AI Builder Portfolio 2025–2026 7 tools shipped

Built, not
commissioned.

Python · Anthropic API · React · Next.js · Netlify · Vanilla JS

Seven tools, pipelines, and data products I built as core infrastructure for a global nonprofit accelerator managing 4,486 startups. When generative AI landed commercially, I stopped waiting for a data team and started building. The same pattern I recognized at One Degree Solar with LED costs in 2011, and at Formlabs with desktop SLA in 2017: a technology crossing a threshold.

§ 01 · Why I built these

The operating question was: what does AI actually unlock for a lean team?

By early 2024, MassChallenge had 4,486 alumni companies in a database with no reliable sector taxonomy, no way to search by pitch text, no survival model, and no operational tooling that wasn't living in spreadsheets or static decks. A data team request would have taken months. I built the foundation in weeks.

The classifier came first. That unlocked the Explorer. The Explorer unlocked the Dashboard. The Dashboard unlocked the LinkedIn data journalism series. Each tool was infrastructure for the next one. The order mattered.

Everything here was built solo. Python/pandas for data work. Anthropic API directly for classification and content generation. Netlify for static deploys and serverless functions. No frameworks that required a build pipeline. No IT tickets. That's the point: a non-traditional technical operator who can ship working tools rather than spec them for someone else.

7 Tools shipped
4,486 Companies indexed
$27.1B Funding analyzed
100M+ Rows processed
§ 02 · The projects

Seven tools. Each one solving a real operational problem.

01 · Agentic Platform
3-Pass Agentic Evaluation Platform Deployed

Crucible

Most accelerator programs evaluate companies the same way: spreadsheets, gut feel, and whoever has the most domain knowledge in the room. Crucible replaces that with something more rigorous. An HC&LS company submits an application; within minutes the system has run live web research on the founders and market, looked up their FDA regulatory pathway, pulled CMS reimbursement data, and scored them across four frameworks: IDEO human-centered design, MIT Disciplined Entrepreneurship, Clinical Science maturity, and a Revenue Bridge analysis. That used to take a program team days.

The architecture is three-pass, not a wrapper. Sonnet with web search runs the initial evaluation and captures every query it ran and what it found. Haiku critiques the output against four specific criteria: FDA pathway accuracy, reimbursement specificity, risk severity calibration, and score-recommendation alignment. If it flags a problem, Sonnet revises only the failed fields. The reasoning trace is visible in the UI, collapsed by default. Specialists, who only see applications the AI flagged for genuine domain uncertainty, see more of it. Their time is treated as the scarcest resource in the system.

The scoring rubric is built around one question: does this company's survival depend on a future binary event it can't control? A regulatory approval it hasn't gotten. A reimbursement code that doesn't exist yet. The top band (90–100) is reserved for companies that don't have that dependency. The demo cohort is 12 real HC&LS companies, all publicly raised Series A: Hippocratic AI, Tennr, Abridge, Rad AI, Eko Health, Proprio, Cala Health, Pomelo Care, Nourish, Avenda Health, Proscia, and Boundless Bio. Every evaluation runs on publicly available information only.

Stack React (Vite), Netlify, Neon Postgres, Clerk (magic-link), Resend, Anthropic API. No GitHub; deployed via Netlify CLI. Built with Claude Code across approximately 7 sessions. Architecture Sonnet + web search (eval + reasoning trace), Haiku (domain-specific critique), conditional Sonnet (revision of failed fields only). Comparative analysis across five dimensions available for any two or more companies. Cost ~$0.07–0.14 per evaluation (three-pass). Full program load: ~$20–50/month. AI role Core evaluation engine, agentic web research, self-critique loop, conditional revision, comparative synthesis. Reasoning trace surfaced in the UI.
02 · Deal Intelligence
AI-Powered VC Framework Private Tool

