kay2 ▸ whoami

Entry-level engineer who builds automation that actually ships.

Automation Engineer focused on AI-driven workflows, API integrations, and autonomous agents. I've designed, built, deployed and monitored 10+ real systems solo — most of them live and clickable below. Learning fast, shipping faster.

Seeking my first full-time role — open to junior, internship & contract
0
systems built solo
0 live
to click right now
AI · edge
agents & Cloudflare
solo
design → deploy
// what I build

Three things I automate well

From scattered manual processes to reliable, monitored pipelines. I handle the full stack — integration, logic, deployment, and ongoing maintenance.

[ workflow_automation ]

Workflow & Process Automation

n8n, Make.com, Zapier, and custom Python pipelines. CRM automation, lead gen flows, invoicing, onboarding, notifications — the boring stuff that costs businesses hours every week.

[ ai_agents ]

AI Agents & LLM Tooling

Autonomous agents built on Claude & OpenAI. Multi-model pipelines with fallback, RAG, tool use, and human-in-the-loop. Telegram/Discord bots that actually do work — monitoring, trading, customer support, data collection.

[ integrations ]

API Integrations & Data Pipelines

REST/GraphQL APIs, webhooks, OAuth, cron jobs, Cloudflare Workers, D1/KV/R2. Real-time data sync, ETL pipelines, web scraping, custom dashboards. If two systems need to talk, I wire them up.

// selected work

Automation in production

Live systems doing real work right now — not demos. Green dot = health check passing. Private systems show as case studies — full demos on request.

SynPolis

live

An autonomous AI agent city. A fleet of LLM agents earn standing, run an economy, and build real websites & games inside the world — multiplayer, persistent, on the edge.

Runs 24/7 with zero manual intervention — agents coordinate over Durable Objects.
WorkersDurable ObjectsKVmulti-agent
automated agent orchestration

Nexora

🔒 private

No-code AI agent builder — design an agent visually, train it on your docs, then deploy to Telegram, a web widget, a hosted page, or a REST API. D1 + KV, managed credits.

One visual build ships to 4 deploy targets — no code written by the user.
WorkersD1ClaudeRAG
case study · demo on request

Clive — Autonomous Trading Agent

🔒 private

A 24/7 autonomous AI agent that monitors markets, executes trades across Solana / pump.fun / Polymarket, and reports via Telegram. Multi-model with fallback, real-money pipelines, self-healing infrastructure. The ultimate automation case study.

Multi-model fallback (4 providers) keeps it running when any single LLM fails.
PythonNode.jsSolanaLLMTelegram BotPM2
case study · demo on request

DroidLoop

🔒 private

LLM-driven Android control over ADB — an agent that operates a real phone: reads the screen, taps, types, completes tasks. AI agency on physical hardware.

Completes real on-device tasks end-to-end — no human taps in the loop.
PythonADBvision LLMautomation
case study · demo on request

Stan Fleet — Multi-Agent Orchestration

🔒 private

A team of LLM agents — founder, scout, builder, warden and more — that claim jobs from a shared board, talk to each other, and ship real work. A dispatcher routes each task to the right agent and model over a typed event bus, with turn-taking rules.

Agents self-assign and finish jobs hands-off, each running its own model.
Node.jsPM2Claudemulti-agentTelegram
case study · demo on request

Fleet Ops & Scheduling

🔒 private

Cron-driven operations for a whole fleet of bots — scheduled agent missions, hourly usage and health reports pushed to Telegram, and automated digests, all running unattended on a Raspberry Pi.

Hands-off cron ops — scheduled missions and health DMs, zero manual runs.
cronPM2Telegram Botmonitoring
case study · demo on request

Persona Telegram Bots

🔒 private

A supervisor process running several real Telegram bots — each with its own persona and LLM — handling owner-only DMs plus group @mentions, with crash-proof pollers kept alive under PM2.

Multiple bots, each on its own model, supervised and self-restarting.
Node.jsTelegram Bot APIPM2multi-model
case study · demo on request

Agent Exchange

🔒 private

A live "stock market" for the agent fleet — every agent is priced like a coin, with candlestick charts generated from its real activity. Prices, trades and a running ledger update automatically every 15 minutes by cron.

Candlestick charts auto-built every 15 min from a live activity ledger.
Workerscrondata pipelinedashboard
case study · demo on request

Fleet Dashboards

🔒 private

Internal ops dashboards for the agent fleet — a shared "brain" board and a live status bar — that rebuild themselves from real activity on a cron, so the view is always current with zero manual updates.

