Work
The write-ups behind the numbers.
As sole PM, I turned a manual, spreadsheet-driven lead operation into a configuration-led platform that cut delivery time from 1–2 hours to under 5 minutes, reduced the ops team by ~75%, and scaled to 600+ clients and 78M+ distribution records.
I led a 0→1 education platform (website, CMS, structured data, student tools and technical SEO) that doubled indexed pages to 300K+, cut content processing from 4 hours to 10 minutes, and grew monthly sessions to a peak of 339K.
I designed, built and launched RankFlowHQ on my own: a Generative AI workflow that takes a keyword to a cited, publish-ready article. The product decisions were about trust, time-to-value and positioning, not just prompts.
I built an explainable replenishment engine that turns four CSV exports into a daily order list with a reason on every line. On a simulated 120-SKU store it matches the best spreadsheet's 98.1% fill rate with 66% less inventory, cuts perishable waste from 45% to 0.4%, and protects 22% more gross margin under a cash cap.
I built a store designed for the next type of customer and operator: AI agents. Shopping agents buy through a discoverable JSON API, operator agents run the store via MCP and tool APIs, and every experiment is a Thompson-sampling bandit that optimises profit, with a full audit log of every action an agent takes.
How I planned and built HarshOnRoads end to end: the user personas, the problem framing, a PRD for the AI trip planner, the decision to put verified data before AI, the tool roadmap, and how my own travel content became the distribution channel.