Field Notes

A private deal intelligence tool for early-stage VC and advisory work. Three capabilities, all connected through a persistent company record: an investment memo builder structured around the Barley/Roberts HBS framework (why now, why this, why these people, traction read, what would have to be true, risks, recommendation) with inline framework cards citing Andreessen on markets and Botha on "what would have to be true," plus AI-generated IC pitch and skeptical-partner stress test; a term sheet analyzer that translates every clause into plain language and tags it Market/Aggressive/Founder-friendly against Q1 2026 benchmarks (Aumni, Carta, NVCA), with a VC Lens and Founder Lens toggle and exit waterfall at four scenarios; and a fund profile and portfolio construction model showing investable capital, companies the math supports, and three return scenarios, with every term sheet showing a deal-vs-fund analysis: ownership achieved vs. target, percent of fund consumed, reserves needed, the multiple this single deal has to return the whole fund.

The integration is the point. Cap table tools (Carta, Pulley) and term sheet templates (NVCA, YC) exist separately. None connect memo writing to term sheet analysis to fund construction logic. The Berkeley VCEP framework is the through-line: the tool encodes what a VC partner with formal training actually thinks, with source attribution visible in the UI. Waterfall math handles the common case correctly and explicitly flags edge cases, like pari passu structures and participation caps, rather than producing confidently wrong numbers.

Built in extended conversation with Claude across a single working session. Three versions shipped: v1 (memos, term sheets, AI synthesis), v2 (lifecycle events, multi-round stacked waterfall, shareable links with viewer tracking), v3 (fund profile, portfolio construction, deal-vs-fund integration, in-app admin invite system). An early scoring prototype was scrapped for being too accelerator-oriented and rebuilt from investor-standard memo structure. About 4,500 lines of TypeScript/TSX.

Stack Next.js 15 (App Router), TypeScript, Tailwind CSS, Drizzle ORM, Netlify DB (Neon Postgres), Clerk v6 (invitation-only), Anthropic API (Opus, all generations logged), Resend. ~30 source files. Architecture Framework data (memo prompts, market norms, waterfall math, fund construction logic) in structured TypeScript modules with source attribution. Every query scoped by user from day one. Multi-user and team mode supported without restructuring. Access Invitation-only. Submit a request at notes.gaurav.ventures. I approve in-app; Clerk sends the invitation automatically. AI role Memo drafting, IC pitch generation, skeptical-partner stress test, term sheet parsing from raw pasted text, fund construction synthesis.
03 · Platform Prototype
Platform Prototype 8 AI Agents 7 Personas

Accelerate v2: Program Management Platform

MassChallenge runs 12+ programs across Boston, Texas, Israel, and Switzerland using seven separate systems. No single view answers "how is this cohort doing" without opening at least four tabs. AcceleratorApp's contract ends July 2026, right after HC Traction 2026 closes. That's the ship date. Accelerate v2 replaces AcceleratorApp, the legacy Accelerate platform, and the Airtable workflows that accumulated in the gaps between them.

A 6,957-line single-file interactive prototype: React via CDN, Babel in-browser, no backend, no build pipeline, realistic demo data seeded for HC Traction 2026. Every workflow in the PRD is click-through interactive. Seven user personas, each with a fully scoped role view. Three program types, each with its own module configuration: Traction (20–40 startups, 4 months, mentor-centric), Challenge (2–5 corporate partners each selecting 1–4 startups, 3 months), Custom (single partner, 1–10 startups, 6–8 weeks, designed to launch in under two weeks from contract).

Eight AI agents underneath, each producing a recommendation a human accepts, edits, or rejects. Screener triages incoming applications before they reach the PM queue. Allocator distributes judge load by expertise match. Synthesizer rolls up R1 and R2 scores and proposes a cut line. Matchmaker pairs mentors to startups with rationale that propagates to both parties' views. Coach pre-drafts biweekly progress reports from session activity so mentors edit rather than write from scratch. Curator scores applications against each partner's challenge statement in real time. Scout surfaces alumni-to-mentor pipeline candidates. Conductor orchestrates all seven and maintains the audit log. Every agent output is visually distinguished in MC Purple, the only use of that color in the design system. Total production agent cost: approximately $103/month. Platform ceiling: $500/month all-in.

