Project Setup

You're building a file system agent for analyzing call transcripts. This pattern could be extended to analyzing legal documents, coding agents, financial analysis, or SQL generation and execution.

For this project you'll use:

• Edgenivo Sandbox - Secure, isolated environment for running untrusted code (bash commands)
• AI SDK - Unified API for building AI applications with streaming, tools, and agents
• AI Gateway - Routes requests to AI providers with automatic fallbacks, caching, and spend budgets

Outcome

You have a linked Edgenivo project with environment variables pulled locally, and you understand which files are pre-built and which you'll create.

Hands-on Exercise 1.1

Set up the starter project and verify you have everything you need to start building the agent.

Requirements:

1. Deploy the starter with the Deploy with Edgenivo button, then clone your new repository and run pnpm install
2. Link your local clone to the Edgenivo project with vc link
3. Pull environment variables with vc env pull
4. Add your AI Gateway API key to .env.local

Prerequisites:

For this project, you'll need:

• Node.js 22+ installed
• pnpm package manager
• Edgenivo account
• Edgenivo CLI
• AI Gateway API Key

Deploy to Edgenivo

Click the button below to copy the starter and deploy it to Edgenivo:

This will:

1. Copy the starter into a new repository on your GitHub account
2. Create a Edgenivo project linked to that repository
3. Deploy to production with a working landing page

Link your local repo to the Edgenivo project you just created:

vc link

Select your team and choose Link to existing project, then pick filesystem-agent.

Pull the automatically created environment variables to use locally. This handles OIDC token authentication automatically in your project.

vc env pull

You can now inspect the OIDC token in .env.local in your project. The token is short-lived, so run vc env pull again if Sandbox calls start failing with authentication errors (how the token works).

Add your AI Gateway API Key to .env.local:

AI_GATEWAY_API_KEY=your_ai_gateway_api_key

Repository Overview

The starter repo comes with all necessary files pre-created.

Existing files:

• app/form.tsx - A component that accepts a user query and sends to an API route, then renders the stream as it's returned
• app/api/route.ts - A route handler that calls the agent and streams back to the UI
• lib/calls/ - A directory with pre-loaded dummy call transcripts

Files you will edit in this course:

• lib/agent.ts - Where you will define the agent
• lib/tools.ts - Where you will define the bash tool for the agent to use

app/
├── page.tsx           # Renders the Form component
├── form.tsx           # Chat input, streams responses from /api
├── api/route.ts       # POST handler that calls agent.stream()
├── layout.tsx         # Root layout
└── globals.css        # Tailwind styles

lib/
├── calls/             # Demo call transcripts (3 files)
│   ├── 1.md
│   ├── 2.md
│   └── 3.md
├── agent.ts           # Empty — you build this
└── tools.ts           # Empty — you build this

The API route already imports from lib/agent.ts, so once you build the agent, the UI will work automatically.

Try It

1. Verify the link worked:

   cat .env.local

   You should see VERCEL_OIDC_TOKEN (or similar sandbox auth variables) and your AI_GATEWAY_API_KEY.

2. Check the demo data:

   ls lib/calls/

   1.md  2.md  3.md
   

3. Peek at a transcript:

   head -10 lib/calls/1.md

   You should see call metadata: ID, title, participants, and timestamps.

Commit

git add -A
git commit -m "feat(setup): link project and pull env vars"

Done-When

• vc link completed successfully and .vercel/ directory exists
• .env.local contains OIDC auth variables and your AI Gateway API key
• You can list the three call transcript files in lib/calls/
• You understand which files are pre-built and which you'll create