Agentic sales, CRM, and growth inside a healthcare-BNPL platform
Forward-deployed with Hazel Pay, a Cashew-family healthcare financing platform, building in-app sales, CRM, and growth agents with Strands on serverless AWS.
Illustrative engagement pattern. This entry describes the shape of work I deliver and the outcomes that engagements of this type typically produce. Names, exact figures, and client-specific details are anonymized. Confirmed engagements with named clients are added as written permission lands.
The problem
Hazel Pay lets patients split treatment costs while clinics get paid upfront. The platform needed AI woven into the product itself: agents that qualify and route leads, assist CRM workflows, and drive growth, running on the same serverless AWS footprint the platform already uses.
Constraints
- Agents embedded in a regulated healthcare-financing product
- Serverless AWS + JAMStack delivery
- Human-in-the-loop approval on customer-facing actions
What I built
- 01Built in-app sales and CRM agents with the Strands Agents SDK
- 02Wired agent tools to the platform via MCP with typed, structured outputs
- 03Ran the work under AIDLC + SpecForge with enforced approval gates
- 04Deployed on serverless AWS alongside the existing JAMStack surface
Stack
Engagement
Want a similar outcome?
Every engagement is scoped fresh. Book a discovery call to see if there's a fit, or send a brief in writing.
AI engineering engagements start at $18k.
Agent platform builds, MCP servers, and production AI integration. Day rate from $1,800 for embedded work. Most engagements run 4 to 12 weeks.