Philippines · Remote
Available for Projects

Jam Susana AI Automation Specialist_

I build n8n pipelines, AI agents, and data systems that actually run in production — connected to BigQuery, Supabase, and Vercel.

n8n
BigQuery
Supabase
Vercel
Claude Code
RAG
ETL
GoHighLevel
24+
Live Pipelines
12K+
Records via ETL
90%
Manual Effort Cut
01What I Can Build For You

Document Generation Pipelines

Webhook-triggered pipelines that pull data from BigQuery or Supabase, run it through an LLM, and produce structured docs — zero manual steps.

Lead Enrichment & Scoring

Multi-source enrichment pipelines that cross-reference patent DBs, academic records, LinkedIn — then score and route leads automatically.

Telegram & Community Bots

AI-powered onboarding agents, pairing bots, and digest engines for Telegram communities — fully automated with Supabase-backed state.

ETL & Data Pipelines

Data extraction, transformation, and loading between any stack — APIs, databases, spreadsheets. Clean, validated, structured output every run.

RAG & Knowledge Systems

Vector-search pipelines using Pinecone or pgvector — retrieve the right context, combine with live data, generate accurate structured outputs.

Agentic AI Workflows

Multi-step AI agents that plan, retrieve, execute, and loop — built in n8n with proper error handling, retry logic, and structured outputs.

02How I Work
01

Discovery

Understand the workflow, existing stack, and where the manual pain actually is.

02

Architecture

Map out nodes, data sources, error paths, and outputs before touching n8n.

03

Build

Wire it up — n8n, Supabase, BigQuery, Vercel. Real integrations, real data.

04

Test & Refine

Edge cases, error handling, retry logic. Only prod-stable pipelines get signed off.

05

Shipped

Handoff with docs, monitoring, and a walkthrough — so your team can own it.

03Pipelines Shipped
All Projects →
The Graph CoinGecko React Query 6 Dashboards
Real on-chain data · Demo-mode fallback

Uniswap V3 Analytics

Rebuilt a mock-data dashboard template into a real DeFi analytics product — live subgraph data, IL calculator, address lookup, and full TS + test coverage.

ReactTypeScriptThe Graph View Live ↗
Cap Nur Sales Post Onb Ret Re-Act reactivation loop
7 stages · Full lifecycle automated

GHL Customer Lifecycle System

End-to-end GoHighLevel automation: lead capture through retention and win-back, with AI-enhanced nurture and behavior-based branching.

GoHighLevelCRMAI View Diagram ↗
Patent DB n8n ETL Academic Supabase
12K+ records · 90% effort cut

Global Talent Scout — ETL

Multi-source enrichment cross-referencing patent DBs, LinkedIn, and academic records via n8n + Supabase.

n8nSupabaseETL View Diagram ↗
Webhook n8n Pinecone BigQuery LLM
5× faster · 95% output alignment

RAG Agentic Workflow

Intelligent RAG agent combining vector search and live BigQuery queries to generate structured document outputs.

n8nBigQueryRAG View Diagram ↗
Telegram member AI Agent n8n Supabase Pairing Reply
+40% onboarding completion

Community Automation Suite

AI-powered Telegram onboarding agent and Random Coffee pairing engine — Supabase-backed state, fully automated.

n8nTelegramAI View Diagram ↗
Sched GitHub API Filter Dedupe Sheets Bot →TG WF1 WF3 3 workflows · weekly · on-demand
3 workflows · self-healing CFP data

Tech Events Bot — Automation System

3-workflow n8n pipeline: weekly data ingestion from GitHub + public API, new-events discovery with team email digest, and on-demand Telegram bot delivery with paginated CFP results.

n8nTelegramSupabase View Diagram ↗
Intake Pinecone BigQuery LLM Doc Out
Retrieval-augmented · adaptive tone

