Available for new engagements

Automation that
survives contact
with production.AI Automation EngineerAI Business AnalystAI ConsultantAI Automation Engineer

I map how work actually moves through a business, redesign it, and then build the systems that run it — with security, audit trails and AI governance in place from the first sprint, not bolted on after the demo.

engagement_pipeline.flow● live
CRM / ERPsalesforce · hubspot Documentspdf · sheets · mail Conversationscalls · chat · forms Ops datalogs · events · db Orchestration agents · rag · rules human-in-the-loop iso 42001 guardrails Decisionsscored · routed · logged Actionsshipped · auditable INGEST REASON + GOVERN EXECUTE
7+Years in delivery
150+Automation workflows
12Certifications held
3Ventures operating
One engagement, three altitudes

The three titles are one service ladder.

Most automation projects fail in the gap between the people who decide, the people who specify, and the people who build. I cover all three, so nothing is lost in the handover.

Altitude 01 — Advise

AI Consultant

Where automation is worth the money, where it isn't, and what has to be true before you start.

  • Automation maturity and opportunity assessment
  • Build-vs-buy and tool selection, vendor-neutral
  • EU AI Act risk classification and ISO 42001 readiness
  • Roadmap with a business case attached to each phase
Altitude 02 — Specify

AI Business Analyst

The layer most AI projects skip. As-is reality on paper before anyone writes a prompt.

  • Process mapping, gap analysis, to-be design
  • BRD / FRD, acceptance criteria, edge-case catalogues
  • Data readiness, quality rules and governance baseline
  • Stakeholder workshops and UAT sign-off
Altitude 03 — Build

AI Automation Engineer

Working systems in your stack, documented well enough that your team can run them without me.

  • n8n, Make, Zapier and custom orchestration
  • React / Next.js portals on Supabase and Postgres
  • RAG pipelines, MCP integrations, agent workflows
  • Runbooks, monitoring, handover and enablement
What I actually build

Six kinds of problem I take on.

Tool-agnostic by default. The stack is chosen after the problem is understood, never before.

Production-ready architecture

Full-stack systems

  • Multi-tenant SaaS with security hardened from day one
  • Real-time systems over WebSocket
  • Databases built for zero-downtime migration
  • Deployment automation, monitoring, disaster recovery
Intelligent automation

Agentic AI systems

  • Multi-agent orchestration with tool use and reasoning loops
  • Retrieval-augmented generation for grounded answers
  • Human-in-the-loop checkpoints on anything consequential
  • Evaluation harnesses so quality is measured, not assumed
Risk & compliance

AI governance

  • EU AI Act mapping and implementation
  • ISO/IEC 42001 management system design
  • Risk categorisation: prohibited, high, limited
  • Audit trails, transparency notices, PII handling
System architecture

Data integration

  • One data layer across ERP, CRM and accounting
  • ETL with validation, quality checks and error handling
  • Master data governance and a real single source of truth
  • Real-time sync with full audit logging
Revenue operations

Go-to-market systems

  • Lead scoring, routing and enrichment
  • Funnel velocity work — 90 days to 62 on one programme
  • Predictive scoring for forecast accuracy
  • Multi-touch attribution and win/loss analysis
Marketing automation

Content operations

  • Multi-channel pipelines: email, social, reports, dashboards
  • Orchestration that removes the majority of manual effort
  • Personalisation at scale from real behaviour
  • Measurement loops that feed back into the workflow
How an engagement runs

Four phases, in order, with deliverables you keep.

The order matters here — each phase produces the input the next one needs. You can stop after any phase and still own something useful.

PHASE 01

Foundation & readiness

Establish what's worth automating and whether the data can support it. Executive alignment, technology audit, as-is process mapping.

✓ Opportunity roadmap
✓ Integration blueprint
✓ Governance baseline
✓ As-is documentation
PHASE 02

Architecture & design

Design the workflows and the safety rails together. RBAC, row-level security, audit logging, bias and PII handling — specified, not improvised.

✓ Workflow architecture
✓ Compliance framework
✓ Technical specification
✓ Risk classification
PHASE 03

Build & test

AI-assisted development against the spec, then tested properly — functionality, performance, and the edge cases that break demos in month three.

