Definitions for the terms Vocion uses, grounded in the framework's own docs and schemas.
The term covers two different things — a discovery directory of running agents, and a versioned source of truth for agent definitions.
Software that runs a team of AI agents as declared, versioned files applied to a database, with approvals and an audit trail built in.
A five-level scale, set per mission, for how much an agent may do without a human — from draft-only to self-improving.
A versioned set of default agents, skills, and playbooks shipped inside the framework that a workspace can pin, activate, and override without forking.
A workflow step that pauses a run in a review queue for a human decision before the run continues.
A named, whitelisted bucket of rules an agent reads, where corrections from past runs accumulate instead of turning into scattered prompt edits.
A single queue of paused workflow runs, missions awaiting review, and pending action proposals, with a REST API to decide each one.
A workspace-level file naming which proposed actions may auto-execute without a human, and the confidence threshold each one needs.
An audit row recorded on every workspace apply, plus a hash stamped on every run, so any agent output traces back to the exact files that produced it.
The open-source Agent Workforce Platform. AI coworkers you can trust with real work — running in your own AWS account, on a foundation your company owns.
MPL-2.0 · Self-hosted · Runs on AWS