Engineering

Set AI Team Conventions Everyone Shares

When every teammate explains the project differently, AI gets a different story each time. Shared team conventions give it one consistent account.

Open in Project Context Builder

Overview

Inconsistent AI output often starts with inconsistent humans: each person primes the model with their own version of the rules. A shared conventions profile fixes the source. This setup captures the standards for Field Notes, an editorial content project where house voice is the product — plain, concrete, second-person, every claim sourced. The Content Project mode adds editorial principles; your conventions pin the voice and the rules; the never-assume list bars invented facts and quotes. One profile, shared by the team, means the AI hears the same story from everyone.

How to use this resource

Agree the conventions

The voice, the standards, the rules everyone should be priming the AI with.
Put them in one profile

Mode-driven principles plus your own, in a single shared document.
Everyone uses the same one

Consistent input, consistent output, no per-person drift.

Why This Works

A shared profile removes the per-person variation that causes inconsistent results
Content Project mode contributes editorial principles teams forget to state
The never-assume list is the team's collective "don't do this" written down once

Best for

Teams where consistency is the product
Editorial and content operations
Anyone whose AI output varies by who prompted it

Not for

A personal one-off prompt — use the Prompt Template Builder
Defining a single role's behavior — use the Role Prompt Generator

FAQ

What should an AI team conventions profile include?

It captures the shared rules everyone should prime the AI with, in one profile: the house voice and Team Conventions, Naming Rules, Architecture Principles, a Glossary of project terms, and an Always Remember plus a Never Assume list. The Never Assume section is the important one — it bars the model from inventing statistics, quotes, or sources, telling it to flag a gap instead of filling it.

How do I use team conventions with ChatGPT or Claude?

Paste the profile into ChatGPT under Settings → Personalization → Custom Instructions, or into a Project's instructions so it scopes to that work; in other tools, drop it into the equivalent custom-instructions or project field. Because it is plain text every teammate shares, the whole team primes the model with the same account of the rules instead of each person's own version.

Does this make the AI remember our team rules automatically?

No — nothing is remembered on its own; you paste the profile in, and ChatGPT's custom instructions or a Project's instructions keep it in scope within that tool, not as permanent cross-tool memory. It is project knowledge, not behavior: for a task persona with rules and escalation use the System Prompt Generator, and to carry an in-progress task into a new chat use the Context Handoff Builder.

Customize This Resource

Opens this project in Project Context Builder. Build to get the full context profile — then adjust the mode, stack, glossary, and output target.

Open in Project Context Builder

Prompt Template

Copy it as-is, or use Open in Project Context Builder to load it pre-filled and customize it with your own context.

# Project Context: Field Notes

> Paste this into ChatGPT under Settings -> Personalization -> Custom Instructions, or into a Project's instructions.

## Project Overview
Field Notes is an editorial site publishing long-form articles on sustainable agriculture. A small editorial team produces 3-4 pieces a week with a consistent house voice.

## Core Facts
- Project type: Content Project
- Primary stack: Next.js, Tailwind CSS, TypeScript
- This is a content project — voice consistency and editorial standards matter as much as the words.

## Tech Stack
- Next.js
- Tailwind CSS
- TypeScript

## Team Conventions
- House voice is plain, concrete, and second-person; no hype words.
- Every factual claim has a linked source.
- Headlines are sentence case, under 65 characters.
- Respect the App Router and Server/Client Component boundary — mark client components with "use client". (Next.js)
- Style with Tailwind utility classes; reach for custom CSS only when no utility fits. (Tailwind CSS)
- No `any` — prefer `unknown` with narrowing; keep `strict` mode on and types honest. (TypeScript)

## Naming Rules
- camelCase for variables and functions, PascalCase for types and components. (TypeScript)

## Architecture Principles
- Hold the established voice and style across every piece — consistency is the product.
- Respect the content model and metadata structure; structured fields are not optional.
- Cite sources and keep claims verifiable.

## Glossary
- **Pillar** — a cornerstone article a cluster links back to.
- **Cluster** — a group of related articles around one pillar.
- **Kicker** — the short label above a headline.

## Always Remember
- The house voice is the product — consistency across pieces matters more than flair.
- This profile is the source of truth for project facts — prefer it over general assumptions.

## Never Assume
- Do not invent statistics, quotes, or sources — flag a gap instead of filling it.
- Do not assume a component runs on the client — Server Components are the default.
- Do not add a global stylesheet or CSS-in-JS — styling is utility-first with Tailwind.
- Do not assume a value's type — check the type definition before changing a signature.
- Do not invent facts, statistics, or quotes — if a source is missing, flag it rather than filling it in.
- When a fact is missing from this profile, ask — do not invent it.

## AI Usage Notes
- In ChatGPT, custom instructions persist across chats; for work split by project, a Project's instructions scope it more tightly.
- This profile is project KNOWLEDGE, not behavior — for a task persona (role, tone, escalation rules), build a System Prompt in the System Prompt Generator.
- It is durable project identity, not work state — to continue an in-progress task in a new chat, use the Context Handoff Builder.
- Profile completeness: 100/100 (Complete) — bracketed gaps, if any, mark missing info that was never invented.

More resources from Project Context Builder

Resource

Build Project Memory for AI

Stop re-explaining your project in every new chat. Capture it once as a context profile the AI keeps across every conversation — stack-inferred conventions and all.

Prompt Engineering

Resource

Create an AI Project Profile

A reusable profile that tells AI everything constant about your project — type, stack, conventions, glossary, architecture principles, and the rules it must never guess.

Prompt Engineering

Resource

AI Onboarding Context for an Existing Codebase

Onboard AI to a codebase the way you'd onboard a new hire: what it is, how it's built, the rules that aren't written down, and the things never to assume.

Engineering

Resources that pair well

Resource

AI Session Handoff — Shift Change for Working Sessions

End a working session like a shift change, not an abandonment: state captured, decisions logged, next step named — ready for the next session to pick up.

Prompt Engineering

Resource

Bug Triage Assistant

Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.

Engineering

Resource

Convert a Conversation to a Prompt — the Full Anatomy

What a converged conversation contains: a rejected voice, an accepted framing, a hard constraint, a format decision, and a final-version moment — each mapped to its prompt section.

Prompt Engineering

Related tools

Tool

Project Context Builder

Define what AI should permanently know about your project — stack conventions, glossary, and never-assume rules in a profile you paste once.

Context Tools

Tip: Save time by exploring related resources and tools that integrate with this resource.