AI Document Generation System

A retrieval-augmented document generation pipeline for a UK startup client: vector search over prior examples combined with live structured data, automatic document generation, and reviewer sign-off built into the flow. Tone and structure adapt per recipient to avoid a templated feel.

n8nPineconeBigQuerySupabaseGemini
Name+URL Scrape Score Rubric verified end-to-end vs. real candidates
editable rubric · admin scoring panel

AI Candidate Scoring Pipeline

Submit a name and LinkedIn URL; the system scrapes public profile data and scores the candidate against a fully editable, multi-criteria fit rubric via an admin panel. Verified end-to-end against real candidates.

n8nApifyClaude APISupabase
Ingest Tag+Dedupe Digest Out Client Match
email + Telegram delivery · CSV export

Automated Digest & Client-Matching Engine

Weekly content digest with a searchable, filterable archive and CSV export, plus email and Telegram subscription delivery. A companion matching layer scores relevance against uploaded client profiles by extracting tags from PDFs via AI.

n8nSupabaseTelegram Bot APIClaude API
Template Fill Fields NDA / SOW
NDA + Services Agreement · fixed terms

Client OS — Legal Agreement Templates

A structured NDA and services-agreement template system matching WanderingTech's actual fixed-price, 50% deposit engagement terms — ready to fill in and send for any new client.

Word / OOXMLContract Automation
Name+Domain Rubric Score Pipeline View
4-dimension rubric · deterministic demo scoring

ScoutOS — Candidate Intelligence Demo

An independent exploration of multi-criteria candidate scoring, built from scratch with its own logic and synthetic sample data — not derived from any employer's codebase. Enter a name and target domain, get a structured fit score across four rubric dimensions, plus a sortable, filterable candidate pipeline view.

Vanilla JSPersonal Project
Meta Lead Pipeline Won / Lost
6-stage kanban · activity log · human takeover toggle

SiteFlow — Lead Management CRM Concept

A concept demo for a Meta-Ads-to-close lead management system for trade businesses — built independently, with fully synthetic sample data. Dashboard with conversion/pipeline-value stats, a drag-free Kanban pipeline (New → Contacted → Qualified → Quoted → Follow-up → Won/Lost), and a lead detail view with a full activity timeline and an automation on/off toggle for human takeover.

Vanilla JSPersonal Project
Traveler Partner QR + Seal Ops Console
5 transit hubs · QR + tamper-seal verification

BagDrop CDO — Peer-to-Peer Luggage Storage

A two-sided marketplace connecting travelers with local storage partners across Cagayan de Oro's transit hubs. Six-step booking flow with transparent, itemized pricing and an optional insurance add-on; pickup verified by matching a scanned QR code against the tamper-seal number logged at drop-off. Separate consoles for partner counters (daily drop-off/pickup board, payouts) and marketplace ops (partner approval, dispute resolution).

SupabaseMulti-tenant
QR Verification View Live Prototype ↗
In Development
Currently building

Automated Invoicing System

An end-to-end invoicing pipeline replacing manual, spreadsheet-based billing — automated generation, status tracking, and reminders. In active development; full case study coming once it ships.

In Progress

Tools & Tech Stack

04About

I build automation systems that actually run in production.

Currently Technical Project Manager at Immigram (UK), shipping n8n pipelines connecting APIs, databases, and AI models — from lead enrichment at scale to intelligent agentic workflows. Backends are BigQuery and Supabase. Deployments on Vercel.

Background in mechanical engineering and data analysis — financial tracking pipelines, multi-source datasets, and dashboards at ReCool Technologies. That data ops foundation makes the automation work cleaner.

One year deep into this. Still learning fast, still shipping. If your team is sitting on manual processes that should've been automated yesterday — that's the kind of problem I enjoy.

