Training course · AI Agent Development · Tech Leads & Engineering Managers

AI Agent Development for Tech Leads and Engineering Managers

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

This course connects AI Agent Development with the everyday processes of Tech Leads & Engineering Managers. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

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.

AI coding assistants and autonomous agents are changing how engineering teams work: tasks are sliced differently, effort shifts from writing code to reviewing it, and deciding which work can be delegated to agents becomes a leadership responsibility. Tech leads and engineering managers have to select tools, set policies, enable their teams and measure impact without losing sight of code quality, security and the growth of junior engineers. In this course you learn to plan the rollout of AI coding tools in a structured way, establish shared working practices and rule files for your team, choose meaningful metrics beyond raw speed and apply AI to leadership tasks such as planning, onboarding and technical communication. Deep programming skills are not required.

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?

  • Tech leads and lead developers
  • Engineering managers and software team leads
  • Heads of engineering and CTOs in mid-sized companies
  • Delivery and project leads in IT organisations
  • Developer experience and enablement leads

Typical challenges we address

  • Unclear policies lead to a patchwork of tools and shadow AI within the team
  • More generated code increases review load and the risk of technical debt
  • Difficulty measuring the real benefit of AI tools in a credible way
  • Concerns about junior engineers’ skill development and team buy-in

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.
  • Plan the rollout of AI coding tools in a structured way with clear policies, roles and guardrails.
  • Measure the impact on delivery, quality and satisfaction with credible metrics.
  • Use AI agents yourself for leadership tasks such as planning, onboarding and technical communication.

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: Tech Leads & Engineering Managers
  • Writing a team AI policy
  • Rule files and team conventions
  • Measuring impact
  • Slicing work for agents
  • Faster onboarding
  • Technical communication
Module 7 Data protection, quality & transfer to daily work
  • As a leader you own the legal framework: you learn to address licensing and copyright questions around generated code, protection of source code and secrets, works council co-determination rights when measuring performance and obligations under the GDPR and the EU AI Act in your team policies.
  • 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

Writing a team AI policy

Draft a practical guideline that clearly defines approved tools, permitted data classes, review obligations for generated code, handling of secrets and accountabilities, illustrated with concrete examples.

Rule files and team conventions

Build shared context files for coding agents covering architectural principles, testing strategy, style rules and banned patterns, keep them under version control and ensure consistent output across the team.

Measuring impact

Collect metrics such as DORA measures, pull request cycle time, change failure rate and developer satisfaction before and after rollout, and prepare the analysis with AI support.

Slicing work for agents

Write and break down backlog items so they can be delegated to agents with clear acceptance criteria, and decide which tasks deliberately stay with people.

Faster onboarding

Prepare codebases, architecture decisions and operational knowledge for new team members, create guided exploration tasks and have questions about the codebase answered with source references.

Technical communication

Draft incident post-mortems, roadmap updates, decision papers for senior management and release notes from tickets and commits, structured and tailored to each audience. This frees up time for actual leadership.

Possible hands-on projects

Team metrics dashboard

A small web app that pulls data from your Git platform and shows cycle times, review duration and deployment frequency over time.

PR summariser

A bot that collects all merged pull requests each week and turns them into a readable status report for stakeholders.

Onboarding guide generator

A script that analyses repository structure, README files and ADRs and produces a structured onboarding plan with learning tasks. It adapts to role and seniority.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. You lead a software team, either technically or as a line manager, and understand the development process; current hands-on coding is helpful but not required.

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

As a leader you own the legal framework: you learn to address licensing and copyright questions around generated code, protection of source code and secrets, works council co-determination rights when measuring performance and obligations under the GDPR and the EU AI Act in your team policies.

Suggested dates

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

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Thu, 3 December 2026 – Fri, 4 December 2026 Augsburg Request
  • Tue, 15 December 2026 – Wed, 16 December 2026 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Kaiserslautern Request
  • Tue, 2 February 2027 – Wed, 3 February 2027 Online Request
  • Tue, 16 February 2027 – Wed, 17 February 2027 Bremen 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 do we tell whether AI coding tools are worth it?

Don’t count generated lines of code; look at outcomes: lead time from idea to production, change failure rate, review effort, defect rates and team satisfaction. A baseline before rollout and accompanying qualitative surveys are essential. In the course you design a lean measurement approach that fits your organisation and involves employee representatives.

Do junior engineers still learn enough when AI writes the code?

The concern is valid and can be managed. Proven practices include having engineers explain every generated section in review, deliberate practice phases without an assistant and pairing with experienced colleagues where AI acts as a learning partner. You learn to adapt learning paths and review culture so that skill building and productivity go hand in hand.

How much does “AI Agent Development for Tech Leads and Engineering Managers” 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 Tech Leads and Engineering Managers

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