What I Built for
My Own Companies

The Problem

The founder was posting content at 11 PM, manually checking Amazon reviews every morning, and losing Buy Box to competitors for days before noticing. Customer comments sat unanswered for 48+ hours. Inventory ran out twice because nobody was tracking FBA stock levels. A 5-person team (content manager, social media, customer service, analyst, ops) would cost $300K+/year. He had product-market fit but was drowning in operations.

What I Built

• Multi-platform content engine: Publishes 35-40 posts per week across YouTube Shorts, Instagram Reels, Facebook Reels, and TikTok. 233 videos in rotation. Instagram Stories 3x/day. Zero manual posting.
• AI customer engagement layer: Automated comment responses on 3 platforms using Claude API. Spam filtering, brand voice consistency, contextual replies. Runs 3x daily, 365 days/year.
• Amazon intelligence system: Real-time review monitoring (700+ reviews, 4.6 star average), Buy Box tracking 4x/day with competitor hijack detection, daily automated P&L delivered via Telegram at 9 AM.
• Competitor price monitoring: Detects price changes, new sellers, and Buy Box losses. Alerts only when action is needed.
• Inventory forecasting pipeline: Tracks FBA stock levels, in-transit units, reserved quantity. Flags reorder points before stockouts hit.
• Unified command center: Telegram bot consolidating all alerts, reports, and controls into one interface. The founder runs the entire business from his phone.

Results

Timeline

Tech Stack

The Problem

Product was sitting in a Cleveland warehouse collecting dust. No CRM, no website, no online presence. The founder was cold-calling from a spreadsheet and getting nowhere. Hiring a sales team (2-3 reps + manager) would cost $250K+/year and take 3-6 months to ramp. Meanwhile, warehouse rent was burning $3K/month on unsold inventory.

What I Built

• Multilingual AI voice agent (the star of the show): A live conversational voice agent on ElevenLabs with custom voice profile that makes 100-200 outbound B2B cold calls per day in English, Ukrainian, and Russian. 40+ conversation scenarios, real-time objection handling, and warm-transfer of qualified prospects directly into the calendar. Sounds human, not robotic. Replaces 2-3 full-time SDRs at $10-15K/month in payroll.
• 25-page SEO-optimized website: Complete web presence from scratch: product pages, 4 application pages (driveways, patios, pool decks, commercial), 5 geo-targeted state pages, 11 SEO blog articles with full schema markup. All indexed and ranking.
• Automated social media presence: Facebook autoposting system running Mon-Fri with A/B tested hashtag sets. AI-powered autoresponder handles page comments 2x/day using Claude.
• Personalized B2B email sequences: Audience-segmented email campaigns with merge fields and automated follow-ups. Reply rates above industry baseline. Connected to Instantly.ai for delivery.
• Autonomous sales operations: AI handles market research, competitor analysis, email composition, and sales forecasting. The founder focuses on closing deals, not chasing leads.

Results

Timeline

Tech Stack

The Problem

The founder needed to enter NYC cold and was quoted enterprise lead database subscriptions ranging from $58K to $234K per year. On top of that, hiring even a small B2B sales team (2 reps plus a manager) would add another $250K+ in annual payroll. He couldn't justify either. Meanwhile, competitors with bigger budgets were locking up NYC contractors one by one.

What I Built

• Public-data lead intelligence pipeline: Integrated 8 free public data sources: NYC Open Data APIs (DCA licensed contractors, DOB building permits, HPD paint violations, HPD managing agents, job filings, license applications) plus Google Places and Yelp Fusion. The pipeline identifies buyers based on their actual operational signals, not a purchased contact list.
• Pain-based segmentation engine: Prospects are scored by buying intent, not industry. HPD paint violation data identifies property managers who must repaint by a compliance deadline. DOB permits flag contractors mid-project who need materials now. This is intelligence, not a database dump.
• Automated personalized outreach sequences: Segment-specific email campaigns personalized by borough, business type, and pain point. Subject lines A/B tested for open rate. Connected to Instantly.ai for delivery and tracking. Reply rates sit above industry baseline with zero human sales headcount.
• Autonomous sales operations: An AI orchestrator routes tasks to specialized agents for lead discovery, email personalization, bounce prevention, market research, competitor tracking, and forecasting. The entire outreach pipeline runs without a human in the loop.
• Sales simulation system: Built realistic prospect personas to test email sequences before launch. Forecasts conversion patterns, identifies objection patterns, and optimizes messaging pre-send.
• Single reporting dashboard: Automated daily digests to Notion: campaign metrics, reply rates, pipeline status. Full visibility without manual reporting.

Results

Timeline

Tech Stack