Sample data. These figures are not a customer bill.Learn more
parezenparezen
Devbox Agents
Team · Sample · cloud
Home
  • Get startedSoon
  • Audits
  • Overview
Analyse
  • Spend
  • Cost per taskLock
  • Agents
  • Model comparisonSoon
  • Budgets
  • AlertsSoon
  • Reports
  • PR cost checksSoon
  • AdvisorsSoon
  • Spend analysis
Optimise
  • RecommendationsSoon
  • Routing policiesSoon
  • Shadow testsSoon
  • CachingSoon
  • TrimmingSoon
  • BatchSoon
  • Waste detectorSoon
Gateway
  • SetupSoon
  • ProvidersSoon
  • ModelsSoon
  • API keysSoon
  • DeploymentsSoon
  • PlaygroundSoon
  • LogsSoon
Savings & billing
  • Savings history
  • Savings ledger
  • Bill match
  • Billing
  • Invoices
Settings
  • Data & privacySoon
  • OrganisationSoon
  • ProjectsSoon
  • TeamSoon
  • RolesSoon
  • SSOSoon
  • Audit logSoon
Plan: Team · Sample ↗
DocsHelp

Sample data. Not a customer bill.

Devbox Agents/Routing policies/Automatic optimisation

Automatic optimisation

Planned

Policy-driven auto-apply with guardrails, approvals and rollback.

Included with Scale

Automatic optimisation is plan-gated in this sample. The preview stays visible.

Compare plans
Policy-driven
Automatic optimisation only applies a change the route policy already allows. Quality switches still need a passed shadow test.

Guardrail

$0.00$0.00

Auto-apply stops at 10% of the organisation soft budget.

Shadow gate

A quality change cannot auto-apply until its shadow test passes.

Rollback window

24h

A person can roll a change back inside this window. The log keeps the reason.

Routes on auto

Only these policies have automation set to auto.

No route is on auto. Suggestions stay in the inbox.

Approvals queue

Open recommendations. Enable still respects the shadow gate.

  • Right-size code review to GPT-4.1 mini

    Code review agent

    $700.00est.open
  • Kill the agent loop and retire the stale test key

    Agent loop runner

    $75.93est.open

Rollback log

No rollbacks in this sample.