← All articles

GreatCTO now builds compliance-reviewed software for regulated industries — 5 new verticals, 20 new products

The catalog grew from 10 US industries to 15, and 40 products to 60 — but the news isn't the count, it's the kind. The five new verticals are all regulated: allied health, dental, insurance, accounting & tax, and law firms. Describe a product in one of them and the pipeline attaches the matching compliance reviewer — HIPAA, NAIC, SOX, or the bar rules — automatically.

Describe a product, approve the spec, ship the software. That's GreatCTO. Until now the catalog covered ten US service industries — home services, retail, proptech, fitness, HR, and the rest — 40 buildable products across six pipelines.

As of this week it's 15 industries and 60 products. The interesting part isn't the number. It's that all five new verticals are regulated — and GreatCTO now builds for them with the compliance review attached, not bolted on later.


The five new verticals

IndustryProducts
🩺 Allied health & clinicsPatient scheduling · Clinical charting · Insurance claims · Patient intake
🦷 Dental practicesDental scheduling · Treatment planning · Dental claims · Recall & reactivation
🛡️ Insurance agenciesQuote management · Policy management · Commission management · Agency CRM
🧾 Accounting & tax firmsClient books · Tax workflow · Document portal · Engagement billing
⚖️ Law firms & solo practitionersMatter management · Document automation · Client intake · Trust & billing

These aren't demo scaffolds. Each product maps to a real build pipeline — the healthcare "winning formula" (scheduling + charting + claims + intake), the insurance product surface (quote → policy → commission), the law-firm stack (matter → documents → trust accounting) — chosen from how these businesses actually run, not from what's easy to generate.

What makes it different: the compliance reviewer comes with the build

Anyone can generate a CRUD app for a dental office. The hard part of regulated software isn't the CRUD — it's the rules around it. So when you build in one of these verticals, GreatCTO detects the archetype and attaches the matching domain reviewer automatically, before a line ships:

  • Allied health & dental → HIPAA / PHI review (encryption, access control, BAA surface, CDT/ICD coding)
  • Insurance → NAIC / ACORD review (actuarial auditability, anti-discrimination pricing, filing standards)
  • Accounting & tax → SOX ITGC + IRS review (segregation of duties, ASC 606, 1099, Circular 230, taxpayer-data safeguards)
  • Law firms → the legal reviewer (below)

The reviewer writes a threat model, flags the domain-specific risks, and signs off before the build proceeds. You still approve one spec — the compliance expertise runs inside the pipeline, not in your head.

The one I'm proudest of: a legal archetype

Law-firm software has failure modes no generic reviewer catches, so GreatCTO got a brand-new legal archetype with a dedicated reviewer that understands the profession's actual obligations:

  • UPL (unauthorized practice of law) — the software must inform, not advise; attorney review is a structural gate, not a disclaimer.
  • IOLTA / client trust accounting — the no-commingling rule, per-client ledgers, three-way reconciliation, no drawing earned fees before they're invoiced. Get this wrong and it's a bar complaint, not a bug.
  • Attorney-client privilege — Model Rule 1.6: encryption, matter-level access, metadata scrubbing.
  • Conflict-of-interest screening — adverse-party checks that block intake before a conflict is created.
  • E-filing & court integration — PACER / CM-ECF, FRCP 5.2 redaction of PII.

That's the difference between a build that looks like legal software and one a solo practitioner can actually run without risking their license.

What else shipped this cycle

The verticals are the headline, but the engine got sharper underneath them:

  • Measured product quality. Every generated product now gets an automated 0–100 quality score (archetype-aware) — a clean build benchmarks ~89/100. "The AI built it" is no longer the quality argument; the number is.
  • Cross-model review. High-stakes diffs are red-teamed by a different model family (via OpenRouter) before they land — because a model reviewing its own family's code is blind to its own class of mistakes.
  • great-cto upgrade --self. One command self-upgrades the CLI, detecting however it was installed (npm / pnpm / volta / npx). Plus a quiet update notice when a new version ships.
  • A leaner board. The local build dashboard (great-cto board) now bundles cleanly on a fresh install and runs fully offline — no external fonts or CDNs.

Try it

GreatCTO is MIT-licensed and runs locally. Pick a vertical, describe the product, approve the spec:

npx great-cto@latest

Browse all 60 products across the 15 industries at greatcto.systems/build, or read the changelog — v2.82.2 is live.