Energy optimisation sounds like specialist work for a few hot loops. GreenCode's Constitution research applied one method across 45 algorithmic problems in six programming languages.
The fix you can use today
Give your team (or your AI agent) a ranked list of anti-patterns to look for.
Measure a baseline with hardware counters, fix, and re-measure.
Keep only the changes that save energy and pass every test.
GreenCode researchers found that an AI agent with energy rules saved 25.1% of the energy across 45 problems.
Tools that help
GreenCode Constitution skill (GreenCode researchers): open-source energy principles and a catalogue of 37 energy anti-patterns that an AI coding agent can follow to find and fix waste like this
GreenCode Constitution profiler (profile.sh) (GreenCode researchers): a script from the Constitution tooling that measures the energy of a command from processor counters, GPU sensors and an optional smart plug, and writes the result as JSON
green-languages (GreenCode researchers): a command-line tool that measures the energy of whole programs or marked sections of code, across languages
How GreenCode helps
GreenCode helps tackle this by publishing the method, the Constitution, for anyone to use. An AI agent profiles the code, fixes ranked energy anti-patterns, measures again and keeps only changes that save energy, leaving changes developers can review. More on this.
