Development guide

The repository is a pnpm workspaces monorepo, primarily TypeScript 5, with a React Portal and a Rust AI gateway. Start with Local development to install dependencies and run the stack, then read Contributing before opening a pull request.

Repository structure

Path	Contents
apps/api/	REST API and live event streaming
apps/portal/	Web UI and Storybook components
apps/cli/	CLI for evaluation management and automation
apps/scheduler/ and apps/judge/	Run dispatch and criteria evaluation
apps/workers/	Coding-agent, post-processing, and report workers
apps/gateway/ and apps/token-manager/	AI traffic capture and credential management
packages/	Shared types, storage clients, migrations, and supporting libraries
evaluations/	Developer-run static prompt quality tooling
config/ and docs/	Evaluation examples and technical documentation
website/	This documentation website

Development commands

Run these commands from the repository root:

pnpm test                  # Unit tests
pnpm lint                  # Workspace lint and type checks
pnpm build                 # Workspace builds
pnpm storybook             # Portal component catalog
pnpm test:integration      # Integration tests; requires .env and backing services

Evaluate Scope’s own AI prompts with pnpm eval:prompts -- --mode quality (the default mode). See the prompt evaluation guide for setup, model credentials, and offline validation.

For service-by-service development, Rust commands, migrations, and code conventions, read CONTRIBUTING.md. For documentation authoring and preview commands, see website/README.md.

Architecture and configuration references

These detailed engineering references live alongside the source code:

Topic	Guide
Architecture and run lifecycle	System architecture
Domain models and API design	Application design
Project organization	Projects
Evaluation and criteria DAGs	Criteria provider
Static prompt quality	Prompt evaluations
Agent context	Skills and codebases
Scheduling and recovery	Queue scheduler
Configuration and authentication	Environment variables
Kubernetes and Azure deployment	Kubernetes self-hosting
AI limitations and data handling	Responsible AI FAQ
More architecture, operations, and research	Documentation index