Agentic AI · Advanced
Agentic AI Engineering
Agents that plan, use tools, remember and coordinate — with supervision, budgets and auditability engineered in from the first commit.
- Level
- Advanced
- Mathematics depth
- Essential
- Engineering depth
- Systems
- Modality
- Cohort-based
- Duration
- Announced per cohort
- Status
- Open for inquiry
Audience
Who this is for
- Engineers building autonomous workflows
- Platform teams designing agent runtimes
- Technical leads evaluating where agency pays off
Career paths
Prerequisites
- — Production software experience
- — LLM engineering fundamentals
Outcomes
Skills acquired
- Design agent systems with explicit action spaces and budgets
- Evaluate agents on task success, cost and safety
- Ship autonomy progressively with audit trails
Tools used
Curriculum Architecture
Module progression
Expandable, visual, ordered. Each module is a prerequisite-aware step, not an isolated video.
- 01Agency: When Autonomy Pays
- 02Tool Calling & Action Spaces
- 03Planning Loops & Decomposition
- 04Memory Architectures
- 05Multi-Agent Coordination
- 06Supervision, Policy & Kill Switches
- 07Agent Evaluation: Success, Cost, Safety
- 08Tracing & Auditability
- 09Rollout: Shadow Mode to Staged Autonomy
Projects
- A supervised agent completing a multi-tool workflow
- An evaluation suite with adversarial cases
Assessment philosophy
Assessment is engineering review: written error analyses, measured system behavior, defended design decisions. We evaluate whether you can explain and justify what you built — because production will.
Stack position: Agents → Systems.
FAQ
Frequently asked questions
Do I need a mathematics background?
It depends on the program. Foundation-tier programs start from the mathematics itself; advanced tiers list working linear algebra as a prerequisite. The Mathematics for AI program exists precisely to close that gap.
Is this a bootcamp?
No. CAS Studies is an engineering institute. Programs are built around architectures, derivations and projects with written error analysis — not tutorial replays.
How long does a program take?
The two diploma tracks run on fixed lengths — AI Architectural Engineering spans 18 months, AI Application Engineering spans 1 year. All other program durations are announced per cohort, by modality.
Will I build real systems?
Yes. Every program ends in projects that resemble production work: evaluated models, grounded answer systems, supervised agents — with measurement, not vibes.