Radar / Ideas / Gatehouse

Gatehouse

daily ideamoderateJEV confidence 0.61JEV monetization 0.62026-11-19
OutcomeEvery agent-written pull request in a regulated codebase merges with a full audit trail — and not one line of source code ever leaves the building.

The problem

Coding agents now write most of the code, and review is the bottleneck: a Harvard working paper across 718 firms found engineers wrote about 30% more code after adopting agents while completed work did not measurably rise and pull requests took 49% longer to merge. In banks, insurers and hospitals the problem is worse — cloud AI reviewers are unusable because the code cannot leave the perimeter, and Goldman Sachs reportedly pulled Claude Code from bankers and traders in September 2026 over data-security and IP-leakage concerns.

The idea

A self-hosted, air-gapped merge gate for agent-written code. Every pull request is checked against a versioned acceptance-criteria file before a human ever sees it; an independent open-weights reviewer model running on the org's own hardware re-reviews the diff and writes a verdict with evidence; a minimal memory layer remembers past verdicts so the same argument is never re-litigated; nothing merges until a human signs off, and every step lands in an audit log the compliance team can replay. Ships as a single Docker image plus a GitHub/GitLab check.

Why now

Three pieces landed this week — SoduWork's acceptance-criteria-plus-independent-review governance model, BRIDGE's minimal agent memory, and DaisyRose-27B, an RL-trained open agent model that doubles its base model's Terminal-Bench score — and the demand side just got measured: a Harvard working paper (Nov 17) shows review is now the bottleneck, and the Goldman pullback (Sept 28) shows regulated orgs are structurally excluded from cloud reviewers.

What it combines

SoduWork (governance: acceptance criteria plus independent AI review plus human sign-off) + BRIDGE (minimal RAG memory that remembers past review verdicts at ~5-7K tokens per query) + DaisyRose-27B (open-weights agent model, RL-trained for long-horizon agent tasks, runnable on-prem) + a typed decision gate for the merge verdict. Each piece alone is infrastructure; together they make a merge decision that is checkable, memorable, auditable, and entirely inside the customer's perimeter.

MVP

Build first: (1) a GitHub check that runs DaisyRose-27B via Ollama against a PR, (2) an acceptance-criteria file the reviewer must check each item against, (3) a BRIDGE-style memory file of past verdicts, (4) a block-until-human-approves rule with an audit log. Deliberately skip: Jira/Linear sync, auto-fix, multi-repo dashboards, hosted anything — one repo, one Docker image, one gate.

How it makes money

Budget owner: VP Engineering / Head of Platform, from the existing code-quality and AppSec budget — the same budget that already pays for SonarQube Server and AI reviewers. Pricing anchor: CodeRabbit Essentials at $24/user/month billed annually (https://crewmark.ai/blog/ai-code-review-tools) — a 100-developer team pays $2,400/month; SonarQube Server Developer Edition at ~$2,500/year for 100K LOC (https://dev.to/rahulxsingh/sonarqube-vs-sonarcloud-self-hosted-vs-cloud-code-quality-2026-dkj) anchors self-hosted pricing. Willingness-to-pay evidence: regulated orgs already pay for in-perimeter tooling and are actively losing the cloud option — Goldman Sachs reportedly pulled Claude Code from bankers and traders in September 2026 over data-security and IP-leakage concerns (https://www.promptzone.com/florence_herrera/goldman-sachs-pulls-claude-code-from-bankers-and-traders-20cf), and banks are building Bedrock-inside-the-boundary setups precisely to keep code in-house (https://www.nileforge.com/resources/insights/ai-coding-tools-regulated-enterprises-aws).

The moat

Business model plus architecture. CodeRabbit, Greptile and Qodo sell per-seat cloud review — their revenue requires customer code to flow to their servers. An air-gapped, flat-licence, open-weights gate cannibalizes that model: to copy it they would have to ship models and infrastructure on-prem, support air-gapped updates, and give up per-seat metering — a rebuild of both product and pricing, not a feature. The buyer segment is also structurally excluded from their product today: regulated orgs cannot send source code to a third-party cloud at all.

Distribution

B2B, sold to platform engineering and application-security teams at banks, insurers, healthcare providers and government agencies; the wedge is the air-gapped Docker image they can trial on their own hardware in an afternoon, sold through GitHub Enterprise Server / GitLab self-managed marketplaces and the security resellers that already serve these buyers.

Why it wins

CodeRabbit, Greptile, Qodo and Sourcery all review PRs in their cloud — the code must leave the building. Gatehouse is the only gate that runs the reviewer, the memory and the verdict inside the customer's own perimeter, and it gates on versioned acceptance criteria written before the work starts, not on a summary written after it.

Risks

Biggest risk is reviewer quality: an open 27B model will miss things a frontier cloud reviewer catches. The MVP de-risks it by benchmarking the gate on the team's own historical merged PRs and routing only low-risk paths to auto-verdicts while humans keep high-risk paths.

Build it with

Repo to start from

gatehouse — self-hosted merge gate: acceptance criteria, an independent open-model reviewer, review memory, and a human sign-off with a full audit trail

Evidence

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

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