Matt Kilmer
Product Builder · CPTO at ABE · Musician
Projects
ABE
Agentic operating system that turns company data into prioritized action
Production platform connecting customer conversations, revenue, analytics, strategy, and code so teams can see what matters, decide what to do next, and move work forward.
VoteShip
AI-native feature request platform with MCP server integration
SaaS platform for product teams to collect user feedback, triage with AI, share public roadmaps, and ship features users actually want. First feature request tool with an official MCP server for AI agent integration.
Align
AI-powered relationship agreements that grow with your partnership
Mobile app helping couples create personalized, living relationship agreements through therapy-informed AI. Partners take adaptive quizzes, negotiate AI-generated clauses together, digitally sign, and revisit monthly.
CEO Simulator
Text-based business simulation where every decision has consequences
A retro-styled (1986) browser game where players run a company through text-only decisions, balancing money, trust, and sleep until they inevitably get fired.
Production SaaS helping Shopify merchants optimize product listings at scale through intelligent content generation and bulk processing.
Clean Beauty Advisor
AI-powered beauty product ingredient analysis with personalized recommendations
Production SaaS platform analyzing 100k+ beauty products with GPT-4o, helping users make informed choices based on their skin profile and ingredient preferences.
Interactive music creation tool that transforms touch into particle animations and synthesized soundscapes - playable by anyone, no training required.
Claude Slackbot
Autonomous AI development assistant operating directly in Slack
Production bot that analyzes codebases, generates fixes, creates pull requests, and deploys previews - all from natural language Slack messages.
HomeGrow
Multi-state cannabis home growing platform with AI-powered tools
Comprehensive web platform helping US residents legally grow cannabis at home, deployed across 10 domains with state-specific legal information, growing guides, and interactive AI tools.
TradingGPT
Natural language to executable trading strategies with backtesting
Platform translating plain English into validated, backtested algorithmic trading strategies with risk management and paper trading deployment.
About
I build products and write code. I am currently Chief Product & Technology Officer at ABE, an agentic operating system that turns customer conversations, business data, strategy, and code into action. I am also a Senior Product Manager at Viewcy, where I own the core ticketing, video, and membership products.
At ABE, I lead the product and build across web, mobile, and desktop. The platform includes 56+ AI tools, 20 integrations, autonomous agents, institutional memory, human approval gates, and a system for running and measuring experiments. At Viewcy, the products I own serve 1,500+ organizers and 250,000 monthly fans and have processed more than $20M.
Earlier, I built music products at Jammer and Keezy that reached 100K+ active users and 1M+ downloads. I still prototype directly in code, including an interactive audio-visual instrument that anyone can play in a browser.
Music Background
Before product management, I spent a decade as a professional musician and producer. Berklee-trained, toured with Lauryn Hill and Reggie Watts, coordinated music for an Emmy Award-winning TV show. That world taught me about creating for audiences, iterating under uncertainty, and the difference between what is technically impressive and what actually resonates. That is why I care about building products that feel as good as they perform.
Experience
ResumeChief Product & Technology Officer
- •Lead product strategy and hands-on full-stack development across web, mobile, and desktop
- •Shipped 56+ AI tools and 20 integrations spanning customer intelligence, strategy, experimentation, code, and operations
- •Designed autonomous agents with institutional memory, observability, and tool-level human approval gates
- •Built a closed-loop experimentation system that connects hypotheses, execution, attribution, and measurement
Senior Product Manager
- •Own the core ticketing, video, and membership products for a platform that has processed more than $20M in transactions
- •Lead continuous discovery with organizers and creators through interviews, usability tests, data analysis, and prototypes built in code
- •Launched an AI event creator that reduced setup time by 60% and shipped checkout improvements that increased mobile conversion by 18%
- •Rebuilt delivery around AI coding agents, automated testing, review gates, and a cross-functional release cadence
Founder and CEO
- •Oversee all aspects of business operations and strategy for a boutique eco-conscious health and beauty brand
- •Establish and maintain relationships with vendors and strategic partnerships
Senior Product Manager
- •Led product development lifecycle for flagship music app and interactive digital music service
- •Measured and evaluated product optimizations for business impact including conversion, retention and LTV
- •Built the team from scratch - hired across product, engineering, sales, and design
- •Worked with major labels on licensing and content partnerships
Product Manager
- •Set product vision and strategy inline with business objectives for music software startup
- •Defined releases, oversaw user testing, prioritized features, owned product roadmap
- •Built three apps - one of them took off unexpectedly
Music & Production
Music Coordinator
- •Oversaw music production for a comedy series - hiring musicians, managing sessions, delivering assets
- •Five seasons of figuring out how to make creative collaboration work under deadlines
Touring / Session Musician
- •Played sessions and tours across genres - learned a lot about showing up prepared and adapting on the fly
Notes on Building with LLMs
The demo-to-production gap
Demos optimize for wow moments. Production systems optimize for reliability, cost efficiency, and graceful degradation. The hardest problems usually aren't the AI - they're context management, quality evaluation at scale, and handling non-deterministic outputs in deterministic systems.
Trust beats capability
The biggest blocker to AI product adoption isn't model capability - it's user trust. Quality control mechanisms (preview before apply, rollback capabilities, validation layers) matter more than using the newest model. Users need confidence that AI won't break their production systems.
The boring stuff matters most
Prompt caching, context window management, knowing when to use a smaller model - these ended up mattering more than clever prompting. Cost-per-request directly impacts product viability. It's not an optimization problem, it's a design constraint.
Measure before you scale
How do you know if your AI product is improving? Traditional metrics don't apply to subjective outputs. Human evaluation pipelines, quality scoring systems, failure case analysis - you can't improve what you can't measure, even when outputs are probabilistic.
Anticipate misuse
AI products carry unique responsibilities. Input validation to prevent prompt injection, output filtering, rate limiting, audit logging. Building responsibly means anticipating misuse, not just optimizing for the happy path.
Skills
AI/ML
- •LLM Integration & API Design
- •Prompt Engineering & System Design
- •Context Window Optimization
- •Structured Outputs & Function Calling
- •Streaming & Real-time Processing
- •Prompt Caching & Cost Optimization
- •Evaluation Frameworks
- •Safety & Content Filtering
Product
- •AI Product Strategy
- •0→1 Product Development
- •Roadmap Planning
- •User Research & Testing
- •Stakeholder Management
- •Go-to-Market Strategy
- •Agile/Scrum
- •Product Analytics
Technical
- •TypeScript/JavaScript
- •React/Next.js
- •Node.js
- •Python
- •PostgreSQL
- •API Design
- •AWS/Vercel
- •Git/GitHub