Advanced · Software & ML engineers
Agentic AI for Developers
The builder's course on agentic AI. Learners move from single prompts to production-grade agents that plan, call tools, recover from errors, and ship without running up a runaway bill. Covers Assistants, MCP, LangGraph-style orchestration, and the guardrails every CTO will ask about.
3 hours
Verifiable certificate
25 languages
4 modules · 32 lessons
€29
/ seat
Ship autonomous systems that stay on the rails.
Hands-on labs
Tool-use patterns
Production guardrails
Includes 12 months access, certificate, and evidence trail. Cancel any time before your learner starts.
What you'll learn
Three concrete things every learner walks out with.
01
Design tools and schemas an agent can invoke without foot-guns.
02
Architect long-running agentic workflows with memory and checkpointing.
03
Stand up a lightweight eval and observability stack for agent deployments.
Curriculum
A short course that respects your team's time.
4 modules · 32 lessons · 180 minutes. Designed to complete in a single working session or stretch across a week.
01
From prompts to agents
7 lessons · 40 min
+
01
From prompts to agents
7 lessons · 40 min
Planning, tool use, and why most 'agents' are actually orchestrated pipelines.
02
Tools, MCP, and function calling
9 lessons · 50 min
+
02
Tools, MCP, and function calling
9 lessons · 50 min
Designing tools agents can't misuse, versioning schemas, and handling partial failures.
03
Memory, state, and long tasks
8 lessons · 45 min
+
03
Memory, state, and long tasks
8 lessons · 45 min
Episodic vs. semantic memory, checkpointing, and resumable multi-hour workflows.
04
Evaluating and shipping safely
8 lessons · 45 min
+
04
Evaluating and shipping safely
8 lessons · 45 min
Guardrails, budget caps, red-team scenarios, and the observability stack that catches regressions.
Outcomes
What your team will be better at by next month.
Agents that actually finish
Ship multi-step flows with retry, fallback, and clear completion criteria.
Tool-use that is safe by default
Tools agents can't accidentally misuse, with schemas and permission scopes baked in.
Production-grade observability
Traces, evals, and budget telemetry so nothing silently drifts or runs up a bill.
Verifiable certificate
Deterministic ID, third-party verifiable.
Evidence trail
Cited, timestamped, regulator-accepted.
25 languages
All 24 official EU languages plus English.
Private by default
Zero-retention mode, EU residency available.
More from the library
Pair it with something your team already asks for.
Agentic AI for Developers
Ready to train your team on this one?
Start with a single seat and grow into a team bundle, same dashboard, same evidence trail, either way.