{
  "version": "3.0",
  "generatedAt": "2026-08-07T06:28:03.041Z",
  "lastUpdated": "2026-07-12",
  "project": {
    "slug": "casey-ai",
    "title": "Casey AI",
    "tagline": "Chase's first AI agent for voice and text customer help.",
    "description": "Chase's first customer-facing AI agent, and the pattern the rest are built on.",
    "company": "JPMorgan Chase",
    "role": "Senior Product Designer",
    "year": 2025,
    "tags": [
      "Agentic AI",
      "Voice",
      "RCS",
      "Home Lending"
    ],
    "url": "https://www.sebmendo.design/work/casey-ai",
    "experienceRoleId": "jpmc-ai",
    "sections": [
      {
        "id": "summary",
        "headline": "Chase's first customer-facing AI agent, and the pattern the rest are built on.",
        "body": "Casey is a conversational agent that talks to Chase customers by voice and by text. Home lending was the first place it shipped, chosen deliberately because it is the hardest room in the bank."
      },
      {
        "id": "challenge",
        "label": "Challenge",
        "headline": "A bank cannot ship a chatbot.",
        "body": "Every sentence an AI says to a customer is a sentence the bank said. Voice and text are also the two channels federal law watches most closely, so the real problem was not building an agent that talks well. It was building one that knows what it is not allowed to say."
      },
      {
        "id": "approach",
        "label": "Approach",
        "headline": "Solve it where the stakes are highest, then it travels.",
        "body": "We started with mortgage because it has the most regulation, the biggest dollar amounts, and the longest customer journey in consumer banking. Anything that survives there works anywhere. So I designed Casey as a reusable conversational system rather than a mortgage feature: one agent, two surfaces, and a shared model of what it knows, what it may say, and when it steps aside."
      },
      {
        "id": "solution",
        "label": "Solution",
        "headline": "The handoff is the product.",
        "body": "Casey can qualify, explain, and schedule. It cannot advise or quote, because that requires a licensed human, so the work went into making that wall feel like a door. Any question beyond its authority, any sign of customer stress, and any repeated confusion routes to a person with the full conversation attached, and that routing logic is the piece every future Casey inherits."
      },
      {
        "id": "results",
        "label": "Results",
        "headline": "Live on two surfaces. Cleared through three regulatory regimes.",
        "body": "Casey Voice shipped July 2025. Casey RCS shipped May 2026 on iOS and Android. Chase trademarked the voice, and the conversational patterns are now the reference model for agentic work across the business."
      },
      {
        "id": "tldr",
        "label": "TLDR",
        "headline": "The quick version.",
        "body": "Chase needed a customer-facing AI agent that could not create legal exposure every time it opened its mouth. I designed Casey as a reusable system across voice and text, proved it in home lending because that is the hardest environment in the bank, and spent most of the project on the boundary where an AI hands a person to a licensed human. Both surfaces shipped, Chase trademarked the voice, and the pattern is what the next agents are built on."
      }
    ],
    "impact": [
      {
        "metric": "calls_initiated",
        "value": "3,000+",
        "context": "Casey Voice production; ~12% lead conversion rate",
        "confidence": "measured"
      }
    ],
    "media": {
      "thumbnail": "https://www.sebmendo.design/assets/casey-ai.png",
      "preview": {
        "frame": "phone",
        "src": "https://www.sebmendo.design/assets/casey-ai.png",
        "video": "https://cjeb7madwget0lzn.public.blob.vercel-storage.com/casey-rcs.mp4",
        "poster": "https://www.sebmendo.design/assets/posters/casey-rcs.jpg"
      }
    }
  },
  "relatedExperience": {
    "id": "jpmc-ai",
    "company": "JPMorgan Chase",
    "role": "Senior Product Designer — AI",
    "period": "Jul 2025 – Present",
    "startDate": "2025-07",
    "current": true,
    "summary": "Leads design for Casey AI, Chase's first customer-facing AI agent—shipped on voice and RCS, proven in home lending, and now the reference pattern for agentic work across the business.",
    "responsibilities": [
      "Design conversational AI flows for complex banking use cases",
      "Work cross-functionally with AI engineers and Forward Deployed Engineers to ship agentic experiences",
      "Lead design thinking sessions for strategic AI implementation",
      "Conduct detailed QA for agentic edge-case prioritization and guardrail resolution",
      "Build and ship customer-centric UI through AI-native development processes",
      "Train and mentor junior designers on AI-native programming with Cursor, Claude Code, VSCode, and Figma MCP"
    ],
    "outcomes": [
      "Casey AI shipped to production with voice and RCS channels",
      "3,000+ calls initiated at ~12% lead conversion in production"
    ],
    "capabilities": [
      "Agentic AI",
      "Voice UX",
      "RCS",
      "Regulated design",
      "Design leadership"
    ],
    "relatedProjectSlugs": [
      "casey-ai"
    ]
  },
  "verifiedImpact": [
    {
      "id": "casey-production",
      "metric": "calls_initiated",
      "value": "3,000+",
      "context": "Casey Voice production; ~12% lead conversion rate",
      "confidence": "measured",
      "projectSlug": "casey-ai"
    }
  ],
  "shippedWork": [
    {
      "id": "conversational-rcs",
      "title": "Conversational RCS",
      "affiliation": "Chase",
      "dateLabel": "May 2026",
      "sortDate": "2026-05",
      "projectSlug": "casey-ai",
      "url": "https://www.sebmendo.design/work/casey-ai"
    },
    {
      "id": "conversational-voice",
      "title": "Conversational AI (Voice)",
      "affiliation": "Chase",
      "dateLabel": "July 2025",
      "sortDate": "2025-07",
      "projectSlug": "casey-ai",
      "url": "https://www.sebmendo.design/work/casey-ai"
    }
  ],
  "machineReadable": {
    "siteJson": "https://www.sebmendo.design/content.json",
    "index": "https://www.sebmendo.design/llms.txt",
    "corpus": "https://www.sebmendo.design/llms-full.txt",
    "agentGuide": "https://www.sebmendo.design/.well-known/ai.txt",
    "thisUrl": "https://www.sebmendo.design/work/casey-ai/content.json"
  }
}