✓ Tested systems
✓ Performance baselines
✓ Escalation guide
✓ Runbooks
PHASE 04

Deploy & scale

Phased rollout under monitoring, UAT sign-off, and enough team enablement that the system outlives the engagement.

✓ Live systems
✓ Metrics dashboard
✓ 90-day roadmap
✓ Handover package
Selected work

Shipped systems, with the trade-offs included.

Open any engagement for the problem, the approach and what it produced. Client names appear only where I have permission to use them.

Self-service SaaS portal for 200+ SME customers

Full-stack build · 8 weeks · Designer + me

Problem

Over 200 SME customers had no way to see their own workflow status. Updates went out as manual CSV exports, which meant delays and a support queue full of “is it running?” tickets. They needed live status, execution logs and cost tracking in one place.

Approach

  • React and TypeScript front end with real-time updates over WebSocket
  • Node.js and Express API on PostgreSQL with JWT auth
  • Supabase multi-tenant architecture with row-level security
  • AES-256 encryption, audit trails and GDPR data endpoints
ReactTypeScriptNode.jsPostgreSQLSupabaseWebSocketDocker

Outcome

200+customers on one platform
99.8%uptime over 18 months
<100msP99 response time
40%fewer support tickets

Trade-off

Row-level security across every tenant added query complexity and cost roughly a week of the eight. It was the right call: the alternative was application-layer filtering, which fails silently the first time someone adds an endpoint and forgets the tenant check.

Workflow automation programme — Clepto.io client portfolio

n8n orchestration · ongoing · Clepto.io Services Pvt. Ltd.

Problem

SME clients across recruitment, property and professional services were each losing hours a day to the same shape of problem: information arriving in one system that a human had to retype into another, with judgement applied somewhere in the middle.

Approach

  • Newsletter production pipeline that drafts, sources and schedules end to end
  • Rental-platform chatbot handling tenant enquiries with escalation rules
  • Meeting capture and transcription pipelines via Vexa AI and Fireflies.ai
  • CV screening with structured scoring and a human review gate
  • Contract and invoice generation triggered from Telegram
  • MCP server integrations across HubSpot, Notion, GitHub, Workato and n8n
n8nZapierMCPAirtableNotionSlackGoogle OAuthTelegram

Outcome

Over 100 workflows in production across the client base, each one documented with a runbook so the client's own team can operate and amend it. Clepto.io runs to an ISO 42001-aligned management system with EU AI Act risk classification applied per workflow.

Trade-off

Every screening and scoring workflow keeps a human decision gate, even where the model is accurate enough to run unattended. It costs throughput. It also means no client has had to defend an automated decision they couldn't explain.

YouX Studio & Entertainer's FAQ — product builds for A Bodhi Tree Media

Product architecture & delivery · A Bodhi Tree Media, Indore

Problem

An integrated marketing communications agency wanted to move from selling services to owning products — but had no internal engineering function to take a concept from idea to running platform.

Approach

  • YouX Studio, an AI video intelligence product: positioning, architecture and investor-facing collateral
  • Entertainer's FAQ platform end to end — PRD, Supabase schema, build and post-launch fixes
  • Agency website rebuilt in Next.js with legal pages and technical SEO
  • Client pitch and proposal systems for the agency's own new business
Next.jsSupabaseClaude CodePostgreSQLVercel

Outcome

Two products taken from blank page to launched platform, plus a rebuilt agency web presence. I hold all three roles on this account — consultant on what to build, analyst on the specification, engineer on the delivery.

Trade-off

Writing a full PRD before touching code looks slow to an agency used to shipping campaigns in days. It is slow. It is also why the schema didn't need rewriting after launch.

KKAUNHAI — QR doorbell platform

Venture build · Clepto.io

Problem

Deliveries, visitors and service calls at a residence or unit all depend on the occupant being reachable — and on a stranger being able to reach them without knowing their number.

Approach

  • QR-triggered contact flow that connects a visitor to an occupant without exposing personal contact details
  • Platform architecture, market sizing and investor reporting
Product strategyTAM-SAM-SOMPlatform architecture

Outcome

A venture built and reported on inside Clepto.io — the same discipline applied to my own product that I apply to client work: risk classification, privacy-by-design on contact data, and a business case that survives being questioned.

