Mandate · Issue Nº 1 · MMXXVI

Authority over every agent, every action.

The governed AI work control plane. Route missions, grant explicit mandates, seal every action — under one writ. Built for teams that can't afford ungoverned autonomy.

Join the Waitlist →See the system

$ mandate · session · sealed

$ mandate grant --to codex.research \
    --scope board.review \
    --ttl 72h
↳ writ #04812 · sealed

$ mandate audit --writ 04812
↳ 142 actions · 12 agents
↳ cedar://acme/governance/quarterly
↳ ratified by 3 of 3 directors

500+

Governed runs in production

Agents under policy control

Cedar

Policy engine — same as AWS

Services under one writ

I · Manifesto

Most software asks for permission.
Mandate grants it.

Authority

Every action carries an explicit mandate. Nothing happens in secret, nothing happens without scope.

Orchestration

One conductor over N agents. Codex, Claude, OpenCode, humans — all under the same writ.

Audit

Every decision is sealed and counter-signed. The log is the product, not a side-effect.

II · The System

Governed execution.
Not ungoverned speed.

Each capability is engineered for deterministic operations, risk control and transparent decision flow. Speed inside the guardrails your compliance team actually requires.

§ 01 · Mission

Mission lifecycle

Define objectives in natural language. Mandate decomposes them into traceable execution plans with explicit dependencies.

§ 02 · Runtime

Task DAG execution

Complex work as deterministic DAGs: parallel lanes, checkpoints, automatic reordering — never an opaque queue.

§ 03 · Approval

Approval gates

Risky actions pause at human checkpoints. Low-risk work flows on its own. No false approvals, no rubber-stamping.

§ 04 · Agents

Agent runtime

Specialized agents in isolated workspaces. Clear ownership, traceable side-effects, scope enforced by policy.

§ 05 · Context

Conversation intelligence

Multi-turn context preserved across channels. Follow-ups stay coherent, auditable, and inside the writ.

§ 06 · Audit

Full observability

Decisions, runs, costs and outcomes on a single timeline — designed for operations and compliance, not dev curiosity.

III · The Writ

Every action carries the mandate.

The writ is the agent's legal document: who was authorized, on what scope, for how long, under which policy, and who ratified. Nothing flows without it. Nothing is lost from it.

Underneath: Cedar (the same engine AWS uses), HMAC event log, per-run cost accounting, and an immutable audit trail.

Writ · MND-2026-04812

Quarterly review automation

Granted under cedar://acme/governance/quarterly · TTL 72h

Acme Corp
Tenant · prod-eu

Granted to

codex.research, claude.legal, opencode.sync

Scope

board.review · linear.write · github.draft

Constraints

no-delete · no-merge · approval ≥ L4

Ratified by

3 of 3 · directors signed

Actions

142 sealed · 03 pending · 0 revoked

Sealed · 14:08 UTC

Issued 2026-04-29 · MMXXVI

IV · Position

Not another IDE.
The control plane above your tools.

Mandate works alongside Cursor, Claude Code, Copilot, Codex — whatever your team already runs. It adds the governance layer those tools never ship.

Capability	[ Mandate. ]	No-code stacks	Ad-hoc scripts
Business-intent missions	● granted	partial	custom build
Task DAG orchestration	● granted	—	partial
Human approval gates	● granted	partial	custom build
Audit-ready run history	● granted	partial	custom build
Per-run cost accounting	● granted	—	—
Cedar policy engine	● granted	—	—

V · Design Partner Cohort

Where AI gets
its mandate.

Apply for the design-partner program. Direct input on product direction, weekly architecture office hours, and priority issue handling.

No spam · Design-partner updates only · Unsubscribe anytime

Mandate.