ES · EN
Q · Agent Board
Jose Antonio Vilar · QMetrika Labs
how it works

From installing to governing

What adopters actually live through: from launching agents blind and at uncontrolled cost, to watching them work by department, approving only what has effects, with budget and audit — and having that control compound as capital.

highlighted step = the moment of governance (human decision)

1

Install

One command. Zero dependencies (Python only). You have it running in 2 minutes.

2

Configure

With /setup or a template, define your specialists and departments.

devlegalfinanceIT supportgenomics
3

Start and connect

Bring up the broker and plug in any LLM.

ClaudeGeminiOpenAIlocal ~free
4

Observe the swarm

Each agent is a live card, grouped by department (lanes), with its tokens and cost in €.

5

You govern

Every operation with effects stops at Needs Input and waits for your Approve or Deny. The decision is made by a policy in code, not by the model.

6

Control cost

Budgets in €: local barely counts; the expensive model that goes over falls into «⚡ No budget».

7

Audit

Every decision lands in a verifiable chain, tamper-proof.

8

Compound capital

The residue becomes an asset: captured human judgment, data for evals, and cost per task trending down — your moat grows.

▶ See the demo Capital board Home