What I Automate

n8n WorkflowsLead Enrichment RAG AgentsETL Pipelines AI OnboardingPatent Intelligence Multi-Source EnrichmentTelegram Bots CRM AutomationAPI Integrations Agentic WorkflowsCompetitive Intelligence

Technical PM — AI & Automation

Immigram · UK

2025

Freelance Data Analyst

Independent

2024

Research Analyst

ReCool Technologies

2022

Currently Building

WanderingTech CRM

A personal lead pipeline dashboard backed by Supabase — built to manage freelance projects end-to-end.

05Certifications
View All →

GoHighLevel — Level 3 Certified

Extendly

2025

Google Project Management Professional

Coursera

2025

Google Data Analytics Professional

Coursera

2025

Data Analysis in Tableau

DataCamp

2024
06Tech Stack
Full Stack →

Automation & Integration

n8nWebhooks & APIsGoHighLevelTelegram BotClaude Code

Data & Infrastructure

BigQuerySupabase · PostgreSQLSQL · ETLPineconeVercel

Dashboards & BI

TableauPower BILooker StudioGoogle Sheets
07Recommendations

"Jam was hands-on with our AI-powered onboarding bots, prospecting pipelines, and intelligence dashboards. His work helped provide the data we needed to make better decisions and grow the business. He's reliable, communicates clearly, and genuinely enjoys the nuts and bolts of how automations work. I believe he has a very bright future ahead."

MF

Maria Azaryan Fainberg

Head Of Business Development · Immigram (UK)

Working together? I'd love to feature your experience here.

Book a Call →
08Contact

Book a Call

Schedule a Session →

Location

Philippines · Remote

Availability

Open to Projects

← Back

All Projects

Personal Project · DeFi Analytics Live View Live Dashboard ↗

Uniswap V3 Analytics — Real-Time DeFi Dashboard

A six-page Uniswap V3 analytics product pulling real on-chain pool, swap, and LP position data from The Graph — rebuilt from a mock-data template into a working data product with its own quant tooling.

Problem

Started from a template where every dashboard — pool performance, LP analytics, live trading, risk management — rendered hardcoded mock arrays. No real data, no working exports, fake "live" updates via setInterval.

Solution

Rebuilt the data layer on The Graph's Uniswap V3 subgraph and CoinGecko behind React Query hooks, with an automatic demo-mode fallback so the app still runs fully without an API key. Migrated the whole codebase to TypeScript, and added an impermanent-loss calculator with the real concentrated-liquidity V3 math, a read-only address lookup for any wallet's LP positions, working pool comparison/watchlist/CSV export, and dark/light theming — plus Vitest coverage and CI.

Impact
6Live dashboards & tools
44Unit tests (Vitest)
100%Mock data → real API
0Wallet connect surface
Stack
React + TypeScriptThe GraphCoinGecko APIReact QueryRechartsVitestGitHub ActionsVercel
Features
Pool performance, LP analytics, live trading & risk dashboards on real subgraph data
Impermanent-loss & fee-breakeven calculator (concentrated liquidity math)
Read-only address lookup for any wallet's LP positions — no wallet connect
Pool comparison, persisted watchlist, working CSV export
Demo-mode fallback keeps the app fully functional with zero API keys
Freelance · CRM Delivered View Diagram ↗

GHL 7-Stage Customer Lifecycle Automation System

End-to-end GoHighLevel automation architecture: lead capture through retention and win-back, with behavior-based branching, AI-enhanced nurture sequences, and a reactivation loop feeding back into Stage 2.

Problem

Client had a functional GHL account but every stage of the customer journey required manual intervention — leads weren't being nurtured, post-call follow-ups were inconsistent, and churned clients had no re-engagement system.

Solution

Designed and built a 7-stage automated lifecycle — from landing page capture to reactivation — with conditional branching based on engagement, lead scoring thresholds, outcome-based post-call flows, and a lapsed-client win-back loop that re-enters at Stage 2.

