The trust layer for AI coding agents · Invite only

Let the agents ship. Nothing unproven gets through.

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

Agents made code free. Judgment got expensive.

The failures aren't loud. They look like progress.

03:12 AMREGRESSION

The confident regression

Tests deleted. Suite green. Bug shipped.

04:58 PMUNREVIEWED

The 9,000-line diff

Too big to review. Approved anyway.

11:42 AMTENANT LEAK

The missing tenant filter

One forgotten clause. Another customer's data.

09:17 AMRULE LOST

Rules that live in a prompt

Advice the agent may ignore.

The fix

Trust is not a prompt. It's a gate.

Hardrails™ assumes the agent is wrong until the evidence says otherwise.

01

Gates that fail closed

Rules live in code. If a check can't run, nothing ships.

02

Review that tries to break it

Reviewers hunt for the flaw. Authors never approve themselves. A deadlock goes to a fresh arbiter with no prior vote.

03

Proof bound to the change

Approval covers exactly what was reviewed. Change one byte and it's void. No change can rewrite its own grader.

BUILT FOR AGENTS

Built for agents, not adapted for them.

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.

You set the goals and the rules. Hardrails™ makes sure every agent keeps them.

How it holds

Four checkpoints. None of them negotiate.

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.

Edit
Commit
CI
Runtime
 
A change passes from Edit to Commit to CI to Runtime. A refusal branches away and returns the change instead of letting it proceed.

From Hardrails™' own development

Refused at commit.

This change removes tests that cover a live path. Restore them, or record in the plan why they no longer apply.

Refused at edit.

This query reads tenant data without a tenant scope. Open it inside a tenant context.

Approval void.

The submitted change differs from the reviewed change. Request a fresh review.

Proof

Hardrails™ builds Hardrails™.

Our own agents plan, build and review this product under the same gates.

From Hardrails™' own development

  1. Round 1ReviewerReject

    A nested repository can rewrite its own metadata and escape the sandbox.

  2. Fix submitted.

  3. Round 2ReviewerReject

    A symlinked file is invisible to the cross-check.

  4. Fix submitted.

  5. EscalatedFresh arbiterApprove

    Both holes closed. Evidence attached.

From Hardrails™' own development

Caught before merge

  • A sandbox escape through a nested repository
  • A terminal-read hole
  • A symlink blind spot in a cross-check
  • A test-coverage tool that failed open

The unlock

Safe enough to stop watching.

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

What it does while you sleep.

Each night's run ends in a morning digest. Your phone rings only for decisions that are yours.

  1. 01

    Overnight runs.

    Work continues unattended and ends in a morning digest.

  2. 02

    A plan that moves.

    The planner re-ranks by impact the moment you pivot.

  3. 03

    Independent reviewers.

    Reviewers from different AI vendors challenge each change.

  4. 04

    Production signals.

    Real usage, failures and drop-offs improve the product through the same gates.

  5. 05

    A place to run.

    The Hardrails™ runtime hosts what it builds.

Two ways in

Bring the team. Or bring the idea.

Platform

For engineering teams.

Bring your agents. Hardrails™ makes their work safe to ship.

Studio

Have an idea, not a team?

We take it from idea to a running product, built under Hardrails™.

Investors: request a briefing through the form.

Apply

Access is by invitation.

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.

Draft with AI (optional)

Sent to Lovable AI when you draft. Leave out credentials and confidential code.