Skip to content
View netsatsawat's full-sized avatar
15 followers · 7 following

Achievements

Achievement: Pull SharkAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull SharkAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Block or report netsatsawat

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.

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
netsatsawat/README.md

Satsawat Natakarnkitkul (Net)

Data & AI leader in ASEAN. Sixteen years building enterprise AI across banking, telecom, energy, and government in Southeast Asia. I build the AI systems and defend the business case for them.

✍️ I write at satsawat.ai: architecture teardowns, strategy frameworks, and honest accounts of what enterprise AI actually costs and returns.

📬 Newsletter: AI in Practice, one enterprise AI teardown a month.

📚 Books

  • Why Your AI Agent Will Fail: what the 11% who ship agents to production do differently · Amazon →
  • REPLACED: where your career value lives when AI does the 80% · Amazon →

🔧 Selected work

  • agent-failure-lab: watch compound error kill your AI agent, then watch the mitigations save it · live calculator
  • tsfm-bakeoff: 13 time-series foundation models against classical baselines, in four isolated environments
  • markov-and-hmm: one matrix prices a loan book, rates an AI agent, and values a customer; five beginner-friendly notebooks
  • fft-seasonality: build the FFT by hand, prove it on the Keeling curve, then turn hourly demand into a staffing baseline and an anomaly alarm

📫 [email protected] · LinkedIn

Pinned Loading

  1. agent-report-card agent-report-card Public

    A performance review for your AI agent: one CLI, one YAML test file, one markdown report. Local judge that grades itself, no API keys, every README number asserted by CI.

    Python

  2. agent-failure-lab agent-failure-lab Public

    Why 85% per-step accuracy means 80% agent failure: runnable compound-failure math (CLI, notebook, web calculator) plus a real 8-step agent on a local LLM with every failure logged and classified

    Jupyter Notebook

  3. markov-and-hmm markov-and-hmm Public

    Five-notebook tutorial on Markov chains and hidden Markov models: credit risk, market regimes, AI agent reliability, and customer lifetime value. Beginner-friendly, offline-reproducible, every numb…

    Jupyter Notebook 6 1

  4. fft-seasonality fft-seasonality Public

    Three-notebook tutorial on the FFT and seasonality: build the transform by hand, prove it on the Keeling curve, then turn hourly demand into a staffing baseline, an anomaly alarm, and a capacity plan.

    Jupyter Notebook 7 2

  5. tsfm-bakeoff tsfm-bakeoff Public

    13 time-series foundation models vs classical, ML and naive baselines: 10 datasets, 4 horizons, one venv per family. Foundation models won 30 of 38 contests; the GIFT-Eval leader's open predecessor…

    Jupyter Notebook