Skip to main content

Hands-On evaluation scenarios

An Agent Router evaluation expressed as a sequence of hands-on scenarios. Each scenario follows one or more documentation guides, ends with a verifiable outcome, and receives a grade, so the evaluation produces evidence rather than impressions.


How to use these pages:

  1. Run the fast track first: it builds the organization, SSO, keys, traffic, teams, and budgets the graded sections assume, and pre-completes several scenarios (see the carry-over table).
  2. Then work through the graded sections in order; each section is a separate page and notes which evaluation categories it feeds.
  3. For each scenario, follow the linked guide, run the scenario, and check the verification.
  4. Grade the scenario Pass, Pass with gaps, or Fail using the rubric below, and note anything surprising (gaps, workarounds, documentation problems).
  5. Total each section and carry the results into the scorecard. The Installation and onboarding section applies to Self-Hosted Data Plane evaluations only; fully hosted evaluations (Service or Enterprise Fully Managed) start at First requests and developer onboarding. Scenarios marked (optional) depend on the evaluation scope.
Scoresheet document

For your convenience, this page can be downloaded as PDF or printed directly. Site navigation is omitted, the scoring table keeps its rows intact with the header repeated on every page, and the Grade and Notes columns leave room for handwriting.

Grading rubric

GradePointsDefinition
Pass2Scenario completed as documented; at most minor polish items.
Pass with gaps1Scenario completed, but the documentation was unclear or workarounds not in the documentation were needed.
Fail0Scenario could not be completed, or only partially; capability missing or non-functional.

On a printed scoresheet, mark the Grade column P, G, or F; the points are tallied in each section's subtotal.

Prerequisites checklist

Before starting, confirm the following:

  • Console access: sign-in works for the Agent Router Console of the evaluation environment
  • Admin Dashboard access: sign-in works with the initial admin credentials
  • At least one AI provider credential on hand (for example, an OpenAI API key)
  • Terminal or HTTP client available (curl, Python, Postman)
  • OpenID Connect (OIDC) identity provider (IdP) details: issuer URL, client ID, client secret, and an IdP administrator reachable during setup

For self-hosted data plane configurations:

  • A Kubernetes cluster meeting the prerequisites, plus cloud CLI access

Optionally, depending on the evaluation scenario:

  • Model Context Protocol (MCP) client installed (Claude Code, Cursor, or VS Code)
  • OpenTelemetry-capable observability backend for telemetry export testing

Evaluation sections

The ungraded Fast-Track Evaluation runs first and covers the end-to-end first week, from first access to an onboarded team. The graded sections follow:

Fast-track carry-over

Work done in the fast track counts here. Grades for fully covered scenarios can be claimed from fast-track evidence; partial rows list what remains.

Fast-track jobPre-completesCoverage
D0.1 Onboarding wizard9.1 Add a provider and enable modelsPartial: verify the disabled-model error separately
D0.2 Configure SSO8.1 Configure single sign-onFull
D1.2 Key and agent2.1 Make a first API call; 2.5 Connect a coding agentFull
D1.3 Analytics onboarding5.1 Monitor traffic and usagePartial: locate a specific fast-track request with its provider, tokens, and latency
D1.6 Hello-world budget6.4 Exhaust a test budgetPartial: convert the warn-mode budget to a hard cap and exhaust it
W1.1 Invite users8.3 Onboard a developer and issue keysPartial: key revocation still to test
W1.3 Teams and budgets6.3 Create a team budgetFull

Summary scoring

Count only the scenarios in scope for the evaluation (skip Installation and onboarding for fully hosted paths; skip scenarios marked optional that were not attempted) and compute the percentage of the applicable maximum.

SectionFeeds categoriesScenariosMaxScore
Installation and onboardingF, G612
First requests and developer onboardingG2510
Routing, resilience, and provider abstractionD714
MCP gatewayE48
Observability and auditC, A3510
Cost control and budgetsD2, D3918
Safety and data protectionA, B612
Identity and developer governanceF136
Models, providers, and projectsD1, G11122
Enterprise operations and complianceF2, F3, G1714
Total63126
PercentageFitTypical profile
90--100%Excellent fitNearly all scenarios pass clean; none fail
70--89%Strong fitMost scenarios pass; some documentation gaps
50--69%Acceptable fitScenarios complete, but with gaps throughout or a few failures
below 50%Not recommendedFailures on core scenarios

A Fail on any non-optional scenario caps the outcome at Acceptable fit, regardless of the percentage.

Reporting issues

When a scenario fails or a guide does not match product behavior, record:

  1. Scenario ID and the guide followed
  2. Expected behavior per the documentation
  3. Actual behavior, with the exact error message or screenshot
  4. Environment: deployment path (Service, Fully Managed, Self-Hosted), browser, and OS

Share the record with the Tetrate contact for resolution, and grade the scenario on what was achieved, not on the promise.