SerenQuantDocs
Sign up
Sign up
© 2026 SerenQuant. All rights reserved.
DocsPrivacyTermsStatusSupport
Docs
Documentation
Start here
Overview
Guide library
GuidesGetting Started: APIGetting Started: MCPAuth + Workspace ScopesAccount and Workspace ManagementMarkets WorkspaceMarkets Symbol WorkspaceMarket Guides and Beta ScopeFutures ReadinessResearch WorkflowResearch Workbench, Pipeline, and ExperimentsResearch Specialist MethodsResearch Context SurfacesBacktests Run LifecycleBacktests Run Detail and CompareStrategy Sweeps and OptimizerExecution WorkflowProviders and BenchmarkingSettings and Runtime ConfigAgent WorkbenchNews WorkflowDatasets WorkflowGlobal Language SelectionMFA Getting StartedMFA Recovery + Device LossMFA Trusted DevicesMFA API ReferenceLLM Market Analysis LoopStrategy Generation + Backtest LoopPromotion + Risk Guardrails
Reference
API ReferenceMCP Reference
Lifecycle
Changelog
  1. Docs/
  2. Guides/
  3. Providers and Benchmarking
Public docs

Guide: Providers and Benchmarking

Review provider inventory, benchmark evidence, route policy, and recommendation flow in the signed-in providers surface.

Signed-in workflow

What this guide covers

Use this guide when you need to understand how SerenQuant evaluates provider capability, benchmark evidence, and route policy before a provider becomes the default for a route family.

  • Treat /providers as a decision surface, not only an inventory page. Profiles, entitlements, capabilities, policies, and recommendations all interact.
  • Use benchmark runs and recommendation badges to validate the direction of a route policy before you change it.
  • Keep exports, route decisions, and usage evidence available so provider changes remain auditable.

Routes and surfaces

The provider page combines inventory, policy, benchmark, and evidence surfaces into one operating view.

/providers · profiles & entitlements

Profiles and entitlements

Review the provider profiles and account or entitlement context that determine what the workspace can use.

/providers · capability matrix

Capability matrix

Inspect coverage, quality tier, support flags, and enabled state across provider capability rows.

/providers · route policies

Route policies

Edit or review route-policy behavior that controls which provider is preferred for a route family.

/providers · benchmark runs

Benchmark runs

Use benchmark runs, result filters, and recommendation badges to evaluate provider quality and latency tradeoffs.

/providers · route decisions & usage

Route decisions and usage

Review recommendation outcomes, latest route decisions, and usage rows before treating a change as stable.

/providers · export & audit

Export and audit

Export the capability matrix and preserve the evidence trail around provider configuration changes.

Recommended provider decision loop

Use this loop to keep provider changes evidence-based instead of intuition-driven.

01

Inventory the provider surface

Start by confirming profiles, entitlements, and capability rows so you know what the workspace can actually route through.

02

Benchmark before changing defaults

Use benchmark results, coverage, latency, and drift metrics before treating a provider as preferred.

03

Adjust route policy deliberately

Change route policies only after the recommendation flow and route-decision evidence point the same way.

04

Export and review the decision trail

Capture exports, usage, and recent decisions so the provider change can be audited later.

Capability matrix controls

The capability matrix is where provider posture stops being abstract and becomes route-by-route operating reality.

quality tier

Quality tier and provider fit

The capability matrix lets you downgrade or upgrade quality expectations by route family. Read those selectors before changing a default provider.

availability

Enable and disable rows deliberately

Use enabled flags to control which capability rows can participate in routing. Disabled rows should reflect intentional policy, not stale config.

coverage scope

Scope, asset, and interval coverage

Each row carries provider, data kind, asset class, scope, and interval context. Validate that scope coverage matches the route family you plan to benchmark.

workspace posture

Entitlements and workspace posture

Keep the entitlement card beside the matrix in mind. A strong capability row is not actionable if the workspace cannot actually access that provider.

Route policy controls

The policy editor is where benchmark evidence becomes an actual routing change.

policy draft

Draft route-policy creation

Use the draft form to pin data kind, asset class, region, market segment, interval, and quality tier before you assign a primary provider.

fallback chain

Fallback chains and primary precedence

Set the primary provider and fallback chain together so route behavior is predictable when the preferred source is degraded.

best effort

Best-effort and enabled flags

Best-effort is a conscious tolerance decision. Pair it with enabled state so exceptions are explicit instead of accidental.

live policy table

Live policy rows

Review the existing policy rows after each change. They are the operational truth for what the router will actually do.

Benchmark and recommendation evidence

  • Use the benchmark panel's run selector, provider filter, and coverage or latency rows to decide whether a provider wins because it is actually better, not merely more recent.
  • Recommendation badges are strongest when the benchmark table, recent route decisions, and entitlement posture all point to the same provider.
  • Open the Why this decision drawer when route behavior is surprising. It summarizes top recommendation, recent route decisions, fallback chain, and cost pressure evidence.
  • Keep usage counters and recent route-decision cards in view after rollout so you can see whether the new policy behaves as expected under real traffic.

Example provider decision scenarios

Use these playbooks when provider benchmarking needs to translate into a governed routing decision.

winner selection

Promote a benchmark winner into route policy

Review capability rows, benchmark runs, recommendation badges, and route-decision history together before changing the preferred provider for a route family.

Expected outcome

The provider change is backed by evidence from both synthetic benchmarks and recent routing behavior instead of one isolated signal.

resilience path

Harden the fallback chain after a degraded primary

When the preferred source looks unstable, adjust the primary and fallback chain together, then confirm the updated behavior through preview output and recent live decision rows.

Expected outcome

The route family keeps serving through a deliberate fallback posture rather than relying on accidental best-effort behavior.

cost governance

Reconcile recommendation badges with cost pressure

Open the Why this decision drawer and usage evidence when the recommended provider is high quality but expensive, then compare that against entitlements and current route usage.

Expected outcome

You can explain whether the workspace should keep paying for the recommended path or step down to a more sustainable provider tier.

Governance reminders

  • A recommendation badge is a decision aid, not a substitute for benchmark evidence.
  • Do not change route policy without checking whether entitlements and capability rows actually support the path you want.
  • Use route-decision and usage history to validate that a new preference behaves well after rollout.
  • Export the matrix or preserve the benchmark context whenever the provider surface materially changes.

Next steps

Open Providers

Jump into the signed-in providers page and inspect profiles, capabilities, benchmarks, and route policies.

Execution guide

See how provider choices feed into live, paper, broker, and realism execution workflows.

Settings guide

Review the workspace policy and runtime settings that shape provider use and production posture.

Last updated

Mar 24, 2026

Feedback

Report unclear guidance, stale contracts, missing coverage, or broken docs UI on this page.

Open feedback issue
Previous
Execution Workflow
Next
Settings and Runtime Config
On this page

Jump to the section you need without losing your place.

  • What this guide covers
  • Routes and surfaces
  • Recommended provider decision loop
  • Capability matrix controls
  • Route policy controls
  • Benchmark and recommendation evidence
  • Example provider decision scenarios
  • Governance reminders
  • Next steps
Last updated

Mar 24, 2026

Feedback

Report unclear guidance, stale contracts, missing coverage, or broken docs UI on this page.

Open feedback issue