Remote or On-site2 DaysZurich, Switzerland

Build Reliable AI Agents — 2-Day Program in Zurich

Bring your team up to speed on production-minded agents in Zurich. This two-day program uses the Vercel AI SDK — fundamentals, MCP, workflows, then build and deploy a real agentic feature with testing and telemetry.

View Full Workshop Details Book for Your Team

Why Take This Workshop in Zurich?

Zurich hosts Google's largest engineering office outside the US, along with ETH Zurich, one of the world's top technical universities. The city's fintech and enterprise scene is deeply invested in type-safe development. Our AI agents workshop in Zurich gives your team hands-on experience with reliable agentic systems and the AI SDK — the skill set engineering teams need to ship, not just demo.

Workshop at a Glance

Duration

2 Days

Format

Remote or On-site

Participants

Up to 15 participants

Price

CHF 7,520/team

What Your Team Will Learn

For software developers, technical leads, and builders moving from experiments to dependable agentic systems — especially teams standardizing on the Vercel AI SDK and modern web stacks.

Solid grounding in AI SDK Core: generation, streaming, structured data, and tool calling
Hands-on agent loops with explicit limits, validation, and error handling
Exposure to MCP and workflow patterns you can extend to your own systems
A deployable slice: streaming agent with tools, ready to iterate after the workshop
Practices for testing and telemetry so behavior does not regress silently

Workshop Curriculum

Content follows the AI SDK Core docs (generation, streaming, structured data, tool calling, MCP, middleware, testing, telemetry) and agent patterns your team can apply in production — not toy scripts.

Day 1 — Fundamentals with AI SDK Core

Agents vs. plain LLM apps: providers, models, and where the AI SDK fits
Generating text & streaming — shaping responses and handling stops
Structured outputs & validation — schemas and safe defaults
Tool calling — schemas, bad arguments, and bounded behavior
Agent-shaped loops — max steps, when to stop
Errors & reliability basics — timeouts, retries, logging

Day 2 — Deeper: MCP, deploy, and a real agent

Model Context Protocol (MCP) — tools and context at scale
Memory & prompts — system vs. messages, trimming
Workflows & subagents — handoffs and parallel vs. sequential work
Middleware & providers — logging, fallbacks, routing
Build block: end-to-end agent (e.g. Next.js) — stream, tools/MCP, state
Deploy & harden — env, secrets, testing and evals
Wrap-up: observability, regression tests, human-in-the-loop

Focus Areas

SDK

Vercel AI SDK Core

generateText, streaming, structured outputs, tool calling, and provider setup — the spine of the exercises.

MCP

Tools & MCP

First-party tools plus Model Context Protocol for real integrations with clear boundaries.

Ship

Next.js & deploy

Typical stack for Day 2: App Router patterns, streaming routes, and shipping to production.

Your Instructor

Davy Engone

Founder & Software Mentor @ Hackages

Davy helps teams ship software with confidence — including AI-assisted development and agentic systems. This program emphasizes reliability, evaluation, and shipping over slide-ware.