Available for new systems — Remote · Worldwide

FELU AI·DEV

Favour Adefelu Adeleye — AI Automation Expert & Software Developer

I build systems that remove the human bottleneck.

n8n pipelines, LLM integrations, and clean software — I take the repetitive work eating your week and turn it into something that runs itself.

n8n automation workflow routing lead emails from Emma Glober Movers' three inboxes to their team WhatsApp group
running in production · n8n + wassenger
SPECIALISMAI automation / software
STACKn8n · LLMs / JS · Python
CURRENTBooking Q3 ● 2 slots

Selected work

Proof, not promises.

03 / PROJECTS

PROJECT 01 — LIVE SYSTEM

Emma Glober Movers: leads → WhatsApp

Job leads from three inboxes routed straight to the team's WhatsApp group in real time — no manual checking or forwarding.

● live systemn8nOutlook (Graph API)Wassenger APICustom JS

Problem

Leads arrived via direct enquiries, Hipages and Findamover across separate Outlook inboxes. The owner hand-checked each one and forwarded winners to WhatsApp — delays and missed leads whenever he was busy, on jobs where speed to first contact decides who wins the booking.

Solution

A scheduled n8n workflow that polls all three inboxes in parallel, filters for genuine enquiries, reformats each one into a clean WhatsApp-ready message with custom JavaScript, and sends it to the team group via the Wassenger API — no human step in between.

RESULT → Owner removed as the manual bottleneck. Instant team alerts, faster first contact — zero extra admin.
Full case study →
n8n automation workflow routing lead emails from Emma Glober Movers' three inboxes to their team WhatsApp group
n8n workflow for a Telegram AI agent pulling real-time crypto market data — price, order book, and candlestick data across multiple tools

PROJECT 02 — LIVE AGENT

Crypto Market Data Agent: prices → Telegram

A Telegram-based AI agent that delivers real-time crypto market data on command — no exchange dashboards required.

● live agentn8nGPT-4oTelegramExchange APIsPrivate client project

Problem

A crypto trading client needed fast access to live market data without switching between multiple exchange tabs and dashboards for every price check — constant context-switching was slowing down decision-making.

Solution

Built a Telegram-based AI agent that pulls real-time market data on command. The client sends a symbol (e.g. "btc" or "eth 4h") and receives an instant, formatted report covering current price, best bid/ask, 24-hour stats, order book depth, recent trades, and candlestick data across multiple timeframes — all through a simple Telegram message.

RESULT → The client gets institutional-style market snapshots in seconds, directly from Telegram — no trading terminal required.
Need a live-data agent? →

PROJECT 03 — LIVE PIPELINE

Reel Scheduler: Sheets queue → Instagram + Facebook

An automated content pipeline for a social media agency that schedules, captions, and publishes Reels to Instagram and Facebook directly from a Google Sheets queue — no manual posting required.

● live pipelinen8nGoogle SheetsGemini APIMeta Graph APICloudinaryPrivate client project

Problem

The agency managed Reel publishing for multiple client accounts manually — writing captions, tracking scheduled times across a spreadsheet, and logging into Instagram and Facebook separately to post each video at the right moment. It didn't scale past a handful of clients, and consistent posting schedules were hard to maintain.

Solution

Built an automated pipeline that runs every five minutes, checking a Google Sheets content queue for the next Reel due. For each due item it pulls the video URL and details, generates platform-specific captions with Google Gemini, publishes to Instagram via the Meta Graph API (confirming processing status first), publishes the same Reel to Facebook Reels, then marks the spreadsheet row posted — the whole calendar runs from one sheet.

RESULT → Manual posting and caption-writing gone entirely — a consistent scheduled Reel calendar across multiple client accounts, zero added headcount.
Need a content pipeline? →
[REEL SCHEDULER IMAGE — 1600×700] Drop the real n8n flow screenshot at
assets/reel-scheduler.webp

Who builds this

The operator.

PROFILE

I'm Favour Adefelu Adeleye. I got into software to delete work — then discovered most teams are drowning in tasks a pipeline could do better than a human.

For 5+ years I've built workflow systems, LLM integrations and internal tools for movers, service businesses and ops teams. My rule: if you do it twice a week, it should be a system — documented, monitored, boring in the best way.

Tools I reach for — a considered list

n8n · OpenAI / local LLMs · Python · Node/TypeScript · Postgres · Docker · GitHub Actions · Gmail / Sheets / WhatsApp APIs · VPS + GitHub Pages.

Education

Self-directed engineering education — automation and AI specialisation built through shipped production systems rather than classrooms.

“If you do it twice a week, it should be a system — logged, retried, and boring.”

Off-hours: self-hosting everything — my own automation, media and backup stack runs from home, which is also why client systems are designed self-hosted first.

Favour Adefelu Adeleye, AI Automation Expert and Software Developer
0Manual reporting time cut — ReportFlow
0Missed leads since Emma Glober pipeline live
0Automation systems shipped & maintained

Track record

Experience.

TIMELINE

Freelance Automation Engineer

2024 — present · Remote / Worldwide

Design and ship production n8n + LLM systems for service businesses. 12+ systems live; retainers for monitoring and iteration.

Software Developer — Emma Glober Movers

2022–2024 · Remote

Built internal tools and integrations; first automation cut weekly reporting from 6h to minutes — the project that became ReportFlow.

Started in ops / support — Emma Glober Movers

2020–2022

Answered the tickets and assembled the reports I now automate. This is why my systems survive contact with reality.

Capabilities

A stack, organised like a system.

CLICK TO EXPAND

Production pipelines, not demos. Every flow ships with retries, logging and a human override.

  • n8n orchestrationdaily driver
  • LLM integration / RAGOpenAI · local
  • Webhooks · APIs · cronevent-driven

Clean backends and interfaces around the automation — so the system is usable, not just clever.

  • JavaScript / TypeScriptNode · APIs
  • Pythonscripting · ETL
  • Postgres · SQLitestate that survives

Self-hosted first. Your data stays yours; deploys stay boring and repeatable.

  • GitHub · Pages · VPSship path
  • Dockerself-host n8n/LLMs
  • WhatsApp · Gmail · Sheets APIsglue layer

How I work

Every engagement runs like this.

PIPELINE

Signature — input → process → output

01 / Input

The messy human trigger — an email, a ticket, a spreadsheet.

email.received →

02 / Process

Parse, classify, decide. LLM where judgment helps, rules where it doesn't.

parse() · classify() · route()

03 / Output

The action lands — message sent, sheet updated, human freed.

→ whatsapp.send · sheet.append
live demo · watch the log
› idle — press run.

Result

“FELU didn't build us a chatbot. He deleted an entire category of work — alerts, follow-ups, reports just happen now.”
— FIMIOJERINDE, Operations Lead, Emma Glober Movers

Next step

Have a system worth automating? Let's talk.

Tell me the task eating your week. I'll reply within 48 hours with an honest read: automatable or not, and what it takes. No pitch decks.

✓ Received — your mail client opened with the message addressed to me. I'll reply within 48 hours.