Governance Overview
Loading metrics…
Total LLM Calls
—
in selected period
Total Tokens
—
prompt + completion
Total Cost (USD)
—
based on model pricing
Avg Latency
—
seconds per call
Daily Calls & Cost Trend
Top Models by Usage
Calls by Type
WPIntelliChat LLM Governance — Live Use Case
6-step governance pipeline running inside WPIntelliChat
Prompt Lifecycle Status
Eval Scores by Prompt
Prompt Catalog — Current State
| Prompt | Category | Status | Relevancy | Coherence | Completeness | Overall | Action |
|---|---|---|---|---|---|---|---|
| Loading… | |||||||
LLM Audit Log
Complete record of every LLM call — who, what model, tokens, cost
Last 24h:
loading…
| Sr. No. | Timestamp ▼ | User | Model | Type | Request ID | User Prompt | Prompt Tok | Completion Tok | Latency | Cost USD | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Loading… | |||||||||||
—
Model Registry
Registry as a planetarium — distance = cost, size = context, colour = kind, ring = guardrail profile, green = the active API key's model. Click a planet to open its model card.
Active API key: checking…
LLM
RAG
Tool
active key
distance = cost · size = context · ring = guardrail profile · click a planet to view
Prompt Experiments
A/B test prompt variants — compare quality, latency, and cost
| Run ID | Experiment Name | Variants | Best Time (s) | Min Cost ($) | Date | |
|---|---|---|---|---|---|---|
| Loading… | ||||||
Prompt Catalog
Engineer, evaluate, and promote prompts through a governed lifecycle (Draft → Approved → Production)
| Name | Category | Status | Use Case | Rating (1-5) | Eval Score | Grade | Model Hint | Updated | Actions |
|---|---|---|---|---|---|---|---|---|---|
| Loading… | |||||||||
Review Queue
Regulation comparisons, gap reports, and AI-drafted PPM clauses awaiting review.
| Title | Kind | State | Severity | Quality | Created by | Updated | ||
|---|---|---|---|---|---|---|---|---|
| Loading… | ||||||||
LLM Orchestration & Governance
WPIntelliChat governance pipeline: guardrails → prompt resolve → model resolve → LLM → evaluate → audit. Toggle with env
ORCHESTRATOR_V2_ENABLED=1.Initializing…
Connecting to orchestrator
Guardrail reflex ribbon · recent decisions · click a bar for detail
allow
warn
block
redact
Chat Playground
Last Request Trace
No request yet. Send a message to see the trace.
Recent Guardrail Decisions
Loading…
Cost Estimator
Estimate LLM call cost before you run — compare models side by side
Estimate Parameters
Counted at 50% of input price (provider prompt-cache hits).
Estimated Cost
Per Request
—
Per Day
—
Per Month
—
Compare All Models
| Model | Provider | Per Request | Per Day | Per Month | Context |
|---|
Guardrail Rules
Database-backed rules per profile. Each chat call uses the rules of its model's
guardrail_profile.| ID | Profile | Name | Type | Action | Stage | Priority | Active | Operations |
|---|---|---|---|---|---|---|---|---|
| Loading… | ||||||||
Orchestrator Metrics
Live rollup from
/api/orchestrator/metrics: all LLM activity — blocked rate, fallback rate, answer relevancy, hallucination, latency.Total runs
—
Completed
—
Blocked
—
Blocked rate
—
Fallback
—
Fallback rate
—
Avg answer relevancy
—
Avg hallucination
—
Latency avg (s)
—
Latency max (s)
—
Total cost (USD)
—
Guardrail breakdown
Decision Tables
Rule tables that map input records to outcomes — used by the Decision Table workflow node.
| Name | Description | Columns | Rules | Created |
|---|
A/B Experiments
Champion/Challenger experiments that route traffic between two decision strategies.
| Name | Status | Split | Variant A | Variant B | Created |
|---|
Policy Watch
Tracked regulations as a living garden — each drift check waters a plant, each detected amendment blooms. Backed by
/api/policy-watch.—
healthy
amendment pending
amendment resolved
stale (30d+)
seedling (new)