Skip to content

Teaching / Course 03

Agentic Engineering

From tool calling and MCP to governed, testable agent systems

How to take an AI agent that works in a demo and give it permissions, tests, an audit trail and a stop button — so you can let it near a real system.

A software-engineering course for moving beyond prompt demos and vibe-coded prototypes toward typed tools, durable workflows, security controls, evaluations and auditable governance.

A directed agent graph on the site's lattice: typed tool nodes, an approval gate rendered as a diamond, a checkpoint ring and a blocked edge marked at the trust boundary.
Format
3 days · 21 contact hours
Audience
AI and software engineers, architects, security specialists and technical product owners.
Delivery
One agent is progressively extended with tools, MCP, state, approvals, tests, security and governance evidence.
Capstone
A governed research or operations agent with typed contracts, an MCP server, evaluation and red-team evidence.

Feasibility verdict

Feasible when one primary Python stack is used and multi-agent systems remain a design exercise. Building several unrelated agents or comparing every framework hands-on would not fit.

Outcomes

What a participant can do afterwards.

  • Distinguish chatbots, deterministic workflows, tool-using agents and multi-agent systems and select the simplest suitable architecture.
  • Explain the responsibilities of an agent harness: instructions, context, tools, state, control loop, permissions, budgets, validation and observability.
  • Build typed tools with preconditions, postconditions, invariants, explicit errors and approval requirements.
  • Package a reusable skill and explain progressive disclosure, versioning, provenance and skill security.
  • Build and consume an MCP server using the current stateless 2026-07-28 specification concepts for tools, resources and prompts.
  • Add state, checkpoints, retries, idempotency, human-in-the-loop gates and safe termination to an agent workflow.
  • Move beyond vibe coding through specifications, tests, static analysis, CI, sandboxes, dependency controls and reviewable changes.
  • Evaluate complete trajectories and map technical evidence to NIST AI RMF, ISO/IEC 42001, the EU AI Act and OWASP agentic risks.

Depth

Realistic depth within three days.

The difference between these three columns is the difference between a course description and a course. Everything in the third column is real content — it is simply not something anyone builds from scratch in 21 hours.

Implemented

Written by participants, from scratch or near it.

  • Typed agent and tool contracts
  • Local MCP server and client
  • Evaluation and approval workflow

Practised

Run, tuned and measured against prepared scaffolding.

  • State, checkpoints and idempotency
  • Security tests and trajectory analysis
  • Governance and operational evidence

Surveyed

Explained and demonstrated. Not built in three days.

  • Large multi-agent platforms
  • Enterprise certification programmes
  • Provider-specific agent products and deployment clouds

Day 1

09:00–17:30

Harnesses, tool contracts, skills and MCP

Build a constrained single agent before adding orchestration complexity.

  1. 09:00

    Architecture baseline

    Chatbot, workflow and agent distinctions; the autonomy spectrum; when conventional software is the better answer.

  2. 09:30

    Harness engineering

    Model, instructions, context, tools, state, control loop, policies, budgets, stop conditions, errors and observations.

  3. 10:45

    Tool calling and contracts

    JSON schemas, typed dependencies, preconditions, postconditions, invariants, error types, timeouts, retries and result validation.

  4. 13:15

    Permissions and approvals

    Read versus write tools, least privilege, capability grants, confirmation, compensation and side-effect boundaries.

  5. 14:00

    Skills

    Reusable procedures, manifests, supporting files, progressive loading, versioning, provenance and malicious-skill risks.

  6. 15:15

    MCP architecture

    Hosts, clients and servers; tools, resources and prompts; the current stateless request model, metadata, caching and authorization concerns.

  7. 16:00

    Lab 1 — typed agent and MCP Lab

    Build a small typed agent, create read-only and side-effecting tools, expose a local MCP server and require approval for writes.

Day output A constrained single agent with typed tools, explicit errors, a local MCP server, a permission matrix and an approval gate.

Day 2

09:00–17:30

Durable orchestration and beyond vibe coding

Make execution explicit, resumable and maintainable.

  1. 09:00

    Recap and trace review

    Inspect Day 1 traces and identify ambiguous tool descriptions, malformed arguments and unsafe side effects.

  2. 09:30

    Agent and workflow patterns

    ReAct, router, planner-executor, evaluator-optimizer, supervisor-worker and deterministic workflow boundaries.

  3. 10:45

    State, context and memory

    Conversation state, workflow state, long-term memory, context selection, data lifetimes, poisoning and deletion policies.

  4. 13:15

    Durable execution

    Checkpoints, resumability, retries, idempotency, compensation, human interrupts and failure recovery.

  5. 14:15

    Multi-agent trade-offs

    Specialization, handoffs, shared state, communication overhead, coordination failure and when not to use multiple agents.

  6. 15:15

    Beyond vibe coding

    Requirements, repository structure, architecture decisions, unit and integration tests, static analysis, CI, dependency pinning and sandboxed execution.

  7. 16:00

    Lab 2 — productionize the agent Lab

    Add explicit state, checkpoints, idempotency, retries, human review and tests to a deliberately fragile starter implementation.

Day output A restartable, testable agent workflow with explicit state, failure handling, review gates and a maintainable repository structure.

