Customer stories
Agents in production, with the numbers.
What each team built on oncell, what it costs per customer, and the moment the runtime made an agent better.
JustCopy builds a small business its website, then the owner launches agents to run it: one that answers customers now, one that works in the background every day. oncell is the runtime for both, one agent per business, metered per business.
OpenCrew is the HQ where AI agents work as a team. Every agent in a crew runs in its own oncell cell behind OpenCrew's HQ: its own tools, its own budget, its own run log, paused at no cost when idle.
What the stories illustrate
Each story is a worked example of one part of the platform. The posts below take one idea each from the stories and show the mechanism in the docs.
Cost per customer
What it costs to run a customer-facing agent per conversationJustCopy runs one agent per small business at $0.0006 a conversation, under a $1 per day budget. How the number is measured, and what a $9.99 plan covers.
Agent evaluation
The run that became a test: turning production conversations into evalsA plumber's agent invented a price. The conversation was already a run in the log, so it became an eval. How promoted runs guard every change to an agent.
Multi-tenant agents
One agent, one cell: isolating a crew of agentsOpenCrew runs every agent in a crew in its own cell. The tool allowlist is the cell, the blast radius is one agent, and shared work happens on forks, not turns.
Agent runtime
Sync and async agents: the two kinds every business launchesEvery business JustCopy serves launches two agents: a front desk that answers now and a follow-up that works every morning. Why a schedule is durable intent.