Training course · AI Agent Development · JavaScript & TypeScript

AI Agent Development for JavaScript and TypeScript Developers

Build AI agents professionally: architectures, tool use, agent SDKs, LangGraph, memory, evals, guardrails and deployment.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

“AI Agent Development for JavaScript and TypeScript Developers” is a hands-on course for roles such as Front-end and full-stack developers working in JavaScript or TypeScript, Teams migrating an existing JavaScript codebase to TypeScript and Library and SDK maintainers in the npm ecosystem. Rather than learning AI Agent Development in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from JavaScript & TypeScript.

AI agents go beyond conventional chatbots: they break tasks down, call tools and APIs, evaluate the results and keep iterating until a goal is met. In this two-day course you learn to build such systems so that they work reliably, transparently and safely in day-to-day business. You compare architectural patterns ranging from simple workflows through the agent loop to multi-agent systems, and you implement them hands-on with the Claude Agent SDK, the OpenAI Agents SDK and LangGraph.

The focus is not on a quick demo but on the path to production. You design tool interfaces and context deliberately, connect tools via the Model Context Protocol, plan short-term and long-term memory and build evaluations that surface regressions early. On top of that come guardrails against prompt injection and harmful actions, human-in-the-loop approvals, tracing, cost control and deployment. By the end you can judge when an agent is worthwhile, when a deterministic workflow is enough and which framework fits your project.

JavaScript and TypeScript now run in the browser, on servers, in build pipelines and on edge platforms. That breadth comes with complex toolchains: bundlers, transpilers, linters, package managers and an npm ecosystem that never stands still. AI coding assistants and agents remove a great deal of that friction. They migrate JavaScript modules to TypeScript incrementally, derive precise types from API responses, fix ESLint findings, write Vitest or Jest tests and explain nested generics in plain language. For the output to fit your project, the tools need clear guardrails: tsconfig strictness, module system, coding guidelines and test commands. This course shows you how to provide that context deliberately and how to scrutinise generated code.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Front-end and full-stack developers working in JavaScript or TypeScript
  • Teams migrating an existing JavaScript codebase to TypeScript
  • Library and SDK maintainers in the npm ecosystem
  • Tech leads who own tooling, linting and build processes

Typical challenges we address

  • Gradual type erosion through any, type assertions and lax tsconfig settings
  • Complex toolchains mixing bundlers, transpilers, ESM and CommonJS that are hard to debug
  • Huge dependency trees carrying security and maintenance risk
  • Asynchronous code with hard-to-reproduce race conditions and gaps in error handling

What you will be able to do

  • You choose the right pattern for a task, from a fixed workflow to an autonomous agent.
  • You design tools and context so that agents work reliably and cost-effectively.
  • You implement agents with the Claude Agent SDK, the OpenAI Agents SDK or LangGraph.
  • You set up evaluations and tracing to measure quality and detect regressions.
  • Use AI agents deliberately for TypeScript migrations, typing work and test generation.
  • Feed assistants your tsconfig, lint rules and project conventions so generated code fits your existing stack.
  • Critically assess proposed npm dependencies and generated code for type safety and security.

Course outline

Day 1

Module 1 Agent architectures and design patterns
  • Workflows versus agents: prompt chaining, routing, parallelisation, orchestrator-worker
  • The agent loop: plan, act, observe, reflect
  • Multi-agent systems, subagents and handoffs between agents
  • Criteria for choosing model, framework and level of autonomy
Module 2 Tool use and context engineering
  • Function calling and structured outputs with JSON Schema
  • Designing good tools: granularity, naming, error messages, idempotency
  • Connecting and reusing tools via MCP servers
  • Managing the context window: summarisation, compaction, retrieval and prompt caching
Module 3 Frameworks in practice
  • Claude Agent SDK: agent loop, tools, subagents, permissions and hooks
  • OpenAI Agents SDK: agents, handoffs, guardrails and tracing
  • LangGraph: stateful graphs, checkpointing and human-in-the-loop
  • Side-by-side comparison on the same task and criteria for choosing a framework
Module 4 Memory, evals and observability
  • Short-term and long-term memory, storage strategies and forgetting
  • Evaluation datasets, LLM-as-a-judge and task-based success metrics
  • Tracing tool calls, token usage and latency
  • Regression testing when prompts, models or tools change

Day 2

Module 5 Guardrails, security and deployment
  • Protecting against prompt injection, data exfiltration and over-privileged tools
  • Input and output checks, approval steps and sandboxing
  • Deploying as a service, asynchronous execution, retries and cost limits
  • Governance, audit logging and requirements under GDPR and the EU AI Act
Module 6 Practice lab: JavaScript & TypeScript
  • Incremental TypeScript migration
  • Deriving types from APIs and schemas
  • Writing Vitest and Jest tests
  • Fixing ESLint findings and code smells
  • Debugging build and bundler issues
  • Upgrading dependencies
Module 7 Data protection, quality & transfer to daily work
  • The npm ecosystem is a frequent target of supply-chain attacks, so vet every dependency the AI suggests for provenance, maintenance and licence (for example copyleft terms). Keep API keys and tokens out of prompts and clarify contractually whether your source code may be used to train the provider’s models.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Incremental TypeScript migration

The agent converts JavaScript files to TypeScript module by module, infers types from usage, replaces any with precise types and tightens tsconfig strictness in controlled steps until the compiler runs clean.

