L
AI Lint
Doctrine for AI agents

Teach your AI the difference between "works" and "belongs."

AI already writes working code. The pain starts when you ship it: abstractions feel wrong, complexity gets hidden, reviewers rewrite half.

AI Lint externalizes senior engineering judgment—so agents build code that fits the language, the framework, and the long-term shape of your system.

Not a linter. Not a style guide. If a machine can enforce it mechanically, it doesn't belong here.

The core idea

AI is powerful, but sloppy in taste.

  • Syntax is cheap. Semantics is where projects rot.
  • Real teams don't ship "it compiles." They ship "it belongs."
  • Judgment shouldn't live only in people's heads.
  • AI Lint makes expectations explicit—for humans and agents.
AI Lint is anti-hype. It doesn't claim to replace senior engineers. It makes their standards visible, discussable, and consistently applied.

The problem isn't syntax.

AI models produce code that compiles. Then you review it and feel the familiar dread: it's not wrong enough to reject quickly—just wrong enough to quietly poison the codebase.

What you see

"Works" code that fights the language, invents needless abstractions, hides state, and turns maintainability into a slow leak.

Correct ≠ idiomatic

What's actually happening

The AI isn't failing at syntax. It's failing at judgment: what patterns belong, what tradeoffs are acceptable, what risks must be surfaced.

Semantics • taste • architecture

Rule of thumb: If a rule could be handled by ESLint, ShellCheck, a type checker, or static analysis, it does not belong in AI Lint. AI Lint is for the hard part: "does this belong?"

How it works

Drop in the doctrine. Wire your agent once. From then on, the agent consults AI Lint for architectural and taste decisions—and pauses when a human should choose.

1

Unzip into your repo

AI Lint ships as additive packs. Overlay App and Systems packs as needed.

2

Wire your agent

Copy the included prompts into AGENTS.md / CLAUDE.md / COPILOT instructions.

3

Agent consults doctrine

When making design decisions, the agent treats AI Lint as the authority.

4

Overrides are explicit

If a choice violates doctrine, the agent surfaces it and asks for an override.

"I can implement that pattern, but it violates AI Lint Doctrine #4 (No Invisible State).

It would make debugging UserSession nearly impossible later. Shall we use a dependency injection pattern instead?"

Packs

The free edition explains the frame and wiring. Paid packs provide deep doctrine, rejects, and exhibits for real languages and frameworks.

Free Edition

$0 source-available
  • Frame: “works” vs “belongs” (semantics, architecture, taste)
  • Wiring prompts for agents
  • Override protocol (tradeoffs are explicit)
  • Internal evaluation use
Download Free

Non-commercial; no redistribution; no model training.

Company License

$299–$499 one-time
  • Single legal entity
  • Unlimited internal users (single entity)
  • Internal commercial use allowed
  • Choose packs: Apps, Systems, or Bundle
Buy Company (Apps) — $299

Company (Systems) — $299  •  Company (Bundle) — $499

Enterprise

Contact custom
  • Multiple entities (subsidiaries / affiliates)
  • Procurement + invoicing
  • Custom terms / security review
  • We’ll fit your process without magic
Contact

If your org chart is complicated, this is the clean path.

Roadmap

We're building doctrine for the domains where AI judgment failures hurt the most. New packs ship as overlay ZIPs. Buy only what you need. Bundles available.

Database Q1 2026

SQL, PostgreSQL, indexes, N+1, migrations, transaction isolation

Infra Q1 2026

Kubernetes, Docker, Helm, resource limits, health checks, secrets

API Design Q2 2026

REST, versioning, pagination, error formats, idempotency keys

Auth Q2 2026

JWT, sessions, OAuth, RBAC, token rotation, confused deputy

Distributed Q2 2026

Sagas, idempotency, exactly-once, circuit breakers, retry policies

Observability Q3 2026

Logs, metrics, traces, cardinality, structured events, correlation

Mobile Q3 2026

Swift, Kotlin, React Native, lifecycle, memory, offline-first

Frontend Q3 2026

React, state management, component boundaries, accessibility

Want a specific pack prioritized? Let us know.

Built from experience, not theory

AI Lint was built after years of using AI to ship paid products—inside legacy codebases and production systems. It's the doctrine I wanted my agents to follow—and couldn't find.

What AI Lint optimizes for

Clarity over cleverness. Visible complexity over hidden magic. Causality you can debug. Explicit risk when you decide to break a rule.

What it avoids

Style policing. Mechanical "best practices." Boilerplate. Anything that a linter, formatter, or static analyzer can enforce.

FAQ

Is AI Lint a linter?

No. It's doctrine for judgment—semantics, architecture, and taste. If a machine can enforce it mechanically, it doesn't belong.

How does installation work?

Unzip ai-lint-core into your repo. Then unzip packs (App, Systems) over it. Files merge by directory.

What if doctrine conflicts?

AI Lint expects conflicts. The override protocol makes tradeoffs explicit. A good agent surfaces the conflict and asks for a decision.

Can my team modify it?

Yes (internal use). The whole point is to encode your standards. The paid license permits internal modification and use in private repos.

Do bundle buyers get future packs?

No. New packs are sold separately as overlay ZIPs. The bundle is Apps + Systems.

Do you have a hiring / contributor loop?

Yes. If you want to encode hard-won knowledge into doctrine packs (languages, frameworks, security), email us. This becomes a virtuous cycle.

Write doctrine. Get paid.

We're looking for engineers who've shipped in production and have opinions about what belongs. If you've debugged the same AI mistakes repeatedly—in React, Kubernetes, PostgreSQL, or anywhere else—that's doctrine waiting to be written.

What we're looking for

Real scars. Patterns you've seen break in production. Framework fights you've lost. The stuff that's obvious to you but invisible to AI.

What you get

Revenue share on packs you author. Your name on the doctrine. A way to encode your judgment into something that scales.

I have scars