Stack React 18 via CDN, Babel in-browser, Inter, JetBrains Mono, MC design system. Single-file HTML. Production path: Next.js App Router, Netlify DB (Neon Postgres), Clerk (auth + magic links), Resend (email + .ics). Scale 6,957 lines. 7 personas. 8 AI agents. 3 program templates. 12+ interactive tabs in the PM view alone. Security Partner portal scopes data at the API layer, not hidden fields over a shared Airtable base. Magic-link judge entry with no standing account. Founder PII hidden by default on all judge-facing surfaces. Complete audit log for every data access, export, and admin action. AI role Product architecture, agent design and prompt engineering, full UI and interaction design, design system, complete code generation.
04 · Interactive Tool
Interactive Tool AI + Keyword Search Deployed

MC Alumni Explorer

Type "spinal cord injuries" and get back 13 companies grouped by relevance tier: high, medium, loosely related. Each card shows one sentence of AI reasoning for why it matched. That's the semantic search layer: natural language queries against 4,486 companies, relevance scored and explained. Staff who don't know the sector taxonomy find what they need without knowing what to call it. Staff who do know it get keyword search, eight filter dimensions (sector, sub-sector, funding stage, geography, demographics, confidence score, exit status, program year), card and table views, starred companies, and CSV export alongside.

Each company card shows funding, last funded date, Crunchbase rank, and a survival confidence score from a cohort-adjusted composite model. A button in each detail modal triggers a Claude API call with web search tool use to find and summarize recent press coverage for that company, on demand. One search, one company, live results.

Stack Vanilla HTML/JS/CSS + JSON data layer. Python/pandas for data processing. Static deploy, password-protected for internal staff. Data 4,486 Crunchbase-matched startups. 3MB JSON. Survival confidence score via cohort-adjusted composite model. Search Dual-mode: keyword filter across 8 dimensions, or natural language AI search with per-result relevance reasoning and tiered grouping (high, medium, loosely related). AI role Semantic search with relevance scoring and reasoning. On-demand agentic news research per company via web search tool use.
05 · LLM Pipeline
LLM Pipeline Data Classification

AI-Powered Startup Sector Classifier

Designed and ran an LLM classification pipeline across 4,486 startups: 5 strategic sectors and 5 healthcare sub-sectors. The pipeline feeds elevator pitches and Crunchbase descriptions to Claude Sonnet in batches of 30–40, with structured output parsing, retry logic, and progress tracking. It replaced a keyword-matching approach that had a 26% error rate on reclassifications. That 26% made the database effectively unusable for any segmented analysis.

This is the foundation layer. The Alumni Explorer, the Portfolio Intelligence Dashboard, and four published LinkedIn articles on 15 years of portfolio data all depend on the classified dataset it produced. The order mattered: the classifier had to be right before anything else was worth building.

Stack Python/pandas for batch orchestration. Claude Sonnet for classification. Structured JSON output. Scale 4,486 companies × 2 classification tasks. ~150 API batches. Manual spot-check of 50 reclassified companies. Validation Cross-tabulation against existing labels. Error rate analysis. Edge cases: dental, pest control, dual-use tech. AI role Core. LLM performs the classification. Prompt engineering for ambiguous sectors and company types.
06 · Data Product
21 Charts Data Product Deployed

Portfolio Intelligence Dashboard

A 6-tab interactive dashboard analyzing 15 years of startup outcomes: 4,486 companies, $27.1B in funding, 21 interactive charts. Tabs cover portfolio growth, challenge areas, funding pipeline, survival benchmarks, demographics, and cohort composition. Built as a public-facing data product for VC, corporate innovation, and ecosystem audiences, and as the analytical foundation for four published LinkedIn articles on portfolio data.