Deriving types from APIs and schemas

JSON samples, OpenAPI specifications or database schemas are turned into TypeScript interfaces and Zod schemas for runtime validation, so front end and back end share one consistent contract.

Writing Vitest and Jest tests

For utilities, hooks and services, the AI generates unit tests with sensible mocks, fake timers and snapshot strategies, runs them and fixes failing cases on its own.

Fixing ESLint findings and code smells

The assistant works through lint warnings systematically, replaces outdated patterns such as callback chains with async/await and explains for each rule why the change makes sense.

Debugging build and bundler issues

Error output from Vite, webpack or esbuild is analysed, ESM/CommonJS conflicts are resolved and configuration for path aliases, tree shaking or source maps is corrected.

Upgrading dependencies

The AI reads changelogs for major npm package upgrades, adapts code to breaking changes, updates lockfiles and verifies everything through a type check and a full test run.

Possible hands-on projects

Type-safe API client

A small TypeScript package that generates a type-safe fetch client with Zod validation from an OpenAPI specification, ready to publish to npm with tests.

Browser extension

A TypeScript browser extension that analyses page content and copies it to the clipboard in a structured format – including manifest, content script and automated build.

Monorepo health check

A Node script that inspects workspaces in a monorepo, detects duplicate or inconsistent dependency versions and proposes a clean-up plan.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. Good command of modern JavaScript, a working knowledge of TypeScript and experience with npm, pnpm or yarn and Git.

Technical requirements

A laptop with Python or Node.js, Git and a code editor, plus API access to at least one LLM provider such as Anthropic or OpenAI. Credentials for the exercises can be provided if needed.

Data protection & compliance

The npm ecosystem is a frequent target of supply-chain attacks, so vet every dependency the AI suggests for provenance, maintenance and licence (for example copyleft terms). Keep API keys and tokens out of prompts and clarify contractually whether your source code may be used to train the provider’s models.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Tue, 1 December 2026 – Wed, 2 December 2026 Kaiserslautern Request
  • Mon, 7 December 2026 – Tue, 8 December 2026 Online Request
  • Tue, 15 December 2026 – Wed, 16 December 2026 Bremen Request
  • Wed, 20 January 2027 – Thu, 21 January 2027 Salzburg Request
  • Mon, 1 February 2027 – Tue, 2 February 2027 Online Request

Frequently asked questions

Which agent framework should we use?

It depends on your model strategy, the level of control you need and your team’s skills. Vendor SDKs offer a lean start with tightly integrated features, while LangGraph gives you finer control over state and flow. In the course you solve the same task with several frameworks and derive clear selection criteria for your own project.

How do you stop an agent from taking wrong or dangerous actions?

With several layers of protection: narrowly scoped tools with minimal permissions, input and output validation, approval steps for critical actions, sandboxing and continuous evaluation. Prompt injection via external content is treated as a realistic threat. You practise these measures directly on your own agent.

Does every automation need an agent?

No. Many tasks are handled more reliably, cheaply and transparently by a fixed workflow of a few LLM calls. Agents pay off when the solution path cannot be planned in advance and the system must react flexibly to intermediate results. We train exactly this trade-off using practical examples.

How well do AI assistants handle complex TypeScript types?

Current models understand generics, conditional types and mapped types very well and can explain them clearly. For highly complex type constructions, though, the compiler remains the ultimate judge. On the course you learn to have the agent run tsc iteratively, so suggestions are not merely plausible but genuinely type-correct before you accept them.

Is the course suitable for pure front-end developers?

Yes. The focus is the language and its tooling – typing, tests, linting, builds and dependencies – which matter equally on the front end and the back end. If you want to go deeper into React or Node.js specifically, our catalogue includes dedicated course variants for those stacks.

How much does “AI Agent Development for JavaScript and TypeScript Developers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for JavaScript and TypeScript Developers

More AI Agent Development courses

All 30 AI Agent Development courses

AI Agent Development · MunichAI Agent Development · SalzburgAI Agent Development · BerlinAI Agent Development · AugsburgAI Agent Development · HanoverAI Agent Development · BremenAI Agent Development · StuttgartAI Agent Development · KaiserslauternAI Agent Development · Online