Back to Work
Next.js + Firebase + GeminiWebAIStrategy

Media & Consumer VC

AI-Powered Deal Sourcing for a Media & Consumer VC

A VC firm was sourcing deals the old-fashioned way — spreadsheets, manual research, and a lot of copy-pasting between tabs. I built two internal tools (a Sourcing Platform and an Intel Hub) that use AI-powered enrichment and multi-source web scraping to surface, score, and track deals in real time. The team went from spending 10-20 hours/week on manual sourcing to having a live pipeline that updates itself.

Enter a company name and website — AI enrichment handles the rest: description, social links, follower counts, sourcing grades, and more.

Scope

Sourcing Platform — investment sourcing platform

Intel Hub — retail intelligence hub

AI enrichment pipeline design

Real-time collaborative data infrastructure

Tech Stack

Next.js 15React 19TypeScriptTailwind CSSShadCN UIFirebase FirestoreFirebase AuthFirebase StorageFirebase Cloud FunctionsGoogle GenkitGemini AIBright DataPerplexity APIGoogle Maps APIGoogle PSERecharts

The Challenge

The client is a startup VC firm focused on media and consumer — music, entertainment, film, digital media, beauty, hospitality, and more. As a lean team without enterprise tooling, researching potential investments meant hours of manual Googling, scattered notes, and no structured way to enrich, grade, or track companies at scale.

The Approach

01

Started with the core problem: the team was spending hours manually researching every company. Built a Sourcing Platform to let them enter a name and website, then let AI do the rest

02

Designed the enrichment pipeline in phases — domain discovery, web scraping, AI analysis, social data extraction, and follower counts — each validating against multiple sources so nothing relies on a single data point

03

Added the tools the team needed around it: theme-based organization with drag-and-drop, a grading system, bulk CSV imports, and a real-time dashboard tracking ROI and pipeline health

04

Built an Intel Hub as a second tool for retail intelligence — analysts photograph store shelves, Gemini AI identifies every brand and SKU on sight, then enriches each with manufacturer data and maps it all geographically

Key Features

Multi-phase AI enrichment: domain discovery → web scraping → AI analysis → social data → consensus scoring

Four concurrent background processing queues for parallel enrichment

Hierarchical theme/folder management with drag-and-drop organization

Interactive dashboard with ROI tracking and sourcing grade distribution

Brand extractor for bulk CSV imports with automated domain discovery

Store walk photo analysis — Gemini AI detects every brand and SKU on retail shelves

Two-pass retail enrichment with Google Search grounding for manufacturer data

Interactive Google Maps view with intelligent markers per store location

A/B/C/D company grading system with pipeline tracking

Real-time Firestore listeners — all users see data updates instantly

The Results

~0

Companies / Week

0+

Hours Saved / Week

0

Days Saved / Year

$0

Cost / 1K Companies

~1,000 companies enriched per week at $10–15 in API costs — work that would take a full team 250+ hours done automatically

13,000+ hours of manual research eliminated per year — the equivalent of six full-time analysts

8,851 companies sourced, enriched, and graded in the system to date

Deal pipeline went from scattered notes and spreadsheets to a structured, searchable platform the whole team uses daily

Investment team now sees enriched company data in real time — research that used to take hours is ready in seconds

This project combined

WebAIStrategy

The best results come when strategy, systems, and web all work together.

See how the pillars connect

Got a project that needs this kind of thinking?

Tell me what you're trying to build. I'll tell you how I'd approach it.

Start a Conversation