Skip to content
mikey.curtis
All work
Product Operations Lead · Feb 2026 — Present

Redbook.

Redbook makes software for cattle feed yards. I act as the bridge between engineering and the people actually using the product (owners, managers, cowboys), and I build the internal AI tooling that scales how the team supports them.

redbookcattle.com
Claude APITypeScriptRAG (pgvector)VercelNotion API
10+
Customer migrations
3 to 4 hrs
Manual hours saved per onboarding

Problem

  • Customer questions piled up faster than engineers could answer them, and product context lived in Notion where support couldn't reach it.
  • Customer-facing comms (release notes, migrations) were a manual handoff from engineering to marketing every two weeks, with predictable drift.
  • Onboarding a new customer meant 3 to 4 hours of manual data wrangling from their previous software.

Approach

  • Visited feed yards in person. Shadowed cowboys, owners, and managers using the product to turn field observations into prioritized engineering work.
  • Owned end-to-end integration of live cattle futures market data. That meant data ingestion, the modeling layer, and the UX that surfaces real-time P&L predictions to customers.
  • Built a Claude-powered TypeScript agent on Vercel, with a RAG pipeline (pgvector + OpenAI embeddings, incremental sync via Notion last-edited-time) connected to the OpenPhone API to auto-draft grounded responses to inbound customer questions.
  • Built a second agent that pulls merge commits from the repo every two weeks and generates polished product-update emails. That replaced the manual engineering-to-marketing handoff.
  • Built an automated migration pipeline from competitor software.

What shipped

  • Live market-data pipeline powering real-time P&L predictions in-product.
  • Notion-grounded support agent answering customer inquiries via OpenPhone.
  • Automated bi-weekly product-update email pipeline.
  • Migration tooling deployed across 10+ customer onboardings.

What's next

  • Expand the agent toolset so it can take action, not just answer.
  • Deeper instrumentation on which retrieved docs actually drive resolved tickets.