What Mneme prevents

Governance violations Mneme catches before generation

Concrete examples of the architectural decisions Mneme enforces against. These are not generic lint rules — they are organizational decisions encoded as structured constraints, injected into the agent's context, and checked at the file-write seam before the code exists.

The frame. Mneme injects your organization's architectural decisions into AI-assisted generation workflows. Each example below is a decision the team has already made — an ADR, a layering rule, a security policy, an ownership boundary — that Mneme keeps the agent honest about. The decision corpus is the source of truth; the violations below are what happens without it.
Category 01

Architecture governance

Layer boundaries, forbidden patterns, deprecated architectures. The decisions that define how the system is shaped — not what it does, but how its parts are allowed to relate.

01

Forbidden architecture patterns

Rule. Do not access BigQuery directly from frontend routes.

// AI generates inside a Next.js API route
const client = new BigQuery();
forbidden dependency ADR violation architectural boundary breach
02

Layer boundary violations

Rule. Controllers must not contain business logic.

@app.post("/checkout")
def checkout():
    # pricing logic
    # tax logic
    # inventory logic
logic in presentation layer missing service abstraction
03

Unauthorized framework introduction

Rule. React app standardized on Zustand. No Redux.

import { createStore } from "redux";
non-approved state management stack divergence
Category 02

Workflow governance

Protected directories, ownership boundaries, migration restrictions, prompt-level policies. The decisions that govern who — or which agent — is allowed to touch what.

04

Monorepo scope violations

Rule. Billing agent cannot modify the auth package.

# AI agent edits
packages/auth/*
scoped ownership breach out-of-domain modification
10

Agent workflow violations

Rule. Codegen agents cannot write directly to production migration folders.

# Agent modifies
db/prod/migrations/*
restricted execution scope protected path mutation
11

Prompt-level governance

Rule. Do not generate mock auth implementations.

# User prompt
"Just create a quick fake JWT validator."
policy conflict before generation governance-before-generation
Category 03

Security governance

Unsafe query construction, credential handling, insecure auth patterns. The decisions where a violation is not just architectural debt but a vulnerability the team has already chosen not to ship.

05

Security policy violations

Rule. No raw SQL string concatenation.

query = f"SELECT * FROM users WHERE id = {user_id}"
unsafe query construction secure coding rule breach
Category 04

Dependency governance

Banned libraries, licensing constraints, version pins, and the supersession history of decisions the team has already revisited. Dependencies are decisions; Mneme treats them as such.

08

Dependency licensing

Rule. No GPL dependencies.

// AI adds to package.json
"some-gpl-library": "^2.1.0"
licensing policy violation approved-list deviation
09

ADR supersession violations

Rule. ADR-002: all async jobs use Pub/Sub. (Supersedes an older ADR that allowed Celery.)

from celery import Celery
superseded decision outdated architecture pattern precedence-aware enforcement
Category 05

Platform governance

Observability requirements, infra standards, deployment policies, API contracts. The decisions platform teams ship to keep services consistent across the org.

06

Infra governance violations

Rule. All infrastructure changes must use Terraform modules.

gcloud compute instances create ...
bypassing approved infra workflow untracked change surface
07

API contract violations

Rule. Internal APIs must version under /v1/.

@app.route("/users")
routing convention breach API governance mismatch
12

Organizational consistency violations

Rule. All services must emit OpenTelemetry traces.

# AI creates a new service with no tracing middleware
def create_app():
    app = FastAPI()
    return app
observability standard breach platform compliance failure

The distinction that matters. Mneme injects organizational architectural decisions into AI-assisted generation workflows. The examples above are not static lint rules; they are decisions the team has already made, in the form the agent needs to see them, at the moment it is about to generate.

This is the difference between "we scan for bad code" and "we keep the agent honest about the decisions you've already made." The first is a check after the fact. The second is the layer that makes drift structurally harder.