Shoten Deshmukh

Technical Delivery & AI Solutions Leader

shotend@gmail.com+44 7792 338583Londongithub.com/shoten-healthjourneys

Capabilities Agent

You could read my CV. Or you could ask an agent instead.

Claude Sonnet 4.6 backed by 8 MCP tools, retrieving structured evidence in real time. Built with Claude Code. This site is itself a demonstration of the agentic patterns described below.

Capabilities Agent
Hi, I'm an AI agent built to answer questions about Shoten's fit for the Technical Deployment Lead role. I use tools to retrieve structured evidence. Ask me anything, or try one of the suggestions below.

The Match

How my experience maps to what you're looking for

JD Requirement

“5+ years customer-facing technical delivery leadership”

Evidence

7+ years: Head of Engineering at Benchmark serving 150 adviser firms (£34bn AUA), Senior Associate at PwC with embedded engineers at client sites

JD Requirement

“Delivered AI/ML/LLM agentic solutions into production”

Evidence

Four production agentic AI solutions under FCA regulation: Fact Find Agent (tool use, ontology grounding, HITL), Advice Case Orchestrator (multi-agent, compliance routing), Meeting Summary Agent (transcript capture, compliance-ready summaries, CRM integration), and Client Reviews Agent (end-to-end annual review support, suitability report generation)

JD Requirement

“Lead architecture discussions, evaluate technical trade-offs”

Evidence

Owned technical direction for Benchmark’s SaaS platform across 102-person engineering org. Designed agentic architectures with tool use, compliance-in-the-loop, and human escalation

JD Requirement

“Complex enterprise delivery in regulated industries”

Evidence

7+ years in FCA-regulated financial services. Security reviews, data residency, and deploying across 150 firms with all the organisational politics that comes with

JD Requirement

“Executive presence”

Evidence

ExCo stakeholder management, £20m change portfolio, executive briefings across 150 adviser firms. Negotiated CEO-level partnerships with major Indian hospital groups

JD Requirement

“Builder’s mindset, create a function not join one”

Evidence

Founded Health Journeys and built the full platform solo with AI. Voluntarily deployed Claude Code into 3 external orgs. Created the AI-Augmented PDLC from scratch

JD Requirement

“Financial services, healthcare/life sciences verticals”

Evidence

7+ years FCA-regulated financial services at Benchmark/Schroders. Founded a medical travel company connecting UK patients with Indian hospitals

JD Requirement

“Codify reusable patterns and technical playbooks”

Evidence

Wrote playbooks for migration programmes and disaster recovery. Designed a repeatable AI-Augmented Product Development Lifecycle (4x cycle time improvement)

What I've Built

Fact Find Agent
Problem

Advisers spend ~90 mins per review on manual admin across 34,000+ annual reviews

Approach

Agentic AI that analyses meeting notes and financial PDFs, retrieves CRM context via tool use, grounds against a financial planning ontology, runs HITL clarification

Result

~90 min reduction per review. Production under FCA regulation.

Meeting Notes + PDFs
Agent
CRM via Tools
Ontology
HITL Check
Adviser Review
CRM Updated
Advice Case Orchestrator
Problem

Advice cases need complex workflow management with compliance checkpoints

Approach

Multi-agent system with tool use for task management, compliance review agents, human escalation

Result

Compliance-by-design in the critical path. Production deployment.

Adviser
Orchestrator Agent
Task Management Tools
Compliance Agent
Pass / Fail Routing
Human Reviewer
Meeting Summary Agent
Problem

Advisers spend 30-45 minutes after each client meeting writing up notes, action items, and follow-ups in a compliance-ready format

Approach

Deploys a meeting bot to capture transcripts, then summarises into a compliance-ready format with action items and follow-ups fed directly into the CRM

Result

Saves 30-45 minutes per client meeting. Production under FCA regulation.

Client Reviews Agent
Problem

Annual client reviews are complex, multi-step processes requiring preparation, meeting management, and report generation

Approach

Supports the annual client review process end-to-end: prepares the advice team ahead of the meeting, manages workflow and tasks through the review cycle, and generates the suitability report

Result

Full end-to-end support for the annual review cycle. Production under FCA regulation.

Health Journeys
Problem

UK patients stuck on NHS waiting lists. World-class healthcare in India at a fraction of the cost. No trusted bridge.

Approach

Founded the company. Built the entire platform solo using AI tools, no engineering team.

Result

30+ page site, AI chatbot, automated blog, 4 hospital partnerships, 64 patient leads. Built by one person.

Patient
Website (30+ pages)
AI Chatbot (WhatsApp / Messenger)
Lead Capture
Hospital Partners
AI-Augmented PDLC
Problem

Traditional product development cycles too slow for AI-era delivery

Approach

Spec-driven development lifecycle with AI augmentation at each stage

Result

4x cycle time improvement. Now used across Benchmark’s engineering org.

Claude in the Field

I already do forward-deployed AI enablement. Voluntarily. On weekends.

Covecta.io

Set up repos, context files, Claude Code workflows. Hands-on training for the engineering team. Ongoing support.

Nikura Essential Oils

Trained CEO and leadership on Claude Code. CEO now saves 15 hours per week.

Sigma Sports

Set up Claude Code tooling and workflows for the dev team.

Same pattern each time: train leaders first, set up repos and context files, train the team, then ongoing weekend support.

Open Source

gym-trainer-ai

github.com/shoten-healthjourneys/gym-trainer-ai

Full-stack AI personal trainer. Claude Sonnet 4.6 via Microsoft Agent Framework, 10 MCP tools, Deepgram voice, React Native, FastAPI, Azure PostgreSQL, Terraform, GitHub Actions CI/CD. Built end-to-end with Claude Code.

Claude Sonnet 4.6React NativeFastAPIAzureTerraformMCP

flight-hacker

github.com/shoten-healthjourneys/flight-hacker

Parallel Docker-based flight price scanner. 8+ containers through different VPN locations to detect geo-pricing on Google Flights. Playwright, SQLite, web dashboard.

DockerPlaywrightSQLiteVPNPython