Skip to main content
// REVENUE_AGENTS

Outreach

Sends the first email, and the seven follow-ups you'd feel weird sending.Runs multi-step outbound sequences, personalises from your research notes, detects replies and out-of-offices, and stops chasing the moment someone answers.

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.

Solo
£49/mo

1 seatOne operator, unlimited runs.

Team
£99/mo

up to 10 seatsShared config, per-seat audit log.

Business
£199/mo

unlimited seatsSSO, priority evals, private bundles.

Or take the whole AIOS

Where it stands

In testing — running its suite ahead of release.

Release gate
  • Scenarios in the suite180
  • Minimum pass rate98%
  • p95 latency ceiling4.0s
  • Cost per run ceiling£0.04
  • RunsScheduled

These are the thresholds Outreach 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.

eval_report.jsonv0.9.0
{
  "agent": "outreach",
  "version": "0.9.0",
  "status": "not_yet_measured",
  "gate": {
    "scenarios": 180,
    "pass_rate_min": "98%",
    "p95_latency_max": "4.0s",
    "cost_per_run_max": "£0.04"
  },
  "suites": [
    {
      "name": "core",
      "scenarios": 99,
      "description": "The ordinary cases. What the agent is for, done correctly."
    },
    {
      "name": "adversarial",
      "scenarios": 45,
      "description": "Prompt injection, contradictory instructions, hostile or malformed input, and attempts to make it act outside its contract."
    },
    {
      "name": "regression",
      "scenarios": 36,
      "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 We do not publish numbers we have not measured.