Impact
7Automated lifecycle stages
ZeroManual follow-up steps
4Post-call outcome paths
AINurture & reply drafting
Stack
GoHighLevelGHL Workflows Email + SMSLead Scoring GHL CalendarProposals & Invoicing AI ContentSmart Lists
Stages Delivered
Lead Capture — funnels, forms, attribution
Nurture — behavior-based email + SMS drip
Sales Pipeline — booking, reminders, tasks
Post-Call — proposals, invoicing, outcome flows
Onboarding — welcome, intake, handoff
Retention — NPS, reviews, upsell triggers
Reactivation — win-back, renewal, lapsed re-entry
Internal Tool · UK Startup Live Optimizing View Diagram ↗

Multi-Signal Talent Intelligence Platform

A Vercel-deployed internal tool that launches and configures six n8n discovery pipelines to surface high-value technical candidates by cross-referencing global patent databases and academic records.

Problem

Manually searching for technical talent across patent filings, Google Scholar, and LinkedIn was taking hours per candidate with no standardized scoring — impossible to scale without a larger team.

Solution

Built a configurable pipeline launcher where the operator selects a discovery strategy, sets scoring thresholds, picks target countries from a tiered 37-country list, and fires a structured payload to the appropriate n8n webhook.

Impact
12K+Records processed
6Discovery pipelines
37Countries targetable
95%Alignment with vetting
Stack
Verceln8nPatent APIsAcademic APIsSupabaseGoogle Sheets
Pipelines
Patent Discovery
Academic Record Discovery
Patent × Academic Cross-reference
Academic × Patent Cross-reference
Media & Mentions Track
Social Signal Discovery
Personal Project Live Optimizing View Diagram ↗

WanderingTech CRM — Personal Lead Pipeline Dashboard

A full-stack freelance pipeline tool — from automation scoping form to real-time Kanban board backed by Supabase.

Problem

No structured way to track inbound leads, understand what they needed before a call, or move projects through stages without relying on spreadsheets and memory.

Solution

Built a portfolio site with an embedded 6-step automation scoping form. On submit, data inserts directly to Supabase and the lead appears live in a password-gated CRM — complete with Kanban board, full brief modal, and Calendly pre-filled with the client's details.

Impact
6Step scoping form
Real-timeSupabase → CRM sync
5Pipeline stages
4Analytics charts
Stack
VercelSupabase · PostgreSQLVanilla JSCalendlyn8n Webhook
Features
Automation scoping brief (6 steps)
Real-time Supabase insert on submit
Kanban board with live status updates
Lead modal with full brief + notes
Telegram notification via n8n — in progress
Personal Project Live View Live Prototype ↗

ScoutOS — Candidate Intelligence Demo

An independent, self-contained demo exploring multi-criteria candidate scoring — no backend, no real data, no scraping.

Problem

Wanted to demonstrate a talent-scoring UX pattern — structured rubric breakdown, verdict, sortable pipeline — without touching any employer's real system or data.

Solution

Built a fully client-side app from scratch: a deterministic scoring function (seeded from name + domain, no network calls) drives a rubric breakdown across four dimensions, plus a sortable/filterable candidate pipeline view seeded with fabricated sample data.

Impact
4Rubric dimensions
0Network calls
100%Synthetic data
Stack
Vanilla JSNo BackendDeterministic Scoring
Features
Name + domain → rubric-scored fit breakdown
Verdict badge (Strong Fit / Consider / Not Yet)
Sortable, filterable candidate pipeline table
Dashboard with sample activity feed + stats
Personal Project Live View Live Prototype ↗

SiteFlow — Lead Management CRM Concept

A concept demo for a Meta-Ads-to-close lead management system for trade businesses — no backend, no real leads, fully synthetic sample data.

Problem

Wanted to demonstrate a full lead-to-close CRM pattern — Kanban pipeline, activity logging, human-takeover control — for a client pitch, without building on any employer's real system or client data.

