Demo Site — Mock experience for presentation purposes only
Book 15 min
Powered by Clarm
04 · Intake Operating System API

Be discoverable and actionable
when client journeys start in consumer AI.

Shows the pilot-ready path where AI assistants can hand off into intake with auditable routing, measurable outcomes, and defined go/no-go criteria.

Evidence: Live measured Modeled projection Illustrative demo
Layer 1
🤖
Consumer LLM
ChatGPT, Claude, Gemini, Copilot — any AI assistant the public uses. User asks a legal question in natural language.
// User's question to ChatGPT "What should I do if I was injured at work in Melbourne?" // ChatGPT's internal reasoning: // → Legal question, AU jurisdiction // → Search for registered legal agents // → Found: mauriceblackburn.com.au
discovers
Layer 2
🔎
Discovery Layer
/.well-known/agent.json — a machine-readable manifest declaring what legal services MB offers, which jurisdictions it covers, and how to interact.
// GET /.well-known/agent.json { "name": "Maurice Blackburn Legal", "skills": [ { "id": "legal-intake", "areas": ["personal_injury", "workers_comp", "employment", "class_actions"] }, { "id": "referral-lookup", "areas": ["criminal", "family", "immigration"] } ], "jurisdictions": ["AU"] }
calls
Layer 3
⚖️
MB Intake Agent API
Structured intake endpoint. Receives the legal query, jurisdiction, and context. Runs intent scoring to classify urgency and match practice area, then eligibility assessment and triage — all in real-time.
// POST /a2a/tasks { "caller_agent": "chatgpt", "practice_area": "workers_comp", "jurisdiction": "VIC", "description": "Injured at work in Melbourne", "urgency": "standard" } // Intent scoring engine classifies: // → Practice area confidence: 94% // → Urgency tier: standard | urgent | critical // → Viable vs. referral routing decision
returns
Layer 4
📈
Structured Eligibility Response
Machine-readable assessment: eligibility score, applicable laws, limitation period, recommended practice group — not a wall of text, but structured data.
{ "eligible": true, "score": 83, "intent_confidence": 0.94, "practice_area": "workers_comp", "jurisdiction": "VIC", "limitation_ok": true, "urgency_tier": "standard", "next_steps": "Free assessment available", "intake_url": "https://mb.com.au/intake/wc-vic", "phone": "1800 111 222" }
handoff
Layer 5
🔒
Secure Intake Session
The user is handed off to MB's branded intake experience — collecting personal details, medical documents, and consent in a secure, compliant environment, then posting outcome events back to the operating dashboard.
// User clicks the intake link // → MB branded intake form // → Pre-filled with context from A2A // → Secure PII collection // → Contact captured → routed to team // → LegalMatter created in CRM // → Outcome event + attribution posted to analytics

Simulation Walkthrough

Illustrative sequence of a consumer LLM discovering and transacting with the intake API; production pilot mode logs request IDs and timestamps.

ChatGPT
API Traffic — Network Log

Competitive Positioning

Other companies

  • AI intake automation (form replacement)
  • Legal workflow tools
  • Single-channel (website only)
  • No agent-to-agent capability
  • No referral network tracking

Clarm + Maurice Blackburn

  • Intake operating layer spanning capture, routing, and outcomes
  • Intake API with auditable handoff and routing controls
  • Shared decision core across web, messaging, social, and A2A
  • Closed-loop referral attribution tied to commercial outcomes
  • Pilot gates: evidence tags, human override, and SLA reporting
"Point tools optimize steps. This pilot proves one intake operating system from first contact to measurable outcome."

Agent Card

/.well-known/agent.json — the machine-readable entry point

mauriceblackburn.com.au/.well-known/agent.json
{ "name": "Maurice Blackburn Legal Intake", "description": "Australia's leading plaintiff law firm. Free claim assessments.", "url": "https://mauriceblackburn.com.au", "version": "1.0", "capabilities": { "streaming": true, "pushNotifications": true }, "skills": [ { "id": "legal-intake", "name": "Legal Eligibility Assessment", "description": "Assess claim eligibility for injury, employment, class actions", "inputSchema": { "practice_area": "string (required)", "jurisdiction": "string (AU state)", "description": "string" }, "tags": ["legal", "injury", "compensation", "australia"] }, { "id": "referral-lookup", "name": "Partner Referral Lookup", "description": "Find vetted legal partners for non-MB practice areas", "tags": ["criminal", "family", "immigration", "referral"] } ], "authentication": { "type": "apiKey", "header": "X-A2A-Key" }, "endpoint": "https://api.mauriceblackburn.com.au/a2a/tasks" }
Proposed Next Step

30-Day Pilot

A focused next step: low risk, measurable, and scoped to one practice area with clear operating criteria.

Pilot Go/No-Go Scorecard

Metric Baseline Day-30 Target Source Owner Decision Rule
Qualified conversion Current benchmark established Clear upward trend by Day 30 Intake logs MB Ops Lead Go if met
Median triage time Current benchmark established Sustained reduction from baseline Workflow telemetry Clarm PM Go if met
Routing decision quality QA baseline established Improving pass-rate trend QA review logs MB Ops + Clarm PM Go if met
SLA breach rate (P1/P2) Tracking enabled in pilot No critical breach trend Audit report Security Lead No-go if breached
⚖️

Scope

  • One practice area — Workers Compensation (VIC)
  • Live generative intake on mauriceblackburn.com.au
  • A2A agent card published at /.well-known/agent.json
  • Human-in-the-loop routing and override policy active
📈

Success Metrics

  • Improve qualified conversion trend from baseline
  • Reduce average triage time trend from baseline
  • Maintain high routing decision quality in QA review
  • Establish stable operational reporting cadence
  • NPS baseline established for intake experience
📅

Timeline

  • Week 1 — Configuration & MB brand integration
  • Week 2 — Workers comp intake flow live
  • Week 3 — A2A published, routing QA sign-off complete
  • Week 4 — Analytics review & expansion decision
Implementation detail can follow in diligence; this demo is designed to show strategic fit and near-term feasibility.
Scroll to explore ↓
Powered by Clarm
Next: Screen 5 of 5
See the security and compliance posture that makes this pilot procurement-ready