Updated for Smartflow 1.10 / dashboard v1.9.22 — covers FinOps, Red-team, Atomizer, MCP Efficiency, Demo mode, and the rest of the live sidebar. 1.10 release notes →
Smartflow Enterprise · Operator guide

Dashboard User Guide

What each sidebar tab does, when to use it, and how Demo mode lets you walk the whole product without touching production.

Home Policies Red-team FinOps MCP Demo mode
Start here Tab map Home Policies Red-team Routing Playground Traces Caching FinOps MCP Agents Identity Auth & SSO Settings Demo mode
1

Start here

The dashboard is the day-to-day control plane for Smartflow — spend, policy, routing, agents, and audit — in one React app.

Sign in

Open your deployment’s dashboard URL (on cluster1: https://cluster1.langsmart.app/dashboard/). Sign in with the local admin account or SSO if you’ve configured Auth & SSO.

Admin key

Some views (Traces, Maestro/Shield policy writes, MCP registry, agent credentials) need the SMARTFLOW_ADMIN_KEY. Paste it once under Settings → Admin key. It’s stored in this browser session only and sent as X-Admin-Key on those calls. Keys start with sf- — if your browser autofills a password, clear it and paste the real key.

Demo mode (top bar)

Next to your avatar is a Demo mode toggle. When it’s on, every page renders seeded sample data and every write (propose a policy, register an MCP server, tag a FinOps group, …) stays in this browser tab. Nothing hits production. It clears when you close the tab or sign out. Use it for demos and partner walkthroughs.

Tip. This guide is also linked from the avatar menu as User guide (book icon) so operators can open it without leaving the product context.
2

Tab map — what each page is for

Quick reference. Jump to a section for more detail.

SidebarWhat it’s for
HomeLive traffic, cache efficiency, cost saved, system health at a glance
PoliciesShield / Maestro / Guardrail policies, builder, identity gates, frameworks, compliance scan, audit, atomizer
Red-teamRun the built-in adversarial prompt suite; see catch rate and suggested rules
RoutingDefault provider, strategy, overrides, fallback chains, virtual keys
PlaygroundSend a live chat request through the gateway and inspect the response
TracesPer-request audit log with attribution, cost, risk tier, control/policy IDs
CachingMetaCache hit rates, savings, compression tester + optional quality check
FinOpsSpend by provider/model/user/group, budgets, anomalies, reconciliation, digests, policy proposals
SustainabilityEnergy / carbon view of AI traffic (where instrumented)
Data & SovereigntyDeployment posture, frameworks, connector registration status
MCPCatalog, registered servers, tool-call efficiency stats, discovery
AgentsA2A agent registry and AIDA credentials
IdentityDevice enrollment / Shield identity views
Auth & SSOOIDC/SSO status, config, team mapping
SettingsAdmin key, session info, PII tokenization notes
3

Home

The landing view after login — a pulse check, not a deep dive.

What you’ll see

  • Request volume and trend
  • Cache efficiency and tokens / cost saved
  • Health of the gateway and related services
When to use it

Morning check-in, status for a standup, or confirming the cluster is healthy before a demo.

4

Policies

Where governance rules live. The Policies group has several child pages.

All Policies

Unified list of Shield, Maestro, and Guardrail policies. Filter by engine, search by name, open a policy to inspect or edit.

Policy Builder

Create or edit a policy with structured controls instead of raw YAML when the builder supports that engine.

Identity Gates

Who can do what — attach policies to groups, roles, or identity claims so enforcement follows your directory.

Frameworks

Regulatory / control frameworks (HIPAA, GDPR, PCI, …) and how they’re assigned to teams.

Compliance Pipeline

Paste sample content, pick frameworks, run the multi-engine scan and watch stages (PII, financial control, regulatory) fire.

Audit & Evidence

Evidence-oriented views for audits — what was enforced and what can be shown to reviewers.

Atomizer

Paste a policy document (text). Smartflow returns atomic, control-mapped rules with severity and suggested action. Optionally persist and reload saved atomizations. Uses an LLM engine when a key is available; otherwise a heuristic fallback (the UI badges which engine ran).

Atomizer note. v1 is text paste only — PDF/DOCX upload isn’t wired yet. Use copy/paste from the source document.
5

Red-team

Self-test your live guardrail stack with a built-in adversarial corpus.

What it does

  • Pick categories: prompt injection, jailbreak, PII exfiltration, data leakage, harmful content, regulated advice
  • Run the suite against your compliance detector (no external LLM required for the harness itself)
  • See catch rate, risk score, per-category breakdown (with NIST function tags), and suggested block rules for misses
When to use it

After changing policies, before a customer demo, or when you want a concrete “what still gets through” report for security review.

6

Routing

How traffic chooses a provider and what happens when one fails.

What you’ll configure

  • Default provider — where requests go when nothing else overrides
  • Strategy — cost / quality / latency preferences
  • Overrides — temporary or scoped routes (e.g. force a model for a group)
  • Fallback chains — ordered failover when a provider errors
  • Virtual keys — issue / revoke gateway keys for apps and teams
When to use it

Onboarding a new provider, cutting over traffic, or issuing a key for a new app.

7

Playground

Send a real request through the gateway from the UI.

What it’s for

Quick end-to-end check: model, prompt, response — without leaving the dashboard. Useful after a routing or policy change to confirm the path still behaves.

In live mode this hits your real gateway and providers. Use Demo mode if you only want a safe walkthrough.
8

Traces

Every AI request with attribution and a tamper-evident audit chain.

