Prompt Engineering

Standardize Project Terminology for AI

When half the team says "route" and the other half says "trail", AI picks one at random. Standardize the terms so its output uses your words, the same way every time.

Open in Project Context Builder

Overview

Terminology drift is quiet but corrosive: the model calls the same thing three names across one document because nobody fixed the canonical word. This setup standardizes the vocabulary for Trailmark, an offline-first hiking app, so route, waypoint, and sync token mean exactly one thing each. Where a glossary teaches what a term means, standardizing locks which term to use — the profile carries the canonical names verbatim and the never-assume rules keep the model from inventing synonyms. Output reads like one author wrote it, in your words.

How to use this resource

Pick the canonical terms

One name per concept — route, not trail; waypoint, not pin.
Carry them verbatim

The profile keeps your exact words; the model doesn't paraphrase them.
Get consistent output

Every answer uses the same vocabulary, document after document.

Why This Works

Standardizing is about which word to use, not just what a word means
Verbatim carriage stops the model swapping in plausible synonyms
Consistent terminology makes multi-session output read like one voice

Best for

Teams with competing names for the same thing
User-facing copy that must stay consistent
Projects spanning many AI sessions

Not for

Defining what unfamiliar terms mean — use the glossary-focused setup instead
A single task's formatting — use the Prompt Formatter

FAQ

How does a project context profile stop AI from swapping in synonyms for my terms?

The Glossary pins each concept to one canonical word — Route, Waypoint, Sync token for Trailmark — carried verbatim, and the Never Assume rules tell the model to ask when a fact is missing rather than invent it. The project-context-builder produces the profile; you paste it into your assistant's project instructions so it loads each chat.

Is this the same as giving the AI a glossary of what terms mean?

Not quite — this profile draws the line between teaching what a term means and locking which term to use. It standardizes vocabulary so Route always means the ordered series of GPS points and the model uses that exact word, and notFor points you to the glossary-focused setup when the goal is defining unfamiliar terms instead. It's project knowledge, not a task persona.

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: Trailmark

> Paste this into your AI tool's custom or project instructions so it loads in every conversation.

## Project Overview
Trailmark is a cross-platform mobile app for logging hikes and sharing routes. It works offline-first and syncs when a connection returns.

## Core Facts
- Project type: Software Project
- Primary stack: React Native, SQLite, TypeScript
- This is a software codebase — correctness, readability, and maintainability come before cleverness.

## Tech Stack
- React Native
- SQLite
- TypeScript

## Team Conventions
- All screens must work offline; network calls are queued and retried.
- No blocking spinners on the main thread.
- Location data stays on-device unless the user opts into sharing.
- Use React Native primitives (View/Text), not web DOM elements; mind platform differences (iOS/Android). (React Native)
- Mind SQLite's dynamic typing and single-writer limits; keep migrations explicit. (SQLite)
- 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
- Keep modules focused — a file or function should do one thing well.
- Prefer clarity over abstraction; introduce indirection only when duplication has actually appeared.
- Changes should come with the test that proves them.

## Glossary
- **Route** — an ordered series of GPS points for one hike.
- **Waypoint** — a user-marked point of interest on a route.
- **Sync token** — the cursor used to resume incremental sync.

## Always Remember
- The app is offline-first — assume the network can disappear at any moment.
- This profile is the source of truth for project facts — prefer it over general assumptions.

## Never Assume
- Do not assume a sync has completed — reconcile against the server cursor.
- Do not assume a value's type — check the type definition before changing a signature.
- Do not assume how a module is used elsewhere — check the call sites before changing a signature.
- When a fact is missing from this profile, ask — do not invent it.

## AI Usage Notes
- Paste this profile wherever your AI tool keeps persistent instructions — it should load automatically in each new chat.
- 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

Guides for this resource

Guide

Build a Project Glossary So AI Uses Your Terms

Give the AI context and it still writes "AI app builder" for your platform and "cart" for your basket — near-synonyms that change your meaning. Build a project glossary so AI uses your terms: define what each word means, name the synonyms to avoid, and paste it in your own tool.

AI Project Context & Handoffs

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