A path with a point
Learn the system, not the buzzwords.
Start with the machinery engineers already know, then add models, context, tools, agents, and protocols one honest layer at a time.
From Automation to Agentic Systems
A practical journey from rules, workflows and evidence to a small, bounded troubleshooting agent. You will understand every moving part because you build it in public.
You will leave with: a deterministic incident investigator and a solid mental model for where models belong.
7 lessons
Begin →
Agent Systems, MCP and A2A
The good stuff: agent roles, delegation, MCP, A2A, capability boundaries and how to make a multi-agent system understandable instead of merely impressive.
You will leave with: the ability to design and review a multi-agent system with clear ownership and evidence.
8 lessons
Begin →
Agents in Production
Observability, Kubernetes, OpenTelemetry, OpAMP, Grafana, Golden Signals, resilience and security for systems that have to earn trust in production.
You will leave with: a production-ready way to reason about reliability, operations and security around agentic systems.
9 lessons
Begin →
How this is taught
One evolving application. No blank-page homework.
The Engineering Troubleshooting Workbench begins as an ordinary Python investigation tool. Each journey adds one useful capability and leaves the previous behaviour visible, testable, and explainable.
Meet the Workbench →