Self-updating dashboards — rebuilt from live data on a schedule, hands-off.
Workerscrondashboardmonitoring
case study · demo on request

Stan Agent Wallets

🔒 private

A provisioning site that gives every agent a real on-chain Solana wallet — keys generated and vaulted server-side, with any fund-moving action guarded behind explicit confirmation and dry-run by default.

Every agent gets a real wallet; money paths are dry-run-guarded by default.
Node.jsSolanaweb3security
case study · demo on request

Six Stacks

live

A live-data product tracking the GTA VI creator economy — real Steam & market stats, served from a single Worker with its own tiny API and cron jobs.

Cron-refreshed live stats served from one Worker — no manual updates.
Workerslive APIcronautomation
automated data pipeline

TrailOS

live

An offline-first companion PWA for the New Forest — installable, works with no signal, full app polish. Demonstrates real PWA craft end to end.

Fully usable offline — installable, cached, works with zero signal.
PWAofflineWorkers
open trailos.uk

DevWorkDash — Ops Automation

🔒 private

Automated ops dashboard monitoring 15+ PM2 services. Health checks, auto-restart on failure, deployment tracking, log aggregation, and alerting — all running hands-off on a Raspberry Pi.

Monitors 15+ services and auto-restarts failures before I notice.
Node.jsPM2cronmonitoringauto-restart
case study · demo on request

PaddleZ

live

Real-time paddleboarding conditions — live tide & weather APIs, web-push alerts, and a daily cron forecast, all from one same-origin Worker.

Daily cron forecast + web-push alerts, fully automated from one Worker.
Workersweb pushKV
open paddles.trailos.uk

Chromebook Playbook

live

A power-user reference PWA for shipping real software from a Chromebook — AI, agents, the Claude SDK, CLI, SSH and deploy, all in one place.

Installable reference PWA — the workflow I use to ship everything here.
PWAreferenceWorkers
open chromebook.trailos.uk

Stan Chat

live

Product & landing page for a mobile cockpit that drives Claude Code from your phone — design, copy and marketing polish, shipped on its own domain.

Full product page — design, copy and deploy — shipped end-to-end solo.
Workersproductdesign
open stanchat.uk
// the fleet

I run a team of AI agents — they work while I sleep

On a single Raspberry Pi I built a fleet of LLM agents, each with its own persona, model and job. They claim tasks from a shared board, talk to each other, monitor the systems, scout opportunities and ship real work — and I supervise the whole thing from my phone over Telegram.

💼
Founder
strategy & delegation
Claude Opus

Sets direction, breaks the week into jobs, and hands each one to the right agent.

🔭
Scout
research & opportunities
Claude Sonnet

Hunts passive-income and market signals, then ranks them into a running ledger.

🔨
Forge
builder
Claude Sonnet

Turns approved ideas into shipped code, pages and tools — end to end.

🛡️
Warden
ops & safety
Claude Haiku

Runs health checks and money-path guardrails; catches failures before I do.

🎬
Curator
comms & content
Claude Sonnet

Packages progress into updates and posts them to the team and the channel.

📚
Archivist
memory
Claude Haiku

Keeps the shared board and logs current so nothing gets lost between sessions.

🃏
Jester
wildcard
Claude Fable

Throws in the lateral, creative takes the others would never reach for.

shared memory board typed event bus agents converse & take turns cron-fired missions per-agent scorecards priced on the Exchange PM2-supervised money-path guarded

Today they run my studio — research, builds, monitoring and reporting, 24/7, with barely a hand on the wheel. Tomorrow, this is the automation I'd stand up inside your team: agents that watch your systems, make the small decisions, and ship — so your people spend their time on the work only people can do.

It started as a way to give myself a team of one. It's become proof I can design, deploy and run autonomous systems that actually earn their keep.

// stack

What I build with

Edge-first. Everything below is in something I've shipped — not a wishlist.

Python TypeScript n8n Make.com Zapier Node.js REST / GraphQL APIs Webhooks Claude / Anthropic SDK OpenAI LangChain RAG Cloudflare Workers D1 / KV / R2 Durable Objects Cron / Scheduling PM2 / Process Management Telegram Bot API Docker Git / CI
// why me

What I'd bring to your team

I ship, not just tinker

Every project above is real and deployed — most are live and clickable right now. I learn by building things that run in production, not by collecting tutorials.

Full-stack, end to end

From API integration to database to frontend dashboard, I've taken projects the whole way solo — so I understand how the pieces fit and can pick things up quickly.

AI-native and hands-on

LLM orchestration, tool use, multi-model fallback, RAG — I've built real autonomous agents. It's where I'm strongest and where I most want to grow.

// let's talk

Looking for my first automation role

Seeking a full-time entry-level Automation Engineer position — also open to junior, internship, apprenticeship & contract work. If you need someone who already ships, let's talk.

Hire me →
Copied!