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/Recommendations/Recommendation

Recommendation

Planned

Evidence, shadow scores, affected routes and the decision log.

1Right-size the modelopen
Open policy
Projected / month
$700.00est.
Right-size code review to GPT-4.1 mini
Ledger in range
—
Verified or realised lines for this route and lever. The projection above is not included.
Affected routes
1
prod

Evidence

What would have to be true before this counts as savings.

Shadow test scored 0.89 against a 0.84 bar.

Shadow test · 0.89 / 0.84Requests on this routeLedger

Projected versus spend

Dashed line is the baseline. Solid line is what the route actually cost. Neither line is a verified saving.

Affected routes

  • Code review agentprod

Decision log

Enable and Ignore are both recorded.

No decision yet.

Subscription terms
This organisation is not on the Performance option, so there is no savings fee to illustrate.