What you’ll see

  • Table: time, user, model/provider, endpoint, risk tier, cost, latency
  • Governance column — how many control/policy IDs are mapped on that request
  • Drawer: attribution (user, groups, department, key), request meta, Control IDs and Policy IDs as chips, prompt/response (when retained), HMAC chain fields
When to use it

Incident review, “who spent what,” proving which controls fired, or verifying the audit chain for compliance.

Traces typically require the admin key. If the page is empty or errors, check Settings.
9

Caching

MetaCache performance — exact, semantic, and vector hits — plus a compression tester.

Widgets & charts

Hit rate, tokens saved, cost saved, latency saved, and a breakdown of match types (exact / semantic / vector).

Compression tester

Paste text, compress it, see ratio and token savings. Optional Quality check asks the HHEM faithfulness sidecar for a quality_delta (higher = more faithful to the original). If HHEM isn’t deployed or enabled, the UI shows quality check unavailable instead of failing silently.

10

FinOps

Cost governance for AI spend — the place finance and platform owners meet.

Live vs Demo mode (FinOps submenu)

  • Live — real cluster spend from /api/finops/*
  • Demo mode (FinOps submenu) — seeded FinOps story for walkthroughs when live traffic is thin. The site-wide Demo mode toggle also covers FinOps when it’s on.

What you can do

  • Spend totals by week / month / year; top provider and model
  • Top users or groups (last 30 days); group tagging when IdP hierarchy is missing
  • Caching / token savings by provider
  • Budgets & burn-rate alerts — caps by all / provider / group; enforce via policy proposal when over
  • Spend trend & anomalies — spike days flagged; draft a policy from a spike
  • Providers & reconciliation — gateway-metered vs billed spend; surface un-governed spend
  • Cost efficiency & ROI — concentration (HHI), allocation coverage, cost-to-value
  • Schedule digest — “what changed & where to save” briefing
  • CSV / FOCUS-CSV export and a print-ready FinOps PDF report
  • Propose policy on recommendations — scope/target pickers and model→model routing
When to use it

Monthly cost review, catching a runaway team, bringing shadow spend under the gateway, or turning a savings idea into a pending policy for admin approval.

11

Sustainability

Energy and carbon framing of AI traffic where the deployment instruments it.

What it’s for

ESG / sustainability reporting context for AI usage — pair with FinOps when stakeholders care about both dollars and footprint.

12

Data & Sovereignty

Deployment posture and where data is allowed to live.

What you’ll see

  • Sovereign overlay / region / FIPS / GDPR / CAC / WORM flags
  • Enabled compliance frameworks
  • Connector registration status (e.g. Box, SharePoint) where configured
13

MCP

Model Context Protocol — catalog, registration, trust, and efficiency.

Tabs

  • Catalog — published MCP servers available to browse
  • Registered — servers your gateway trusts; remove when retiring a tool host
  • Efficiency — tool-call-reduction benchmark (calls avoided, tokens/cost saved, top tools), discovery-cache hit stats, trajectory-cache hit rate and estimated calls avoided
  • + Add server — probe an internal URL, pick a well-known public MCP, or register manually (URL, optional API key, trust flag, cost per call)
When to use it

Onboarding a new tool server, proving MCP caching is paying for itself, or auditing which tools agents can call.

14

Agents

A2A agent registry and AIDA credentials.

What you’ll do

  • List / register / remove agents
  • Issue and revoke AIDA credentials (algorithm, key id, fingerprint shown on create)
When to use it

Standing up a new agent identity or rotating credentials after a leak or offboarding.

15

Identity

Device enrollment and Shield-oriented identity views.

What it’s for

Enrollment tokens, device virtual keys, and identity checks used by Aperion Shield / enterprise device flows. Pair with Policies → Identity Gates when you’re binding policy to who’s on the wire.

16

Auth & SSO

How people sign into the dashboard and how directory groups map in.

What you’ll configure

  • SSO status (enabled / healthy)
  • OIDC config (issuer, client, redirects)
  • Team / group mappings from your IdP

Deeper Entra / Okta patterns: SSO & Unified Identity brief.

17

Settings

Session credentials and operator-facing notes — not a full cluster control panel.

What’s here

  • Admin key — paste SMARTFLOW_ADMIN_KEY for this browser session
  • PII tokenization — explains the proxy-level PII_TOKENIZE_MODE / PII_TOKENIZE_TYPES env vars (reversible [[SF_PII_TYPE_n]] tokens). This is a startup flag on the proxy, not a live dashboard toggle — the card includes a copy-paste kubectl set env example
  • Session — who you’re signed in as; tokens live in sessionStorage
18

Demo mode (site-wide)

Seeded product tour for sales, partners, and internal training.

How it behaves

  • Toggle in the top bar (next to your avatar)
  • Amber banner while active — Reset session clears simulated writes; Turn off returns to live APIs
  • All pages (Home, Policies, Red-team, MCP Efficiency, FinOps, Traces, …) use realistic seed data
  • Writes are simulated in sessionStorage only — they vanish on tab close or logout
  • Login / verify endpoints are never intercepted, so you can always authenticate
When to use it

Any time you need a fully populated story without production risk — investor walkthroughs, partner testing, training new operators.

Don’t confuse the site-wide Demo mode toggle with the FinOps submenu item “Demo mode” — both show seeded FinOps data; the top-bar toggle covers the whole product.