Radar / Ideas / AgentGate: a merge queue that only…

AgentGate: a merge queue that only ships agent PRs it can prove are safe

daily ideamoderateJEV confidence 0.57JEV monetization 0.532026-11-18
OutcomeAgent-written pull requests merge without a human reading every diff, and no bad agent PR reaches production.

The problem

Coding agents now write most of the code at real teams — one two-person startup merged 11,040 PRs in a year with 82% of commits agent-signed. Agents report success while breaking things: one developer's release train froze for six days over a double bracket while every run said done, and another team's agent wrote an idempotency race condition with excellent documentation. Existing review tools read the diff; they cannot see which agent, harness, skill version, or prompt produced it, so the same mistake ships again next week.

The idea

A GitHub app and CI gate for agent-authored PRs. Every agent PR carries provenance: agent, harness, skill version, prompt hash. A decision model grades the diff against the repo's own mistake history — every merged incident becomes a check (ratchet tests, blast-radius review, cross-model second opinion). Low-risk PRs auto-merge; high-risk ones get a human-readable verdict naming the exact check that failed. The gate improves itself: each incident adds a check, so the same failure can never pass twice. Jev acts as the decision layer, scoring each PR's risk before the merge verdict.

Why now

StarSling made CI self-improving, SkillEvaluator grades agent skills with quality gates, t3code gives one control surface across harnesses, and agent-authored code just crossed the majority of commits at real teams. The provenance, grading, and control pieces all landed in the last week.

What it combines

StarSling's self-improving CI + SkillEvaluator's skill grading + t3code's cross-harness control surface + Pulsar's agent-to-agent messaging. CI alone reruns tests, grading alone scores skills, and a control surface alone watches agents — together they are a gate that knows who wrote the code, how good that writer's skills are, and what this repo has already learned not to accept.

MVP

Weekend MVP: a GitHub Action that (1) labels PRs by author agent from commit trailers, (2) runs a skill-grade check on the diff via an existing grader, (3) blocks merge on a configurable risk score with a one-line verdict. Deliberately skip: the self-improving incident loop, cross-harness messaging, and auto-merge — ship the label and block first.

How it makes money

Budget owner: VP Engineering or platform-engineering lead, out of the existing code-review and CI budget. Pricing anchor: CodeRabbit Essentials at $24 per developer per month (coderabbit.ai/pricing) — teams already pay that per developer for AI PR review, and AgentGate prices per agent-authored PR in the same band. Willingness-to-pay evidence: CodeRabbit charges $24-$72 per developer per month with public pricing and is the most-installed AI reviewer on GitHub; and a two-person team (Phoenix/Rush) merged 11,040 PRs in a year with 82% agent-signed commits, building its own mistake-driven checks because nothing on the market sold them one.

The moat

CodeRabbit, Qodo and Greptile would have to rebuild around agent provenance — which agent, harness, skill version and prompt produced each diff — and around per-repo incident corpora. Their product is a diff reviewer; the gate is a harness-layer system of record, and the per-repo mistake corpus is a data advantage that compounds with every incident a team records.

Distribution

B2B via a GitHub Marketplace app and CI integration; sell to platform-engineering leads at teams where agents already write most code. Land through harness vendors and control surfaces so every agent fleet gets the gate by default.

Why it wins

CodeRabbit, Qodo and Greptile review diffs from humans and agents alike; none of them gate on agent provenance, skill grades, or a repo's own incident history. AgentGate's verdict is 'this agent, with these skills, has made this mistake here before' — a diff reviewer cannot say that.

Risks

Biggest risk: teams distrust an automated gate and route around it. The MVP de-risks it by starting in advisory mode — verdicts posted as comments, merge never blocked — and only enabling blocking after a team sees the gate catch a real bad PR.

Build it with

Repo to start from

agentgate — a GitHub Action and app that grades agent-authored PRs on provenance, skill quality, and repo incident history, and blocks the merge when the risk score clears the team's bar.

Evidence

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.