$ whoami ▍

Ryan Eromosele Osagiede

const ryan = new AI_Automation_Engineer();

I design and build AI agents and workflow automation that do real work for Kenyan businesses — answering customers, tracking stock, reconciling cash, chasing invoices — using n8n, Zapier, Make, Gumloop & OpenClaw.

ryan@kenya: ~

$ whoami

Ryan Eromosele Osagiede — AI Automation Engineer

$ cat skills.txt

zapier · zap · gumloop · n8n · make · openclaw · supabase

$ ls ./projects

intervio/  ecom-support/  jobhunter/  shop-hunter/  pipeline-doctor/  document-extractor/  deep-researcher/  qa-agent/  +5 in the roadmap

$ ▍

08projects shipped & on GitHub
06role-tailored CVs (1pg + 2pg)
06focused ideas in the build roadmap
07active automation workflows

// 01 · toolbox

The stack I build with — rendered the way I think about it:

// 02 · projects

Shipped, documented, and running — every project is a working system you can inspect, not a mockup.

main - pipeline-doctor

Pipeline Doctor AGENT

An agent that fixes failing test suites. It runs the tests, reads the failing code, writes a fix, then re-runs - looping until its own verifier sees the suite fully green.

$ loop: run tests - read code - write fix - verify - repeat $ stack: python - deepseek - zero dependencies
main - document-extractor

Self-Auditing Document Extractor AGENT

Extracts fields from messy invoices, validates the arithmetic, and fixes its own mistakes - recomputing totals and VAT until every document is clean.

$ loop: extract - validate - fix - re-validate - repeat $ stack: python - deepseek - zero dependencies
main - deep-researcher

Deep Researcher with Fact-Check Loop AGENT

Writes a report from its sources, then verifies every claim. Anything it cannot back up gets rewritten until the whole report is supported - no invented facts make it through.

$ loop: search - draft - fact-check - rewrite - verify $ stack: python - deepseek - zero dependencies
main - qa-agent

Autonomous QA Agent AGENT

Starts a live web app, runs test scenarios, and files bug reports with reproduction steps - refusing to finish until every failure is documented.

$ loop: run scenarios - detect failures - file bugs - verify coverage $ stack: python - deepseek - zero dependencies
main · intervio

Interv.io — Personalized AI Interview Coach LIVE DEMO

A memory-aware mock interviewer that asks one tailored question at a time and grades your answer — verdict, score, what was missing, and a model answer — then drills your weak spots across sessions. Runs locally in the browser and over WhatsApp via OpenClaw — a working live demo.

$ stack: react · vite · langchain/langgraph · deepseek-v4 · sqlite · openclaw $ memory: local-first markdown + sqlite hybrid search
main · ecom-support

Social Commerce Order Support & Returns Agent LIVE DEMO

A WhatsApp-first AI support agent for Kenyan e-commerce vendors. An LLM classifies customer intent, the agent answers order-status, product and returns questions from the shop's own data, creates RMAs, and escalates to a human — designed to cut response time from hours to seconds.

$ stack: n8n · ai-intent-classification · openclaw · whatsapp
main · jobhunter

AI Internship Job-Hunter RUNS DAILY

Searches Kenyan job boards daily for 6 target roles, matches each posting to a role-tailored CV, tracks applications, and pings WhatsApp when something new shows up. Built to make my own internship hunt systematic.

$ stack: n8n · myjobmag · google-sheets (soon) · whatsapp $ includes: 12 generated CVs
main · shop-hunter

Shop Hunter — WhatsApp Outreach Agent RUNS DAILY

Sends one honest WhatsApp message per day to approved shops and businesses offering workflow automation, AI agents, or websites — with an approval gate, a 5/day cap, and a permanent opt-out blocklist. Built to turn my automation skills into clients.

$ stack: n8n · openclaw · whatsapp · guardrails $ funnel: new → approved → contacted → replied → interested → won

// more AI agents & automation

// in the oven

Jua Kali Supplier Intelligence Supermarket Stock & Restock Cashier Cash-Reconciliation Freelancer Invoice Tracker WhatsApp Lead Intake SME Content Generator

// 03 - agentic workflow lab

Live interactive traces - watch each agent plan, call tools, and verify its own work. Powered by DeepSeek, 4/4 tasks passing. Full lab and eval harness: github.com/ryanreo/agentic-workflow-lab.

agentic-core-loop - the shared engine

pipeline-doctor - fixing a failing test suite

document-extractor - auditing its own extraction

deep-researcher - fact-checking its own report

qa-agent - finding bugs in a live app

// 04 · my other work

Trading bots, health tools, and other projects outside the AI-agent world.

// 05 · about

Software Development student at KCA University (2023–2026) and freelance web developer who fell into AI automation and never looked back. I build practical, low-cost, Kenya-ready systems — WhatsApp, SMS, USSD, M-Pesa — for the SMEs and informal-sector businesses that automation usually ignores.

My superpower: turning a business problem ("cashiers spend an hour counting the till") into a working, logged, human-approvable AI workflow.

I'm currently focused on landing an AI automation / agent development internship where I can take these systems from working demos to production.

const ryan = {

  location: 'Nairobi, Kenya',

  focus: 'AI agents for Kenyan SMEs',

  stack: ['n8n', 'zapier', 'make', 'gumloop', 'openclaw'],

  education: 'BSc Software Development · KCA',

  status: 'building in public',

};

// 06 · contact

Have a workflow that's eating your team's time? Let's automate it.