Solution

Built a fully client-side app from scratch: a seeded sample lead set drives a 6-stage Kanban board, a searchable/sortable leads table, and a lead detail drawer with a generated activity timeline (lead received → confirmation → sequence → reply detected → quote → won/lost) and an automation on/off toggle representing human takeover.

Impact
6Pipeline stages
0Network calls
100%Synthetic data
Stack
Vanilla JSNo BackendDeterministic Sample Data
Features
Dashboard: conversion rate, pipeline value, won/lost stats
6-stage Kanban with searchable cards
Lead drawer with full activity timeline
Automation on/off toggle — human takeover
Won/Lost tracking with lost-reason capture
UK Startup · Production Live Optimizing View Diagram ↗

RAG Agentic Workflow — Intelligent Document Automation

An end-to-end AI pipeline that retrieves context from a vector database, queries live BigQuery data, and generates structured outputs — deployed on Vercel, triggered via n8n.

Problem

Complex document workflows required manually retrieving information from multiple sources and drafting structured outputs — taking 2–4 hours per cycle with inconsistent results.

Solution

Built a RAG pipeline in n8n using Supabase (pgvector) as the vector staging layer and BigQuery as the production data backend.

Impact
2–4hrsSaved per doc cycle
RAGVector + BigQuery in one flow
Stack
n8nSupabase · pgvectorGoogle BigQueryPineconeGemini EmbeddingsLLM · Prompt Engineering
UK Startup · Production Live View Diagram ↗

Community Automation Suite — Onboarding & Engagement Bots

Two Telegram bots: an AI-powered onboarding agent and a Random Coffee pairing engine.

Problem

Onboarding was manual and inconsistent. Weekly team connections (Random Coffee) had no follow-up system.

Solution

Built two bots. The onboarding agent uses a conversational AI persona to guide new members and verify profile status against Supabase. The pairing engine runs weekly, generates pairings, sends introductions, and follows up automatically.

Impact
+40%Onboarding completion
+35%Weekly engagement
Stack
n8nTelegram Bot APISupabase · PostgreSQLAI Persona Design
UK Startup · Production Live View Diagram ↗

Tech Events Bot — Conference CFP Automation

A linked set of n8n workflows that track developer conferences and CFP deadlines — ingesting from external sources, deduplicating, refreshing stale data automatically, and delivering results to Telegram on demand.

Problem

Stale and past events were showing up in digests because filtering had no lower date bound, and previously-missing CFP details never got backfilled once a record was written.

Root Cause Fixed

Rebuilt the date-filtering logic with a proper two-sided window, and switched the write strategy from append-only to an upsert pattern so records self-heal as new data becomes available.

Impact
LinkedWorkflows
MultiData sources
AutoSelf-healing data
0Past events in results
Stack
n8n Supabase Telegram Bot API External REST APIs JavaScript / Code nodes
Delivered
Scheduled data ingestion & normalization
New-events discovery with team notifications
On-demand Telegram bot delivery
Two-sided date-window filter fixes
Self-healing upsert write strategy
Category taxonomy normalization
UK Startup · Production Live View Diagram ↗

Capital Opportunity Mapping Pipeline

A structured funding intelligence pipeline that tracks, scores, and prioritizes capital programs — replacing manual grant research with automated scored shortlists.

Problem

Researching funding opportunities was entirely manual — no consistent scoring, no prioritization system, and no way to track status across multiple programs.

Solution

Built an n8n pipeline that ingests opportunities, scores each across 12+ vetting metrics, and outputs a ranked structured shortlist covering programs up to £5M.

Impact
12+Vetting metrics per opportunity
£5MFunding range covered
100%Manual research replaced
Stack
n8nStructured Data ModelingAutomated ScoringGoogle Sheets
UK Startup · Production Live View Diagram ↗

Community Intelligence Dashboard

A Google Sheets KPI system benchmarking 22 global talent communities across 7 platforms.

Problem

No structured view of how target communities performed across platforms — impossible to prioritize partnerships based on actual engagement data.

