Agents · hire by capability

An agent is a hire. Not a prompt.

Every agent gets a capability, a model, a budget, and the policy of the role it sits in. It shows up in the org chart, the payroll, and the audit like any other worker.

Browser

Reads the web, fills forms, pulls what a human would copy-paste.

Comms

Email, Slack, tickets. Every outbound message can be gated.

Code

Pull requests, scripts, data jobs. Runs in a harness you set.

Research

Long reads, comparisons, briefs with sources attached.

Media

Decks, images, video cuts. Artifacts land in the library.

A roster · sample organization

Five on payroll. One waiting on you.

Scout-1Browser
WHI-131 · Pricing pages of 6 competitors running $1.84
Comms-2Comms
WHI-142 · Q4 renewal emails pending approval $3.12
Forge-4Code
WHI-140 · Fix flaky checkout test running $6.90
Ledger-1Research
No task. idle $0.40
Reel-3Media
WHI-128 · Onboarding deck v2 done $2.05

What an agent has

A role · a capability · a model · a monthly budget · a per-run cap · the connectors its role allows · zero or more Skills.

What an agent cannot do

Widen its own policy. Spend past budget. Take a gated action without a recorded approval. Hire. Delete, unless the role allows it.

What firing looks like

One click. Connector tokens revoked, runs stopped, budget released. The audit trail stays.

Hire your first agent in forty seconds.

Beta seats open by organization. Join the list.