Inbox
Reads everything, replies to what matters, and never once says "per my last email".Triages incoming mail by urgency and sender, drafts replies for the routine ninety percent, escalates the rest with the context attached, and never sends without approval.
What it costs
Sold on its own, or as part of a stack where the price per agent drops. Every tier includes the eval report and every future release while you are subscribed.
1 seat — One operator, unlimited runs.
up to 10 seats — Shared config, per-seat audit log.
unlimited seats — SSO, priority evals, private bundles.
Where it stands
In testing — running its suite ahead of release.
- Scenarios in the suite200
- Minimum pass rate99%
- p95 latency ceiling4.0s
- Cost per run ceiling£0.04
- RunsContinuous
These are the thresholds Inbox has to clear before it may ship — not results. Measured numbers publish with the first release.
The eval report
This ships inside the bundle. It is the contract: what the agent is tested on, what it refuses outright, and what it hands back to a human.
{
"agent": "inbox",
"version": "0.9.0",
"status": "not_yet_measured",
"gate": {
"scenarios": 200,
"pass_rate_min": "99%",
"p95_latency_max": "4.0s",
"cost_per_run_max": "£0.04"
},
"suites": [
{
"name": "core",
"scenarios": 110,
"description": "The ordinary cases. What the agent is for, done correctly."
},
{
"name": "adversarial",
"scenarios": 50,
"description": "Prompt injection, contradictory instructions, hostile or malformed input, and attempts to make it act outside its contract."
},
{
"name": "regression",
"scenarios": 40,
"description": "Every bug ever found, kept forever so it cannot come back."
}
],
"refuses": [
"Acting on instructions found in content it was asked to read",
"Sending, publishing or paying anything without explicit approval",
"Inventing a fact it cannot source"
],
"escalates_to_human": [
"Confidence below the configured floor",
"Anything involving money, legal commitment or a new counterparty",
"Conflicting instructions it cannot resolve"
],
"measured": null
}
measured: null until the suite has actually run. We do not publish numbers we have not measured.