Let agents ship change.
Keep the approvals.
Coding agents open most of your changes now. Traffical gives them a governed path — declare, scaffold, propose, read the evidence — and keeps the calls that need a person with a person.
The problem
Your agents are fast, tireless, and have no memory of last quarter's incident.
An agent can open a pull request that changes a discount, a ranking weight, or a system prompt in minutes. What it can't do is know that pricing changes need sign-off, that refund_rate is the guardrail that matters, or that the same idea was tried in March and reverted.
So teams do one of two things. They let agents ship and discover the damage in a weekly review — or they gate everything behind a human, and the velocity they bought evaporates.
Neither is a governance model. Both are a missing layer.
# agent, Tuesday 02:14 git commit -m "tune discount 10 → 20%" # no plan, no guardrail, no canary # margin drops 6% for 3 days # human, Friday standup > "revenue looks weird, anyone know why?" > "which change was that even?" > "who approved it?" # nobody. that's the problem.
What the agent does
One MCP server. The agent works the same surface a person does.
The agent has real capability: it declares parameters, wires them into surfaces, states intent, resolves a measurement plan from your certified protocols, and reads back the evidence at every phase. It writes the readout, flags the anomaly, and drafts the decision summary.
What it does not get is the ability to invent the metric or the threshold. Plans resolve from protocols your data team certified. If no certified protocol covers the change, traffic is blocked until a person approves the metrics and guardrails.
- Intent is mandatory — the agent can't create a change without stating what it's for.
- Risk is computed — from surfaces and bindings, not from what the agent claims.
- Evidence is bound — a proposal carries the snapshot it decided on, plus an expiry.
- Gates re-run at execution — approval never exposes traffic on stale evidence.
// 1 — declare the parameter traffical.parameters.create({ key: 'checkout.discount_percent', type: 'number', default: 10, surfaces: ['checkout'], }) // 2 — scaffold the change (intent required) traffical.changes.create({ intent: 'Increase checkout revenue by testing' + ' a more aggressive discount.', objective: { metric: 'revenue_per_session', direction: 'increase' }, }) // ← risk: medium (backend · decision binding) // ← template: canary → experiment → rollout // 3 — resolve the plan from certified protocols traffical.plans.resolve({ changeId }) // ← Checkout Commercial v3, Pricing Safety v2 // ← 3 guardrails (2 blocking) · needs approval // 4 — propose, don't execute traffical.changes.propose({ transition: 'start' }) // ← proposal pending human approval
What the human owns
Fewer decisions, each of them consequential.
Certify the protocols
Which metrics must be measured, which guardrails apply per phase, what minimums gate advancement. Versioned and snapshotted onto every change that uses them.
Pre-align the thresholds
Ship at X, stop at Y, discuss at Z — agreed before the change runs, so the readout doesn't become a negotiation.
Approve what propagates
Promoting a winner into the product default is always a human checkpoint. Strategy, taste, ethics, and close calls stay with people.
| Agent action | Autonomy | Why |
|---|---|---|
| Pause a phase | Direct | Safety actions are never gated on risk class. |
| Revert a phase | Direct | Stopping harm is always cleared. |
| Reduce exposure | Direct | Shrinking blast radius needs no approval. |
| Start traffic | Direct if low risk + certified plan | The only auto-approval cell. Anything else waits. |
| Expand exposure | Direct on low risk only | Medium and above become proposals. |
| Advance a phase | Proposal by default | New changes default to propose. |
| Promote a winner | Always a proposal | Writing a product default is a mandatory human checkpoint. |
One queue, whoever proposed it
Agent proposals, monitor recommendations, and teammate requests land in the same place.
Every row carries the evidence it was decided on and writes a decision record when it resolves. The next agent in the seat reads that log before it proposes — which is how the platform stops repeating March's mistake.
Keep reading
The patterns behind this page.
Give your agents room to run
And your team the guardrails, evidence, and audit trail to stay confident while they do.