Complete Guide to Project Context in GenMB

What Is Project Context?

Project Context is a block of plain text you write for a GenMB app that gives the AI lasting context about what you are building. Instead of repeating the same instructions in every chat message, your brand colors, API endpoints, coding conventions, or product requirements, you write them once and the AI reads them on every generation and refinement.

Think of Project Context as the project brief a new developer would read on their first day. It captures decisions, constraints, and standards so the AI produces consistent output across sessions, collaborators, and iterations.

Why Project Context Matters

Without it, every conversation with the AI starts from scratch. You describe your design system, the AI follows it for one generation, and then the next time you refine, it may drift. Project Context solves three specific problems.

Consistency Across Sessions

Your brand guidelines, color palette, and typography choices are read every time the AI generates or refines code. Whether you come back after five minutes or five weeks, the output stays aligned with your rules.

Reduced Prompt Repetition

Instead of pasting the same context into every prompt, "use Inter font, primary color #2563EB, 8px border radius on all buttons", the AI reads it from your project context automatically. Your prompts can focus on what you want built rather than how it should look.

Team Alignment

When multiple collaborators work on the same app, project context gives everyone the same AI behaviour. Design decisions are written down once and applied uniformly regardless of who is prompting.

How to Write Your Project Context

Step 1: Open the Teach the AI Panel

In the app editor, open the Teach the AI panel from the sidebar. It holds a single text box for that app.

Step 2: Write or Paste Your Text

Type your rules directly, or paste text you already have. Markdown is fine and headings help the AI find things. The box saves automatically as you write, so there is no separate save step.

Step 3: Let the AI Draft It For You

If you would rather start from something, use the generate PRD button. It drafts a product requirements brief for your app into the box, and you edit it from there.

Step 4: Keep It Current

Come back and edit the text whenever a decision changes. Stale rules are worse than no rules, because the AI will keep following them.

How the AI Uses Your Project Context

When you generate or refine code, the AI receives your project context alongside your prompt. The flow is simple:

1. You type a prompt like "Add a pricing page"
2. GenMB loads the project context saved on that app
3. The AI receives both your prompt and that text
4. It generates code that respects the constraints, styles, and conventions you wrote

The AI does not just match keywords, it reads the intent. If your text says "all buttons should use rounded corners and the primary brand color", the AI applies that to every button it generates, even if your prompt does not mention styling.

What to Write

Design Specifications

Describe your visual language:

```markdown

# Design System

Colors

• Primary: #2563EB
• Secondary: #7C3AED
• Background: #F8FAFC
• Text: #1E293B

Typography

• Headings: Inter, semi-bold
• Body: Inter, regular, 16px
• Code: JetBrains Mono

Components

• Border radius: 8px on cards, 6px on buttons
• Shadows: subtle (0 1px 3px rgba(0,0,0,0.1))
• Spacing: 8px grid system

`

API Reference

If your app talks to an external API, paste the endpoint reference:

```markdown

# API Reference

GET /api/products

Returns list of products.

Response: { products: [{ id, name, price, image_url }] }

POST /api/orders

Creates a new order.

Body: { product_id, quantity, customer_email }

Response: { order_id, status }

`

Coding Conventions

Write down the patterns you want followed consistently:

```markdown

# Coding Standards

• Use functional components only (no class components)
• Use const for all variable declarations
• Error messages should be user-friendly, never show raw errors
• All forms must have loading states and validation
• Use try/catch for all async operations

`

Product Requirements

Write the bigger picture, what the app is for and who uses it, so the AI keeps the goal in mind even when you are working on one small feature.

Limitations

Project context is useful but it has boundaries:

• Length: the box holds up to 50,000 characters. That is a lot of text, but it is not unlimited, so keep it focused.
• Text only: it is a plain text box. Describe visual requirements in words rather than pointing at an image.
• Order matters: put the most important rules near the top. Long context gets skimmed, short context gets followed.
• One app at a time: the text is scoped to a single app. To use the same rules in another app, paste it there too.

Summary

Project context gives you persistent, automatic context for your GenMB apps. Write your design rules, API reference, coding conventions, and product goals once in the Teach the AI panel, and the AI reads them on every generation and refinement. It removes prompt repetition, keeps output consistent across sessions, and keeps collaborators aligned. Keep it short, keep it current, and put the critical rules first.