The analytical work underneath: a cohort-adjusted survival model calibrated against BLS and Stripe benchmarks (explaining why Crunchbase's raw 87% active rate is actually closer to 59%), a funding pipeline funnel (4,486 companies, 300 Series A+, 12 IPOs), a power law concentration curve (top 1% holds 45% of portfolio funding), and a funding parity analysis by gender and race across all 5 challenge areas.

Stack Chart.js (CDN), vanilla HTML/CSS/JS, Google Fonts. Single self-contained HTML file, no framework, no backend, no build step. Data 4,486 startups, 102 columns merged from Crunchbase and internal records. All figures audited against published articles. Scale 21 interactive charts, 6 analytical tabs, 4 KPI cards, animated counters, methodology panels. AI role Dataset analysis, chart design, data auditing, cross-referencing past articles for number alignment, editorial decisions on methodology transparency.
07 · Web App
Web App Agentic Research Deployed

AI Content Capture Tool with Agentic Research

A web application where marketing and community staff enter information about a startup, mentor, donor, or partner and receive generated marketing copy across four channels: LinkedIn post, blog copy, case study draft, and content angles. Conditional form fields by subject type. Quick-revision buttons (shorter, lead with metric, stronger CTA, warmer tone). Per-output copy-to-clipboard.

The agentic research layer is the differentiator. When a staff member enters a company name, the system autonomously triggers a Claude API call with web search tool use to gather recent press, milestones, and funding data, then simultaneously cross-references an internal alumni database to pull cohort year, sector, and program history. That research context is injected into the generation prompt before copy is produced. Staff get marketing copy informed by live data, not whatever they remember from the intake call.

Stack HTML front end, Netlify serverless function (Node.js) proxying the Anthropic API. API key secured in environment variables. Agent Two-mode function: "research" (web search and DB lookup to structured context) and "generate" (context-informed copy generation). Security API key in Netlify environment variables only. Never exposed in the browser. Staff see no setup or credentials. AI role Autonomous research, content generation, iterative revision on user request.
§ 03 · Tech stack

Tools I actually used.

No scaffolding for the sake of it. Everything here is a deliberate choice for a specific constraint: single-file deploys, no build pipeline, serverless for anything that touches an API key.

Python / pandas Anthropic API (Claude Sonnet + Haiku + Opus) Web Search Tool Use React / Recharts Next.js App Router TypeScript Drizzle ORM Chart.js Vanilla HTML / JS / CSS Netlify Static Netlify Serverless (Node.js) Netlify DB (Neon Postgres) Clerk (Auth + Magic Links) Resend (Email + .ics) openpyxl python-docx CairoSVG Crunchbase Data API
§ 04 · What this changes

The capability I'm building, not the tools themselves.

Being able to ship working tools rather than commission them changes what kinds of bets are feasible and how fast a lean team can move.

The Alumni Explorer took a week. It replaced a workflow that would have taken a quarter to spec and procure. The sector classifier took two days and resolved an error rate that had made the entire database unusable. Crucible went from concept to production in roughly seven Claude Code sessions, and it does work that used to take a program team days per company. Field Notes took a single working session and three rounds of iteration to reach a tool I actually use for every advisory engagement. That's the actual ROI: not the tools, the speed and the scope of what a non-technical operator can now tackle alone.

What's emerged across all seven of these is a pattern. The problems weren't technical; they were operational. Manual reconciliation eating PM time. Gut-feel evaluation without a rigorous framework. A deal intelligence workflow split across three separate products that never talked to each other. AI didn't change what the problems were. It changed how fast one person could address them.

See the full portfolio
20 years · 4 chapters · one method
Back to the beginning.
From a post-conflict Ministry of Health in Liberia to off-grid solar in East Africa to medical 3D printing at Formlabs to this.
View full portfolio →