Solution

Built a multi-tab Google Sheets dashboard aggregating follower counts, engagement rates, and platform dominance metrics across 22 communities.

Impact
22Communities benchmarked
~7MFollowers analysed
7Platforms tracked
Stack
Google SheetsPivot TablesKPI DesignData Visualization
← Back

All Certifications

GoHighLevel — Level 3 Certified

Extendly · 2025

Google Project Management Professional

Coursera · 2025

Google Data Analytics Professional

Coursera · 2025

Lean Six Sigma Yellow Belt

MF Business School · 2025

Lean Six Sigma White Belt

MF Business School · 2025

Data Analysis in Tableau

DataCamp · 2024

Registered Mechanical Engineer (RME)

PRC Philippines

← Back

Tech Stack

Automation & Integration

n8nWebhooks & API IntegrationGoHighLevel (L3)Telegram Bot APIClaude CodeMulti-step PipelinesWorkflow Orchestration

Data & Infrastructure

Google BigQuerySupabase · PostgreSQLSQLETL ProcessesPinecone (Vector DB)Data Validation & CleaningVercel

AI & Agentic Systems

RAG ArchitecturesLLM Prompt EngineeringGemini EmbeddingsAI Persona DesignAgentic Workflow Design

Dashboards & BI

TableauPower BILooker StudioGoogle Sheets (Advanced)KPI Dashboard Design

Project & Operations

Monday.comNotionAdvanced ExcelGoogle Project ManagementCross-functional Collaboration
← Back

Book a Call

Before we talk, tell me a bit about your situation. This takes 3 minutes and means our call goes straight to solutions — no back-and-forth on basics.

01 / 06 — About You
Agency Owner
Startup Founder
Operations Manager
Freelancer
Enterprise Team
Other
02 / 06 — The Problem
Manual data entry taking too long
Leads falling through the cracks
Copy-pasting between tools constantly
Follow-ups not happening on time
No clear view of pipeline or status
Reports take hours to build manually
Team notified too late or not at all
Client onboarding is slow and messy
Too many tools not talking to each other
Can't scale without hiring more people
Repetitive tasks eating team time daily
No system — everything runs on memory
Form Submission
New Lead
Scheduled
Manual Action
Email / Message
Payment
Not Sure
Multiple Times a Day
Daily
Weekly
Monthly
03 / 06 — Your Current Stack
GoHighLevel
n8n
Zapier
Make
HubSpot
Notion
Airtable
Google Sheets
Slack
Telegram
Shopify
WhatsApp
Typeform / JotForm
None Yet
CRM
Sheets / Airtable
Slack / Telegram
Email
Database
Dashboard
Not Sure
04 / 06 — Intelligence & AI
Pure automation
AI classification / scoring
AI content generation
AI data extraction
AI agent / chatbot
Not sure yet
05 / 06 — Scope & Timeline
No — first time
Tried manually
Tried a tool
Have something partial
ASAP
Within 2 Weeks
Within a Month
Just Scoping
Under $300
$300–$800
$800–$2,000
$2,000+
Not Sure
06 / 06 — Let's Connect
Weekday Morning
Weekday Evening
Weekend
Flexible

Brief received — now pick a time.

I'll come to the call reviewed and ready with a rough plan.

What I Help With

n8n workflow design & optimization

GHL + n8n agency integrations

Data pipelines (BigQuery, Supabase, ETL)

AI-powered workflow automation

Lead scoring & CRM automation

Why the Form?

So our call goes straight to your solution — not basics. Most calls end with a clear plan in 30 minutes.

Or Just Email

jamel.mama@gmail.com

WanderingTech_

Got Questions?

Not ready to book a call? Ask me anything — about my work, pricing, or whether I can help with your situation. I'll reply within 24 hours.

Or email directly: jamel.mama@gmail.com

Message sent!

Thanks for reaching out. I'll get back to you within 24 hours — usually much sooner.