Conversational Dashboard

Governance operations through natural language. Ask questions, review escalations, explore decisions, run backtests — all in a chat interface.

Chat, Not Dashboards

Traditional governance dashboards bury critical signals under page navigation. GaaS takes a different approach: you talk to your governance system. Ask "what happened overnight?" and get a summary with data. Say "review that top escalation" and get the context package with approve/deny options. No clicks through menus. No tab switching.

The dashboard is powered by Claude, with 33 tools that map to the full GaaS API. Claude fetches live data, generates visual artifacts inline, and takes actions on your behalf — all within the conversation.


Architecture

1

You

Type a question or click a suggested action. Natural language, no syntax required.

2

Chat UI

React frontend with markdown rendering, live artifact preview, and suggested action chips. Streams responses in real time via server-sent events.

3

BFF (Express + Claude)

Backend-for-frontend server. Sends your message to Claude with 33 governance tools. Claude decides which tools to call, executes them against the GaaS API (up to 10 rounds), and streams text and artifacts back.

4

GaaS API

The governance engine. All data — decisions, escalations, learning, membranes — comes from the same API your agents use.

No direct API access required. The dashboard handles authentication, tool orchestration, and response formatting. You never see raw JSON unless you ask for it.

What You Can Do

The dashboard exposes five categories of governance operations through natural language.

Operational Intelligence 10 tools

Escalation Management 8 tools

Learning & Calibration 9 tools

Onboarding & Membranes 2 tools

Audit & Decisions 2 tools


Visual Artifacts

When data needs to be seen rather than described, Claude generates live React components inline in the conversation. Charts, tables, metric cards, and status indicators render directly below the response text.

What gets rendered

Artifacts are expandable to full-screen and include a code toggle for transparency. Every visualization is generated from live GaaS data — nothing is mocked or pre-built.


Suggested Actions

After responses with clear next steps, clickable action chips appear below the message. These guide workflows without requiring you to type.

Show me pending escalations
Here are 3 pending escalations, sorted by urgency...
[Escalation queue table rendered inline]
Review top escalation Show escalation stats Filter by risk

Example Conversation Flows

Morning check-in

What happened overnight?
Here's your daily digest for yesterday...
[Metric cards + decision trend chart]
12 decisions processed, 2 blocks, 1 escalation pending. Block rate is up 8% vs last week — both blocks were on agent-fintech-01 hitting the PCI data policy.
Review the blocks Show that escalation Agent details for fintech-01

Escalation review

Review that escalation
Here's the context package for ESC-2847...
[Context package: intent summary, policy triggers, deliberation positions]
The agent tried to send regulated patient data via an unencrypted channel. Policy pol_t1_003 triggered. The deliberation panel voted 5-1 to escalate (the dissenting agent noted the low audience size).
Approve Deny Modify Reassign

Calibration backtest

What if we lowered the deliberation threshold to 0.6?
Running backtest on deliberation_threshold: 0.7 → 0.6...
[Impact analysis chart showing verdict changes]
Over the last 30 days, 4 additional decisions would have triggered deliberation. 2 of those were ultimately approved — the other 2 would have caught edge cases that slipped through.
Apply this change Try 0.65 instead Show the 2 edge cases

Setup

ENVIRONMENT VARIABLES
Variable Required Description
ANTHROPIC_API_KEY Yes Claude API key for the BFF conversation engine
GAAS_API_URL No GaaS API server URL (default: http://localhost:8000)
GAAS_API_KEY No API key for the GaaS API (omit if running in open mode)
RUNNING THE DASHBOARD
cd apps/dashboard
npm install
npm run dev

This starts both the BFF server (port 3001) and the Vite dev server concurrently. The frontend proxies /api requests to the BFF automatically.

Prerequisites: Node.js 18+, a running GaaS API server, and an Anthropic API key. See Getting Started for the GaaS API setup.

Related Pages