I design and deploy automated workflows and tailored AI systems that catch every lead, clear the busywork, and hand you back the hours your business was eating.
Speed-to-Lead: scraped or inbound leads get scored 1-10 by Claude, answered in my brand voice, routed hot or nurture, and logged to a CRM before any send fires — built on n8n running on my own server, tested on my own leads first. Includes a live interactive demo.
Set before the first node was wired.
Vallar Browser Agent: an open-source Chrome extension that lives in your side panel, reads the page, and clicks, types, scrolls, and completes multi-step tasks autonomously — with per-site permissions, confirmation gates for sensitive actions, and a user-defined blocklist. Runs on any OpenAI-compatible endpoint, including fully local models via Ollama or LM Studio.
View on GitHubAutonomy with brakes, modeled on Claude for Chrome.
The 40-second Speed-to-Lead film here wasn't cut in an editor. An AI motion pipeline (HyperFrames) storyboarded it, built every frame as code in the handlit design system, and rendered it — using the real numbers from a live run: score 9/10, reply out in 7.4 seconds. The same pipeline produces launch films for client products. Music: "Static Motion" — Kevin MacLeod (incompetech.com), CC BY 4.0.
Open the Full Case StudyI design lightweight, self-testing n8n workflows that clean, route, and transform your data. Out of your head, into code.
Tailored AI agents trained to handle your brand voice, automate customer audits, and draft high-converting proposals on-brand.
A custom AI agent built around your business flows — sales, support, and ops handled by one operating core that runs your playbook, not a generic bot.
Three stages, and you're free to stop after any one of them.
I read a short form about your business myself and send a report in one to two business days, free, no obligation.
For $1,500, I build and test one real automation end to end, and most pilots ship in two to four weeks.
If it's working, we move to ongoing care or a retainer, so the system keeps improving as your business changes.
I spent 15 years running operations in hospitality, gaming, real estate, and fitness — taking bookings, chasing leads, answering the same questions on repeat. I know where that work leaks time and money because I did it by hand for years before I automated any of it. Handlit is me: one person, based in the Philippines, building on self-hosted tools I control end to end. There's no team behind the curtain — every system on this page runs on my own operations first, before it goes anywhere near yours. Everything I build runs on your accounts, not mine. If I'm ever unavailable, you keep full access and documentation, and nothing you own depends on me staying reachable.
A two-minute form, read by me. It finds the waste loops and tells you honestly whether there's a build worth doing.
One workflow from your audit, built and shipped in two weeks. Small scope on purpose — you see it working before committing to anything bigger.
I become your automation department. A monthly partnership: new builds, monitoring, and a roadmap — instead of quoting every workflow separately.
Beyond the retainer: the AI Operating Partner (from $5,000/mo, custom-scoped) for when automation stops being a project and becomes how you operate. After a chat agent ships, the Agent Care Plan ($250–$400/mo) keeps it current.
If your contact page says "we reply within 24–48 hours," this is for you. I research your business the way a customer experiences it, then design and build the chat agent it actually needs — in your voice, with a clean hand-off to a human when it matters.
A plain-language report on how customers reach you today, where each path stalls, and which agent would close the gap. Useful even if you never hire me again.
Everything in the audit, then the build: a brand-matched agent on your website and your busiest channel, answering from your real content.
Your agent stays current after launch: prices, hours, policies, and the questions it couldn't answer last month — reviewed and fixed.
The research agent behind the audit is open source. Bring your own key, point it at any business, and it drafts the blueprint on your machine — nothing leaves it.
A free audit, no strings: tell me how your business runs in the short form here — two minutes, three fields — and I review it myself. No bots on this one.
Who it's not for: if inquiries are rare, or your week already runs without you, there's no build worth paying for yet — and the report will say exactly that instead of selling you one.
Start the Discovery AuditAll four are public repositories, with the run logs committed alongside the code. That's the proof on offer: read the code, run it on your own machine, check the numbers yourself.
A Chrome side-panel research agent. Point it at any business website; it studies the pages and drafts the full chat-agent blueprint — personality, the questions customers ask, scripts, and the numbers to watch. Bring your own key; runs on Ollama or any OpenAI-compatible endpoint, so nothing leaves your machine.
Get it on GitHub
Reads an inbox and sorts every message by what it actually needs — a reply, a task, or nothing — and drafts the replies worth sending. A logged run in the repo's evidence folder clocks 3.19 seconds.
Get it on GitHub
Drafts owner replies to customer reviews in the business's own voice, ready to approve and post. Three live executions logged in the repo, averaging 3.48 seconds each.
Get it on GitHub
Takes one finished piece of content and reshapes it for other channels without flattening the original voice. Logged runs ship in the repo's evidence folder.
Get it on GitHubYes. Everything runs on your own accounts — your email, your calendar, your customer list. Nothing lives on a rented platform tied to me. If we ever part ways, you keep the whole system, and I hand over documentation so someone else can maintain it.
I fix it. Every automation logs what ran and where it failed, so I can usually find the problem fast — most fixes turn around within a business day. For ongoing coverage after launch, there's the Agent Care Plan, $250–$400 a month.
I am one person, and I won't pretend otherwise. Everything gets documented as I build it, and since it runs on your own accounts, another automation professional could pick it up if it ever came to that. I'd rather be honest about capacity than promise round-the-clock coverage I can't staff.
Zapier and Make charge you per task the automation runs, and the bill climbs as your business grows. Self-hosted means a one-time build, no per-task fees, and the system lives where you can see it — not inside someone else's platform that can change its pricing or drop a feature.
Wise covers international transfers if you're outside the Philippines. If you're local, GCash, Maya, or a BPI bank transfer all work. Nothing is charged automatically — you get a reference code by email and pay on your own schedule.
Then I tell you that, and it costs you nothing. The Discovery Audit is free specifically so I can say "this isn't worth automating yet" without either of us losing money on the conversation.
The free audit report lands in your inbox in 1–2 business days. A Pilot Automation — one working piece, tested on real cases — usually ships in 2–4 weeks. Bigger builds get a timeline before any money moves.
I need enough access to build and test the automation — usually a login to the tool it connects to. I don't ask for more than that, and access can be revoked the moment the project ends, since you own the accounts, not me.
That's who this is built for. You don't touch code or settings after launch — you use it the way you already use email or your phone. If something needs changing later, that's what the Care Plan or a retainer covers.
Both, depending on the job. Repetitive steps get plain automation — cheaper and more reliable. Judgment calls, like reading a message and deciding how to reply, use AI. I don't reach for AI where a simpler rule does the job.
The Discovery Audit is a short form, read by me personally, with a report back in 1–2 business days — no pitch, no cost. If it's worth building, we talk next; if it's not, I'll tell you that instead.
// What happens next: submit the form and I read it myself — expect an email back from me, not an autoresponder, within two business days.