Skip to content
View richardan01's full-sized avatar
2 followers · 1 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Block or report richardan01

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
richardan01/README.md

Hi, I'm Richard 👋

I build eval-driven AI product systems — from PRDs and workflows to demos, launch gates, and LLM evaluation loops.

Most of my work sits across AI Product Management, enterprise data platforms, LLM evals, agentic workflows, and practical product systems.

🌐 Portfolio: aboutrichie.vercel.app

🚀 Featured work

  • 🧠 AI-Product-Lab Public proof-of-work lab for AI Product Management, evals, agents, RegEval, and measurable AI product artifacts.
  • 💰 Finance-bot AI finance assistant prototype for structured analysis, reasoning, charting, human review, and eval workflows.
  • 🧑‍💻 aboutrichie - Live site Interactive AI PM portfolio and personal product profile.
  • 🔍 llm-comparator Side-by-side LLM response comparison and evaluation workflow exploration.

🧠 What I work on

  • 🧪 LLM evals, rubrics, failure modes, and quality gates
  • 🏢 Enterprise AI workflows, governance, and trust
  • 📊 Data platforms, Customer 360, CDP, CRM, and semantic layers
  • 🤖 Agentic workflows for product teams
  • 📝 PRDs, launch reviews, product strategy, and stakeholder updates
  • 🛠️ AI builder workflows using Claude Code, Codex, Gemini, GitHub, Python, and SQL

📍 How I think about AI products

Problem → Workflow → Data → Model → Eval → Launch → Learning

AI products should not stop at demos. They need clear user problems, trusted workflows, quality gates, human review, and measurable business impact.

🎯 Current focus

I’m building a public AI PM portfolio around:

  • 🧠 AI Product Lab proof-of-work artifacts
  • 🧪 LLM evaluation systems
  • 🏢 Enterprise AI workflows
  • 📊 Data platform to AI product loops
  • ✅ Launch readiness and quality gates

🤝 Connect

Pinned Loading

  1. AI-Product-Lab AI-Product-Lab Public

    Public proof-of-work lab for AI Product Management, evals, agents, RegEval, and measurable AI product artifacts.

    Python

  2. Finance-bot Finance-bot Public

    AI finance assistant prototype for structured analysis, reasoning, and human review.

    TypeScript

  3. aboutrichie aboutrichie Public

    Personal AI PM portfolio and interactive product profile.

    TypeScript

  4. llm-comparator llm-comparator Public

    Forked from PAIR-code/llm-comparator

    LLM response comparison and evaluation workflow exploration.

    JavaScript 1

  5. pokemonred pokemonred Public

    Experiement on ML on Pokemon Red (You might need a Gameboy emulator for this)

    Jupyter Notebook

  6. evalxiety evalxiety Public

    Eval and release-gate workbench for Claude agents: error analysis, code checks, an LLM judge measured against human labels.

    TypeScript 1