OpenAI Accredited Partner

    OpenAI Accredited Partner — Foundational KnowledgeOpenAI Accredited Partner — Codex Solutions Practitioner
    § Training · AI Agents

    AI Agents training

    From first agent to production multi-agent stack

    Everyone talks about agents, few get them stable in production. In this training you learn the full landscape: architecture patterns, tool use, memory, evaluation and the operational reality of agentic systems.

    Duration4 hours
    Group sizeUp to 12 attendees
    LocationIn-company or at our Utrecht office
    01

    What you learn

    • What an agent is and isn't, and when a workflow is enough
    • Architecture patterns: single agent, hierarchical, swarm and hybrid
    • Tool design: schemas, retries and their impact on model quality
    • Memory: short-term, long-term, episodic and vector stores
    • Evaluation with task suites, trajectory analysis and cost metrics
    • Production concerns: observability, sandboxing and human-in-the-loop
    • Vendor landscape: OpenAI Agents SDK, Anthropic, CrewAI, LangGraph
    02

    Who it's for

    • 01Developers and data consultants experimenting with agents
    • 02Product managers who need to assess feasibility
    • 03Architects fitting agentic systems into an existing stack
    03

    Programme

    09:30

    What is an agent

    Definitions, patterns and when a plain workflow is the better answer.

    10:30

    Tools and memory

    Tool schemas, retrieval, memory types and their failure modes.

    13:00

    Multi-agent

    Orchestration, communication and the pitfalls teams usually find in production.

    14:30

    Evals and monitoring

    Task suites, trajectory analysis, regressions and cost-per-task.

    16:00

    Building

    Build your own agent with a shared toolset and review.

    FIG. 01 — Programme: 4 hours
    04

    What you take away

    What you take away

    • A working agent for your own task
    • Decision tree for agent versus workflow versus chatbot
    • Eval template you can apply tomorrow

    Prerequisites

    • Python or TypeScript at reading level
    • Prior experience with an LLM API helps but is not required
    05

    Frequently asked questions

    Which framework do you use?+

    We show several — OpenAI Agents SDK, Anthropic patterns, CrewAI and LangGraph — and close with a decision model so you know when to use what.

    What does the training cost?+

    Pricing on request. We'll send a tailored quote that includes course materials, recordings and 30 days of async support afterwards. For in-company sessions you pay one flat fee, regardless of headcount up to 12 people.

    Where does the training take place?+

    By default at our office in Utrecht or in-company at your own location. Fully remote is fine too; we then split the day into two half-day blocks.

    Do I receive a certificate?+

    Yes. Afterwards you receive a certificate of attendance listing the covered topics and hours, usable for CPD points and internal records.

    Pricing on request

    Schedule this training

    Discuss your learning goals during a no-obligation intake. Afterwards, you receive a tailored programme and written quote.