The vocabulary of agent execution infrastructure
The category invented a lot of words quickly, and vendors use several of them to mean different things. These are the definitions Promigence uses.
- Environment runtime
also called agent environment runtime, execution plane
- An environment runtime is infrastructure that builds, verifies, reproduces and forks the environment an AI agent runs inside, treating the environment itself as the product.
- Verified environment
- A verified environment is one that ran its own declared test command at build time, so it is known to work before an agent is placed inside it.
- Episode
- An episode is one environment's complete life, fork, execute, terminate, and it is the unit a quote and a spend cap are written against.
- Snapshot fork
also called warm fork
- A snapshot fork creates a new environment from an already-warm one that has finished installing and building, so it costs milliseconds rather than seconds.
- Warm start
- A warm start begins work in an environment where dependencies are installed and caches are populated, so the first command you run is the one you care about.
- Validity report
also called environment validity
- A validity report states, for one run, how many environments were verified, which failed, and whether each failure belonged to the environment or the task.
- Poisoned reward
- A poisoned reward is a training signal produced by a broken environment rather than by the agent's behaviour, so the model learns from an outcome that never happened.
- Burst capacity
- Burst capacity is how many environments a provider actually delivers when many are requested at once, which is often very different from its advertised latency for one.
- Flight recorder
- A flight recorder is a per-episode log of every command executed and every file diff produced, kept so a failed episode can be read rather than guessed at.
Run your own workload on it, free
Send a repo and the command you run against it, whatever that is: an eval suite, an RL rollout, a CI job, a queue of coding tasks. We build the environment once, run it a thousand times, and send back the timings, the failures and an exact price. Free, once, on your real workload.
- 1,000 runs of your own command, on your own repo
- What each one cost in wall clock, and anything that failed
- Whether a failure was your code or the environment
- An exact price for your real volume
Not ready to hand over a repo? Read the quickstart or check the numbers first.