Agentic Systems Engineering
Engineers building systems that act on their own, and the leads accountable for what those systems do unsupervised.
Length
7 weeks, part-time
Commitment
~6 hours per week
Cohort
12 live sessions, 20 seats
What this track assumes
AI Engineering certification or equivalent production experience with LLM systems.
What you cover
7 modules
Each one is worked through live, then built on between sessions.
- 01What makes a system agentic — and the case for the workflow you already have
- 02Architecture patterns — loops, routers, orchestrator-worker, and the cost of multi-agent
- 03Tool design and MCP — interfaces built for a model rather than a human
- 04Context engineering and memory — the scarce resource nobody budgets
- 05Bounded authority — permissioning, reversibility tiers, human-in-the-loop, injection
- 06Trajectory evaluation — replay harnesses, step and cost budgets as assertions
- 07Operating one — sandboxing, durable execution, circuit breakers, and how to stop it
You build it, then you defend it.
There is no exam and no pass for attendance. Some people do not pass first time.
The project
A working agent with a documented authority boundary and a replay-based evaluation harness, plus a written incident plan for the three ways it could go wrong that you consider most likely.
Read first
Some of this is free
The knowledge library covers a good deal of the same ground. Start there, and pay us only once you have decided the reviewed version is worth it.
Agent Architecture Patterns
Single loop, prompt chain, router, orchestrator-worker, parallel fan-out and multi-agent. What each pattern is genuinely for, the coordination cost that multi-agent quietly reintroduces, and a selection table you can argue from.
Context Engineering And Agent Memory
Context is a scarce, expensive, actively managed resource rather than a place to put everything. Working versus persistent memory, what compaction loses, sub-agent isolation, and why long-running agents degrade.
Designing Agents With Bounded Authority
The design question for an agent is not which model it uses but what it is permitted to do. Authority boundaries, idempotency, blast-radius limits, prompt injection as a live threat, and audit trails that hold up.
Evaluating Agents
The unit of evaluation is a trajectory, not a response. Outcome versus trajectory assertions, step and cost budgets as first-class checks, replay harnesses, and why an agent that succeeds expensively has still failed.
Other tracks
The rest of the technical family
AI Foundations
6 weeks, part-time
People who already use these tools daily and want to build with them — analysts, product people, and engineers early in their careers.
AI-Native Delivery
5 weeks, part-time
Teams adopting AI-assisted engineering who want the throughput gain to survive contact with review and production.
AI Engineering
8 weeks, part-time
Engineers building LLM applications, retrieval systems and agents who need them to hold up in production.
Physical AI
7 weeks, part-time
Engineers moving from software-only AI to systems that act in the world, where being confidently wrong has consequences you cannot undo.
Web3 & Smart Contract Security
10 weeks, part-time
Engineers moving into contract development, and teams preparing a protocol for audit and mainnet.
Mobile Delivery
5 weeks, part-time
Mobile teams whose release cadence is set by store review rather than by their own decisions.
Take Agentic Systems Engineering.
6 weeks, 12 live sessions, 20 seats, priced by region from $450. Places in the first cohorts are arranged directly.