Open to product & AI engineering roles

~$32M in customer sales through a platform I built

I build AI products from idea to production. As the solo founder and engineer behind OctoFunnel, I connect full-stack engineering, product design, and an understanding of how customers run their businesses. The figure is combined customer sales through OctoFunnel funnels since 2022

Bali, Indonesia · UTC+8 · Open to relocation

A product I built, in my own wordsVIDEO
Preview of the OctoFunnel product demo
1,000+Lifetime platform customers
~$32MCombined customer sales since 2022
~5MEstimated lifetime contact records
Solo builderProduct, engineering & design

Customer figures are approximate and based on platform records. Sales belong to customers; they cover the platform’s history

Contact-record scale: verified count & lifetime estimate

The supplied database-check summary reports 2,087,071 verified contact records across 187 client installations, excluding our own platforms.

Approximately 5 million is the upper end of the supplied 3–5 million lifetime estimate, not a verified total. The estimate allows for closed or unreachable client sites, including assumed audiences for 387 historical sites with recorded sales whose contact counts could not be measured.

Records include leads, subscribers, and customers. A person can appear on several sites, and some contacts were imported. These counts do not establish unique people, paying customers, simultaneous active users, or contacts generated by the AI agent.

Source: the owner's supplied database-check screenshot. The underlying calculation and queries were not included in the attachment, and this workspace has not independently rerun the count. View the supplied source summary

The product

OctoFunnel
From idea to an operating business

Visit the product

A platform for digital entrepreneurs to build websites and sales funnels, deliver courses, and manage customer conversations. I brought those workflows together in one product and added an AI agent that can operate the same workspace through chat

Explore all platform features

Product & design

Shaped the product, designed the interface, and built workflows for entrepreneurs running websites, funnels, courses, and customer conversations

Engineering & operations

Built and operated the platform end to end. Developed the legacy PHP/MySQL system and the current TypeScript, React, and Node.js product

AI agent systems

Designed a shared virtual filesystem for the built-in AI agent and MCP-connected agents, with contextual instructions, validated changes, checkpoints, and durable execution

Distribution & customers

Developed the commercial model and a network of around 30 sales partners, using regular partner conversations to identify product needs

Platform capabilities

A complete toolkit
for running a digital business

I built connected tools for creating the product, finding customers, delivering the offer, and running the day-to-day business. AI assistance and visual editing bring those workflows into one workspace

16feature areas

One connected
business workspace

Explore the platform · 16 feature areas

Build & automate

AI building workspace

Turn a business idea into structured pages, content, and workflows through conversation

  • Built-in AI assistant
  • External AI agents connected through MCP
  • AI and visual editors working on shared data
  • Contextual playbooks and validated changes
  • Revision history and restorable checkpoints
Build & automate

Websites & landing pages

Create and publish the customer-facing home for a business

  • Visual page and content-block editing
  • Lead-capture forms and interactive quizzes
  • Custom domains and brand settings
  • SEO settings and public page structure
  • Customer proof cards and visitor comments
Build & automate

Visual sales funnels

Connect messages, pages, decisions, and offers into a customer journey

  • Graph-based workflow editor
  • Triggers, messages, pages, and actions
  • Conditions based on purchases and customer state
  • Delays, scheduled steps, and local-time follow-up
  • Variables, calculations, and weighted A/B branches
Build & automate

Business discovery & context

Give the AI useful source material about the customer’s audience, offer, and expertise

  • Structured business and offer briefs
  • Uploaded documents and personal source files
  • Searchable context attached to business resources
  • Lesson scripts and presentation preparation
  • Shared context across AI-assisted workflows
Connect & support

CRM & shared inbox

Keep customer records, conversations, and funnel progress connected

  • Contact records and customer cards
  • Funnel-stage boards and filtered contact lists
  • Messenger conversations in one inbox
  • Purchase and course-access context
  • Contact imports and team follow-up
Connect & support

Messenger chatbots

Let customers enter and continue the funnel in familiar messaging apps

  • Telegram bots and Telegram Business
  • Instagram messaging and comment-to-DM flows
  • WhatsApp connections
  • VKontakte and MAX connections
  • Chatbot menus and Mini App entry links
Connect & support

Customer-facing AI agents

Create conversational assistants that talk to the business’s customers

  • Editable identity, persona, and system prompt
  • Agent-specific document and knowledge libraries
  • Configurable models and stop conditions
  • AI-agent steps inside sales funnels
  • Human follow-up through the shared conversation
Connect & support

Broadcasts & communities

Reach an audience and manage ongoing membership in one workspace

  • Audience broadcasts and scheduled messages
  • Reusable message content and attachments
  • Telegram bot and group destinations
  • Paid Telegram subscription clubs
  • Membership access, expiry, and exceptions
Sell & deliver

Courses & homework

Deliver learning content and keep students moving through the experience

  • Structured courses and lesson content blocks
  • Video, images, documents, and presentations
  • Homework submission and reviewer queues
  • Human curators and AI-assisted review
  • Timed lesson release and customer access controls
Sell & deliver

Pricing, checkout & subscriptions

Connect an offer to payment records and the access a customer buys

  • Reusable pricing plans and checkout pages
  • Connected payment-provider integrations
  • One-time purchases and recurring subscriptions
  • Customer wallets and top-ups
  • Purchase records and paid-access fulfillment
Sell & deliver

Product catalog & commerce

Manage the products and variants behind a small online shop

  • Product pages and catalog collections
  • SKU variants, stock, pricing, and media
  • Product SEO and public storefront pages
  • Persistent shopping cart and checkout
  • Order details and fulfillment actions
Sell & deliver

