Dream Logs Data

Experience settings

Theme
Motion
Effects
Reading

Preferences are saved in this browser only.

Language: TH

DREAM LOGS DATA
EXPERIENCE

Experience settings

Theme
Motion
Effects
Reading

Preferences are saved in this browser only.

Language: TH

EXPLORE

PAKON POOMSON · AI ENGINEER · THAILAND

I BUILD AI SYSTEMS, BREAK THEM, AND WRITE DOWN WHAT I LEARN.

agents · retrieval · evaluation — and why systems behave differently from what we expect.

SEE THE WORK ENTER THE LAB
USER RETRIEVE AGENT TOOL EVALUATE OUTPUT
Diagram: a user request flows through retrieval, agent, tool, and evaluation into an answer.

CURRENTLY EXPLORING

SELECTED WORK

ALL WORK

Real projects with the question, the build, the proof, and the limits left visible.

  1. Customer Support RAG Triage Agent Getting an AI to answer is easy. Knowing what it based the answer on is the interesting part. Live zero-key demo · AI workflow / support
  2. Thai Review Sentiment Intelligence If the model can give a label but is unsure, which reviews should go to a person? Live demo · Thai NLP / review routing
  3. Thai Procurement Intelligence There is plenty of public data. How do we know where the number on screen came from? Portfolio case study · Data / Thai procurement

THE LAB

ALL EXPERIMENTS

Small deterministic experiments. Run them, break them, inspect what happened.

  1. EXP 001 Agent Trace SIMULATION
  2. EXP 002 RAG Retrieval SIMULATION
  3. EXP 003 Evaluation SIMULATION
  4. EXP 004 Context Window SIMULATION

LATEST WRITING

ALL WRITING

Notes published after something actually worked — or refused to.

  1. AI Gets Smarter Every Day. Are We Getting Smarter Too? Lessons from AI NEXT by BIZCORE A personal account of AI NEXT BOOTCAMP by BIZCORE on 25 July 2026—and the question of whether our context, judgment, and practice are improving with AI.
  2. How Much Electricity and Water Does One AI Prompt Use? What happens behind an AI response — from GPUs and data centers to electricity, cooling, and the problem with assigning one number to every prompt
  3. One Small Data Error Can Distort the Whole System What Data Quality really means — and why it matters from spreadsheets and dashboards to ML and AI

ABOUT

Hey, I'm Pakon — an AI Engineer based in Thailand. I build AI systems, experiment a lot, and write about what I learn.

MORE ABOUT ME