Skip to main content
Every team has unwritten rules — technology preferences, naming conventions, architectural decisions. Instead of documenting them all upfront, you can teach Kody through natural conversation.

​
How it works

When you talk to Kody in PR comments, it detects when you’re stating a convention or preference and automatically saves it as a Memory. Memories are then applied as high-priority context in all future code reviews and conversations.

​
Explicit teaching

Directly tell Kody to remember something: 
@kody remember: API payload keys are camelCase, database columns are snake_case.

@kody please remember: in the domain layer, entities must never have nullable properties by default.

​
Implicit learning

State a preference naturally — Kody picks it up: 
@kody in this repo we avoid Lodash and prefer native JS array methods.

@kody we're migrating from AWS SDK v2 to v3; treat any new v2 import as blocker.

@kody for Postgres existence checks we prefer EXISTS over COUNT(*).

​
What Kody won’t save

Kody is selective about what becomes a memory:
  • Temporary instructions (“fix this now”, “skip this for today”)
  • Questions (“what’s the deadline?”)
  • Debugging chatter (“I see an error”)
  • Vague statements without actionable information
  • Requests scoped to a single PR or task

​
Memory scopes

Each memory applies at a specific level:
ScopeExample
Directory”In src/components/ui, always use our design system tokens”
Repository”This repo uses hexagonal architecture”
Organization”All repos use ESLint flat config”

​
Approval workflow

If you want to review AI-generated memories before they take effect, enable LLM-generated memories approval in settings. Memories will enter a pending state until you approve them.

​
Managing memories

Go to Code Review Settings → Kody Rules → Memories tab to view, edit, or delete memories. You can also create memories manually from the UI. For details, see Kody Rules — Memories.