Consultation bookings

Offer calls and services with a configurable appointment workflow

  • Consultation and call types
  • Direct assignment to a team member
  • Regular availability and date-specific overrides
  • Booking windows and scheduling buffers
  • Appointment management and cancellation rules
Create & grow

Images & visual design

Create the visuals used across pages, campaigns, and learning content

  • AI image studio with consistent campaign visuals
  • Image editing with text, elements, and effects
  • Instagram carousel design and slide content
  • Gallery for images, video, audio, and PDFs
  • Reusable media across the business workspace
Create & grow

Video & presentation tools

Prepare and produce the content behind a lesson or social campaign

  • AI-generated video clips and generation history
  • Visual Reels scripts and scene workflows
  • Branded video hosting and playback
  • Course presentations with editable slides
  • Video scripts and a mobile-friendly teleprompter
Create & grow

Team & everyday work

Organize the people, responsibilities, and material needed to run the business

  • Team members and granular role permissions
  • Kanban tasks with assignees and due dates
  • Comments and collaboration on work items
  • Nested notes with rich blocks and visual boards
  • Mobile-friendly, multilingual administration
Create & grow

Analytics & partner growth

Connect marketing signals, business activity, and partner programs

  • Website activity and funnel reporting
  • Google Analytics and Google Tag Manager
  • Meta, TikTok, VK, and Yandex tracking integrations
  • Affiliate rules, statuses, and network dashboard
  • Platform referrals and partner attribution

Engineering case study

One workspace
For people and AI agents

Read the technical case study

My key decision was to expose the platform’s business resources as a virtual filesystem. Both the built-in AI agent and agents connected through MCP inspect and change the same structured resources. Customers continue editing that data visually

The shared interface combines nine filesystem operations, contextual playbooks, and server-side validation. Checkpoints and durable execution help handle changes and interruption

AI agents + shared VFSCanonical shared dataValidated changes
One project · two ways to work

A shared workspace, from idea to live data

AI agentsBuilt-in chat · MCP
Virtual filesystem9 shared operations + contextual playbooks Permission checks · domain validation
Visual editorCustomer edits
Admin builderPages, funnels, courses and settingsHuman review and edits
Single source of truthCanonical project dataWebsites · funnels · courses · assistants
Both routes use the same saved resources; agents read and make validated changes through the VFS.

Recorded production activity

8 Sep–7 Oct 2026 · UTC
39,592AI agent tool calls
115Projects with agent tool activity
8,608Successful modification calls

Combined activity from the built-in AI agent and MCP-connected agents working through the same virtual filesystem. Verified from retained production records on 9 October 2026; calls include reading, navigation, and changes

Metric definitions and evaluation limits

24,706 built-in agent calls + 14,886 MCP calls = 39,592 recorded calls across 115 projects. 35,380 returned a successful technical result (89.36%); 8,608 of 11,954 write, edit, copy, move, or delete attempts succeeded (72.01%). Calls can repeat or make no effective change. 113 owner accounts used chat or MCP; 111 had recorded tool activity. The provisional cohort excludes configured operators and test-like accounts and may include staff-assisted activity. Logs can be incomplete or deleted. Customer acceptance, time saved, and cost per accepted task remain unmeasured. The original report records seven passing and two failing targeted tests

Read the evidence and source references

Customer outcome

Software that supports
a real customer business

Read Customer Case

Vitaly Okunev · platform customer

~$3.75M

Customer sales through the platform · approximate USD equivalent

I built the platform and funnel infrastructure the customer used. Its configured journey connects Telegram signup, four lesson pages, timed follow-up, homework, CRM, and a paid course. The customer brought the offer, audience, and business execution

687,104CRM contact records
10,322Purchase records
8,676CRM IDs with purchases

Approximately $3.75M in USD equivalent, using a fixed reference conversion consistent with the reported customer case. Contact and purchase counts were checked in the client database on 9 October 2026. This case contributes to the approximately $32M combined customer-sales total

Published OctoFunnel customer cases, including Vitaly O with more than $3.75 million in reported sales
Customer results shown on the OctoFunnel product website

The person behind the product

A founder’s ownership
An engineer’s hands

I’m looking to bring that ownership to a team building useful AI products. I enjoy turning a complicated workflow into something people can understand and use, working close to customers, and taking responsibility for the result

I started building this platform in 2019 and grew it through a partner network. The business continues to serve customers. I’m now seeking an engineering role where I can contribute that experience to a team and a new product challenge

I have worked with AI APIs since 2023 and have two years of experience building AI agents. Claude Code and Codex are part of my development workflow, alongside design, implementation review, and testing

Read my résumé
2019

The first platform

Started building the product to support an online education business

2022

MetaFunnels

Developed the business and partner-led distribution under the MetaFunnels name

2026

OctoFunnel

Introduced the current brand and AI-oriented TypeScript platform

Tools I work with

Current engineering stack

TypeScriptReactNode.js / HonoPostgreSQL / DrizzleRedisMCPViteTailwind CSSVitestPlaywright

Legacy platform: PHP, MySQL, JavaScript, and jQuery

Let’s build something useful

Looking for an engineer
who takes ownership?

Open to AI Product Engineer, Product Engineer, and Founding Engineer opportunities

kozyonicon@gmail.com

Working together

Based in Bali, Indonesia · UTC+8

Remote work; open to relocation

English: C1

Meeting window: 07:00–20:00 Bali

This is my scheduling window. Working hours and overlap can be agreed for the role