---
title: "Build Your Own AI Agent - Web Summer Camp"
url: https://stacklist.com/card/e6d3e7d0-d33e-437e-a3c7-e199e555250d
source_url: "https://websummercamp.com/2026/session/build-your-own-ai-agent"
stack: https://stacklist.com/stack/3d40319c-c76c-4ae5-b09d-40eea149cbc9
summary: "Build Your Own AI Agent Workshop at Web Summer Camp 2026 is a hands-on half-day workshop teaching developers how to create tool-using AI agents that can reason, take autonomous actions, and interact with APIs and code. Participants will progress through three stages—setup and first agent, custom tools, and enhancing real projects—to build a repeatable workflow applicable to their own projects."
tags: "ai-agents, workshop, claude, hands-on, tool-building, autonomous-systems, web-development"
key_entities: "Web Summer Camp 2026 (event), Claude Code (technology), Anthropic API (technology), Node.js (technology), Martina (person), Stacklist (organization), Toptal (organization), AI agents (concept), tool-using agents (concept)"
classification: "tutorial"
content_hash: "sha256:d1fefa016048a975e7e98bfb2746cd88b6d320f06d86bd68a1ff5dfcdda6c5a6"
acp_version: "0.2"
token_counts_approximate: 592
visibility: public
agent_accessible: true
status: "final"
---

# Build Your Own AI Agent - Web Summer Camp

Description AI agents are reshaping how we build software — but most developers haven't built one themselves. In this hands-on half-day workshop, you'll go from zero to a working, tool-using AI agent that can reason about problems, take autonomous actions, and interact with files, code, and external APIs. We'll work in three stages, each producing a complete, working agent you can take home: Stage 1 — Setup and your first agent. You'll install Claude Code, connect your Anthropic API key, and scaffold a minimal agent from the CLI. You'll see how the agent loop works from the inside — how Claude reasons about a task, picks tools, acts, and iterates. By the end of this stage, you'll have a working agent that can read and reason about a codebase. Stage 2 — Custom tools. You'll learn to extend your agent with custom tools — giving it new capabilities like calling external APIs, manipulating files, and searching the web. This is where it clicks: you'll watch your agent autonomously decide which tools to use, chain actions together, and recover from failures. Stage 3 — Enhance a real project. You'll pick one of three prepared GitHub repositories — a web app with bugs to find, an API with missing documentation, or a data pipeline with failing tests — and use your agent to actually improve it. Read the code, diagnose issues, generate fixes, write tests. You'll work with Claude Code the way you would on a real project, and walk away with a workflow you can use on Monday. Key takeaway A repeatable workflow for building AI agents with Claude Code that you can apply to your own projects immediately. Prerequisites Have installed on your laptop:   1. Node.js 18+   2. Claude Code    3. Clone the repo: git clone https://github.com/marti06/summer-camp-agent-build.git API keys will be shared by the speaker at the workshop. Speaker Co-founder, CTO @ Stacklist Martina is the CTO and co-founder of Stacklist, an online curation platform helping users organize and save their favourite places. With a background in full-stack development, engineering leadership, and product strategy, she has built and scaled remote technical teams while navigating the complexities of startup growth. Before Stacklist, she held leadership roles at Toptal, working with high-performing distributed teams.