Also shipped

CREEDA, a sports science platform deployed on Supabase; The Right Energy, a D2C commerce build; The Vital Co., AI-assisted video production; and white-label CRM/ERP platforms with RBAC, audit logs and real-time subscriptions.

Career

Analyst first. That's the whole advantage.

Five years of requirements work before any of this was called AI. It's why the specifications hold up.

Oct 2024 — present · Ireland & India

Clepto.io Services Private Limited

Founder · AI Automation Consultant

Building AI-powered automation ecosystems and custom platforms for SME and enterprise clients — RAG solutions, workflow automation and go-to-market systems.

  • React and Next.js client portals on Supabase, integrating APIs via MCP
  • 100+ n8n and Zapier workflows across Airtable, Notion, Slack and Google OAuth
  • White-label CRM and ERP platforms with RBAC, audit logs and real-time subscriptions
  • Langflow, Pinecone and Tavily embeddings with MCP-enabled context retrieval
  • GTM automation using TAM-SAM-SOM frameworks; AI transparency checklists
Oct 2024 — present · Indore, India

A Bodhi Tree Media

AI Automation Engineer · AI Consultant · AI Business Analyst

Holding all three roles across the agency's product and platform work — advising on what to build, specifying it, and delivering it.

  • Product architecture and delivery for YouX Studio and Entertainer's FAQ
  • Agency website rebuild in Next.js with legal and technical SEO foundations
  • Client-facing proposal and pitch systems
Apr 2023 — Sep 2024 · Dublin, Ireland

StarLink World

Digital Transformation Consultant

Digital transformation roadmaps aligning Salesforce and cloud solutions to business goals, with process optimisation and delivery for enterprise clients.

  • As-is / to-be process mapping improving operational efficiency by 40%
  • Experience Cloud portals, custom objects, workflows and Lightning components
  • Requirements workshops and training materials supporting tool adoption
Apr 2017 — Dec 2021 · Indore, India

Teleperformance

Business Analyst

Requirements analysis and data migration for Fortune 500 clients — where the CRM and business analysis foundation was built.

  • BRDs and FRDs for 10+ Salesforce CRM implementations, 95% stakeholder satisfaction
  • ETL migration of 100,000+ records to Salesforce at 98% data integrity
  • Process mapping in Visio improving operational efficiency by 20%
  • Salesforce dashboards tracking e-commerce seller KPIs for weekly ops reviews
Toolkit

Chosen per problem, not per habit.

Automation & analytics

n8nMakeZapierPower AutomateWorkatoGitHub ActionsDify.aiPower BILooker StudioTableauHex.tech

AI, models & coding

OpenAI APIClaudeClaude CodeGoogle AI StudioVertex AINotebookLMLlamaMistralPineconeCursorMCP

Enterprise systems

SalesforceHubSpotClay.comSlackMicrosoft TeamsGoogle WorkspaceMicrosoft 365JiraConfluenceAsanaTrello

Web & application development

ReactNext.jsVueTypeScriptJavaScriptNode.jsPythonPostgreSQLSupabaseFirebaseMermaid.js
Background

Business analytics, operations, and the standards that govern AI.

MSc Business Analytics
Dublin Business School, Ireland
2022–2023 · 2:1 · BI & visualisation, applied statistics & ML, data mining, requirements analysis
MBA, Operations & Marketing
Swami Vivekananda Institute of Management, India
2019–2021 · 72% · Operations, forecasting & modelling, brand strategy, digital marketing
B.Com, Taxation
Idyllic Institute of Management, India
2015–2018 · 73% · Accounting, Indian tax system, statistics, financial management
Currently going deeper on
Industrial IoT and sensor integration · multi-agent orchestration · AI compliance and risk · manufacturing process optimisation
ISO/IEC 42001AI management system
EU AI ActAI compliance
ISO 20000IT service management
Google Cloud AIPrompt engineering
Salesforce AdministratorCertified
Salesforce AssociateCertified
Salesforce Business AnalystCertified
Platform App BuilderSalesforce certified
Six SigmaYellow belt
Scrum FundamentalsSFC certified
Requirements AnalysisElicitation & analysis
Change ManagementCertified professional
Next step

Strategy first. Systems second. Scale always.

Bring me the process that everyone in your team complains about. We'll work out whether it should be automated, and if it should, I'll build it.