Hardrails™' own development
The unlock
You approve the constitution: the rules, the credentials, production, and anything that loosens a gate. Everything else merges itself when the gates and review pass.
Floors only rise. Every incident becomes a new gate.
Unattended work
Each night's run ends in a morning digest. Your phone rings only for decisions that are yours.
Work continues unattended and ends in a morning digest.
The planner re-ranks by impact the moment you pivot.
Reviewers from different AI vendors challenge each change.
Real usage, failures and drop-offs improve the product through the same gates.
The Hardrails™ runtime hosts what it builds.
Two ways in
Platform
Bring your agents. Hardrails™ makes their work safe to ship.
Studio
We take it from idea to a running product, built under Hardrails™.
Investors: request a briefing through the form.
Apply
We onboard a small number of teams at a time. Tell us what you're building.
A human reads every application. No sales sequence. No spam.