Day 3

09:00–17:30

Security, evaluation, governance and deployment

Prove what the agent can do, constrain what it may do and document how it is governed.

  1. 09:00

    Threat modelling

    Assets, identities, trust boundaries and data flows; goal hijacking, prompt injection, tool misuse, privilege abuse and memory poisoning.

  2. 10:00

    Guardrails and validation

    Input, tool-call, tool-result, output and trajectory validation; sandboxing and safe failure.

  3. 10:45

    Agent evaluation lab Lab

    Task success, tool selection, argument correctness, side-effect correctness, trajectory efficiency, robustness and adversarial cases.

  4. 13:15

    Governance evidence

    System inventory, intended purpose, ownership, risk classification, approvals, monitoring, changes, incidents and human oversight.

  5. 14:15

    Standards and regulation

    NIST AI RMF, ISO/IEC 42001 and 23894, EU AI Act responsibilities and the OWASP Top 10 for Agentic Applications.

  6. 15:15

    Operations and deployment

    Secrets, workload identity, network policy, observability, budgets, model routing, rollback and incident response.

  7. 16:00

    Capstone red team Capstone

    Attack another team's agent, remediate findings and finish the technical and governance evidence package.

  8. 17:00

    Demonstrations and review Capstone

    Demonstrate controlled behaviour, evidence, unresolved risks and a deployment recommendation.

Day output A governed agent prototype with evaluation evidence, security traces, risk register, tool inventory and deployment recommendation.

Labs

Four deliverables, each one the input to the next.

01
Contracts and MCP Typed agent, safe tools, local MCP server, permission matrix and human approval.
02
Durable orchestration Explicit state, checkpoints, retries, idempotency, review gates and repository tests.
03
Evaluation and red team Trajectory dataset, task and tool metrics, adversarial cases and remediation evidence.
04
Governed capstone Operational agent, risk register, tool/data inventory, trace evidence and deployment decision.

Capstone specification

  • Documented intended purpose, users, exclusions and autonomy boundary.
  • At least three typed tools with explicit errors and separate read/write permissions.
  • At least one reusable skill and one MCP server or MCP-exposed capability.
  • State, maximum-step and cost budgets, safe termination and resumability.
  • Human approval for sensitive actions and idempotency for side effects.
  • A minimum 20-case trajectory evaluation set with normal, failure and adversarial scenarios.
  • Trace collection, tool and data inventory, risk register and incident/rollback procedure.
  • A deployment recommendation: approve, approve with conditions or do not deploy.

Stack

The tools, and why each one is in the room.

Typed agent layer
PydanticAI Typed dependencies, tool schemas, output validation, approvals, MCP integration and evaluation-friendly design.
MCP implementation
Official MCP SDK / FastMCP Builds a standards-based server and exposes protocol concepts directly.
Orchestration
LangGraph Makes deterministic and model-driven steps explicit and supports persistence and human interrupts.
Observability
OpenTelemetry-compatible tracing Vendor-neutral traces for models, tools, workflows, latency, costs and errors.
Testing
pytest + typed fixtures Validates deterministic code, contracts, tool results and regression scenarios.
Security and policy
Sandbox + explicit allow-lists Separates model decisions from credentials, network access and side effects.

Discussed, not taught hands-on

  • OpenAI Agents SDK is discussed for managed turns, tools, handoffs, guardrails, sessions and built-in tracing.
  • Microsoft Agent Framework is discussed for enterprise workflows, typed executors, state management and explicit multi-agent orchestration.
  • PydanticAI graph and durable-execution integrations can replace LangGraph; the learning objective is explicit state and recovery semantics, not one framework.
  • Crew-style multi-agent frameworks are not the default because coordination complexity obscures contracts, security and evaluation.

Logistics

Who it is for, and what it needs.

Primary audience
Software and AI engineers, solution architects, technical product owners, platform engineers, security specialists and governance practitioners who build or review agentic applications.
Prerequisites
Python, APIs, JSON schemas, Git and basic LLM prompting. Familiarity with asynchronous code and testing is helpful. Course 1 or equivalent LLM application experience is recommended.
Class size
12–20 participants per instructor; a teaching assistant above 16, or when participants have limited software-testing experience.
Conditions for the schedule
  • One capstone codebase for all three days; every new concept improves the same system.
  • PydanticAI and the official MCP/FastMCP tooling for core labs, with LangGraph introduced only for explicit durable orchestration.
  • OpenAI Agents SDK and Microsoft Agent Framework are framework comparisons, not additional participant implementations.
  • Mock tools and synthetic data; no workshop agent receives production credentials or unrestricted external side effects.
  • One multi-agent pattern is taught as a paper or whiteboard design exercise. Single-agent reliability is the practical priority.
  • A deliberately fragile starter agent is provided so participants focus on engineering controls rather than UI and boilerplate.

The workshop produces a governed prototype and evidence package. It does not constitute legal advice, ISO/IEC 42001 certification, a penetration test or approval for autonomous production operation.

Version 1.0 · framework review date 1 August 2026

Book a training

Tell me which course and roughly when. You get a reply from me, not a sales sequence — dates, a quote, and an honest answer if the course is a poor fit for what your team actually needs.

Goes to my own server and straight to me. No mailing list.