Write your awesome label here.
Design agentic systems that finish the task on fewer steps, fewer tokens and less energy.
One completed task as the unit, eleven design levers, grounded in SCI for AI. From whether the agent is needed at all, through decomposition, tool surface, context, retrieval, termination, routing, failure and placement, to proving the change — plus an optional lab where you watch the number move, and a capstone on one of your own features.
10-12h
13
30 questions
80%
Certification
Designing Green Agentic Systems
How the course works
Framework-neutral
The levers apply whatever you build on. One worked implementation illustrates them; nothing depends on a particular agent framework.
One system throughout
The Northbridge support-triage agent, at 4,200 tickets a day, carries every worked example, every worked answer and the lab.
An optional lab where the numbers are live
Ten exercises against a running agent; the nine with worked fixes take the baseline from 2.925 to 0.362 gCO₂e per completed task. Every figure printed in the module is an output of the code that ships.
What this course helps with
The loop you did not need to build
Much of what an agent spends is a deterministic process wearing a loop — steps that were known in advance, rediscovered on every request. Module 2 asks for the number instead of the opinion.
Consumption that accumulates per step
Context that grows every turn, tool definitions re-read, retrieval that returns more than it needs, retries that repeat a step with its whole accumulated context. Energy, and cost, rise together.
A figure you can show
Energy and carbon per completed task, with the boundary, method and date recorded — so the reduction can be checked rather than asserted.
Who this is for
- Architects designing agentic systems and developers building them
- Teams putting an agent into production and answering for its cost and footprint
- Platform engineers setting defaults for agents across several teams
- Assumes working familiarity with LLM applications; no measurement background required
Related courses:
For how to obtain the numbers this course asks you to move, see SCI for AI Practitioner: The Measurement Lab. For fleet-level operations and placement policy, see GreenOps Practitioner. For the water dimension of a placement change, see Software Water Essentials.
What you will work with
The agent decision test
Sample real runs, count distinct sequences, cost the deterministic version, and write the benefit sentence for whatever remains.
The accumulation curve
How context, tools and retrieval compound across a run, and where compaction, projection and scoping cut in.
The lab harness
Prefill and decode reported separately, along with steps, tool calls, retrieved chunks, retries and cost per completed task. A Software Carbon Intensity (SCI) figure is calculated from stated coefficients.
What you will be able to do
Course Lessons
The full course
01
Why Water, and Why You
Software feels dry, but the buildings it runs in use water for cooling, the electricity it consumes was made using water, and the hardware was manufactured with it. This module shows those three connections and closes the gap between the people who can see the water and the people who change the software.
module-01
02
The Four Layers: building, electricity, hardware, and the stress conversion
This module gives the three ways software uses water their proper names, as the draft SWI specification uses them, and adds a fourth layer that converts litres into how much each litre matters. It ends with the only line of arithmetic in the course.
module-02
03
Consumption and Withdrawal: used up vs borrowed
Water figures come in two kinds, and confusing them is the most common mistake in reading them. This module teaches the distinction between water used up and water borrowed and returned, and the rule that the two are never added together.
module-03
04
Reading a Water Number
This module teaches no calculations. It teaches how to look at any water figure, whether a provider report, a news headline or a colleague’s slide, and know what it does and does not say.
module-04
05
Stress-Adjusted Water: a liter is not a liter
The same liter counts for more where water is scarce and for less where it is plentiful. This module turns that idea into arithmetic using a published factor per place, giving the conversion layer its full treatment at foundation depth.
module-05
06
Small Things That Save Water
The earlier modules built a vocabulary; this one turns it into actions small enough to take this week, organised by role. None of them needs a water meter, a budget or permission to run a project.
module-06
07
Final Assessment
A final assessment of 12 questions - 80% to pass, 30 minutes, retake available.
Final Assessment
Assessment & Certification
Time to complete