AGENTS · THE GOVERNED RUNTIME

AI agents that propose. You approve.

AI agents for business shouldn’t mean handing your company to a black box. Command’s agents run on a governed runtime — versioned charters, per-agent budgets, step-level run traces — and every action they want to take arrives as a proposal a human confirms.

Book a demo View plans
CHARTER · RUN · TRACE · CONFIRM
HUMAN-IN-THE-LOOP FIRST

Autonomy is earned, not assumed. Every agent starts at propose-and-confirm, and its autonomy dial climbs only as it earns trust on your account — deliberately decoupled from how powerful the model is. A smarter model doesn’t get more rope. A proven agent does.

HOW IT WORKS

From Run now to a decision on the record.

Autonomous AI agents with human approval, end to end — a background runtime does the work; the decisions stay yours.

1

An agent gets its charter

You request an agent from the shelf; the Vevang team deploys it white-glove — never auto-provisioned. Its charter names what it may read, what it may propose, its playbook, and its budget.

2

You press Run now

The run is queued and a background worker daemon drives it — real model reasoning with no request timeout. Safety gates are checked at enqueue and re-checked when the worker claims the run.

3

Every step lands on the record

The run trace is an append-only timeline: what the agent read, what it reasoned, what it proposed. Each proposed action drills through to the actual artifact — payload, autonomy, decision.

4

You decide

Proposals wait in the escalations desk — money-out loudest, priority-then-age. You answer, confirm, or dismiss on your own session. Nothing applies until a human says so.

THE MACHINERY

Governance is code, not a policy PDF.

Every mechanism below is enforced by the runtime itself — checked before an agent runs, re-checked when the worker claims the run, and written down where you can read it.

CHARTERS

Versioned, append-only

An agent's rules are a versioned constitution — changes create a new version, never edit history. Runs pin the exact version they executed under.

BUDGETS

Per-agent spend caps

Every agent runs inside a budget. A run that would exceed it is refused before it starts — not billed after the fact.

TRACES

Step-level run records

Append-only timelines of every read, reasoning step, and proposal — errors unmissably red, each action drilling to the real artifact.

MONEY-OUT

Locked to propose-only

The eight money-out action classes are platform-locked at the database: an agent may propose, a human must confirm — forever.

And one discipline over all of it: one universal product. Every agent is the same platform configured to your business — never bespoke code written for one client. When config can’t do something, the platform gains a capability that serves everyone. Deeper guarantees — kill switches, isolation, the audit trail — live on the trust page.

THE DIFFERENCE

An AI agent platform for business, not a bot with your passwords.

Most “AI agents” are a prompt and a loop. The difference between that and something you’d let touch your business is governance.

AN UNGOVERNED BOT

What most tools ship

The prompt is the spec — rules change silently, nothing is versioned
Acts first; you find out from the consequences
No step record — when it goes wrong, there's nothing to read
Autonomy set by a checkbox, granted before it's earned
Bespoke scripts per customer that rot the day the developer leaves
A GOVERNED AGENT

What Command runs

A versioned charter — every run pins the exact rules it executed under
Proposes with evidence; a human confirms before anything applies
Append-only step traces that drill through to the real artifact
Autonomy earned with trust on your account, decoupled from model power
One universal platform, configured — every capability serves every tenant
THE DESK

When an agent needs a human, it asks.

Agents don’t guess past their charter — they escalate. Every packet an agent raises lands on one decision desk, ordered by priority then age, with anything touching money-out the loudest thing on the screen. You answer, resolve, or dismiss — and confirm proposed actions on your own session, never the agent’s.

That’s the covenant in daily practice: the agents do the work; the judgment calls come to you, with the evidence attached.

ESCALATION

Pipeline agent — 3 deals stalled past 14 days. Proposed: follow-up drafts for each, ready to send.

evidence: run trace · step 6 of 6 · charter v7 · budget 41%
Confirmed on the human session — never the agent’s.
QUESTIONS

Good to know.

Each agent operates under a charter that names the data it may read and the tools it may propose — sourcing look-alike customers, drafting follow-ups, flagging stalled deals, raising compliance reminders. Everything an agent wants to change arrives as a proposal with the evidence attached; a human confirms it, and only then does the system apply it. Anything in the money-out family is flagged human-confirm at the platform level.

Agents that work for you —
and answer to you.

See the governed runtime live on your own questions — watch a run trace unfold, open the escalations desk, and decide if this is how you want AI working inside your business.

Book a demo View plans