Write your awesome label here.
Put green engineering guidance inside the agentic coding tools your teams already use.
Ten modules on building green agent skills: where they belong across the engineering lifecycle, how to design and build one to the standard, distributing a single source across tools, governing them, and evaluating whether they change what the tools produce.
7h 40m
10
30 questions
80%
Certificate
Building a Green AI Agent
How the course works
Built to the agent skills standard
Skills built to a standard and governed as such, rather than a prompt library.
Review as the highest-leverage point
One integration there influences every change that passes through it.
Worked examples and a capstone
Build and install, evaluate and measure, then design and evaluate your own.
What this course helps with
Guidance at the moment of decision
Green engineering guidance that arrives while the code is being written is followed more often than a standard that sits in a wiki.
One maintained source
Editor, review tool and pipeline carrying the same version, rather than drifting copies.
Evidence that a skill works
A way to check what the tools actually produce, rather than assuming the skill is effective.
Who this is for
- Architects and developers using agentic tools day to day
- Platform and developer-experience engineers who distribute tooling
- Engineering leads standardising practice across teams
Related courses:
For model training decisions rather than the coding loop, see Green AI for ML Practitioners.
What you will work with
The lifecycle map
Where a skill earns its place across design, development, testing, review, delivery and operations.
One source, many tools
Distributing the same guidance without forking it into divergent copies.
The evaluation
How to establish whether the skill changed the output.
What you will be able to do
Course Lessons
The full course
01
Where ML’s Footprint Is Decided
A model’s footprint is created twice: once when it is trained, and again on every inference it serves. This module sets the decision metric and the amortisation rule that every later module is judged against.
module-01
02
Reuse, Adapt, or Train: The First Decision
The largest reduction available on the training side is not to train, yet the question is usually settled by habit before anyone computes it. This module compares six routes to a working model and what to ask of a base model before inheriting its cost.
module-02
03
Sizing the Model and the Data Budget
How large a model, trained on how much data, sets the energy term more directly than any later choice. This module covers compute-optimal sizing and how architecture changes training and serving energy independently of parameter count.
module-03
04
Data Efficiency: What the Model Is Trained On
What the training tokens actually are changes both how many are needed and how good the resulting model is. This is the layer where the footprint lever and the quality lever most often point in the same direction, and this module is careful about where that alignment breaks.
module-04
05
The Training Run: Execution, Stopping and Waste
This module examines the compute that produces nothing: epochs past convergence, crashes without a checkpoint, and experiments that repeat work already done. Waste at this layer is invisible in a cost report, because a failed run and a successful one look identical on the bill.
module-05
06
Search and Evaluation: The Two Multipliers
Earlier modules reduce the cost of one run; this one addresses how many runs happen, which is usually the larger number. It covers search budgets, comparing strategies by cost per answer, and evaluation as a cost that recurs for the life of the model.
module-06
07
Hardware-Aware Training
Compute demanded is one quantity; how efficiently it becomes energy is another. This module covers precision, batch size, accelerator fit and utilisation as the conversion factor sitting between the two.
module-07
08
When and Where to Train
This is the one lever that changes carbon without changing energy, by moving a run to a different hour or region. Training is often a strong candidate, and this module covers the constraints that decide it, along with water, preemptible capacity and embodied allocation.
module-08
09
From Weights to Deployable Artifact
This module deliberately spends training cost once in order to reduce serving cost on every inference that follows. It covers parameter-efficient adaptation, post-training and compression, and the repayment calculation that decides whether the trade is worth making.
module-09
10
Lifecycle, Retirement and Disclosure
Retraining cadence multiplies the training footprint, and retirement is the point at which every amortisation estimate becomes a measured fact. This closing module covers cadence, drift, registry and model card records, disclosure duties, and the capstone footprint report.
module-10
11
Final Assessment
A final assessment of 30 scenario-judgement questions - 80% to pass, 60 minutes, retake available.
Assessment and certificate
Time to complete
Join the Pilot
The GSF Academy is currently in pilot. If your organization would like to enrol learners and issue GSF certifications to your teams, tell us a little about what you need and we'll follow up to discuss access, pricing, and enrolment.
Thank you.
We will be in touch shortly
We will be in touch shortly