Welcome

Not here to sound smart.
Here to make things work.

AI・Tech・Business・Web3・Travel

See all posts

Ask the archive

Checking runtime connection...

Maybe you'd like to ask...

Answer results

Your answer will appear here after the first run.

Latest

View all

AI Agents Aug 24, 2026

Agent-Ready Tools Part 01 | Building a Local-First Job Scraper

A technical case study on turning jobs-scraper from a local job-search script into a bounded tool that an AI agent can call safely.

Read more EN

AI Aug 18, 2026

Stateless MCP Architecture Part 03 | MCP 2026 Migration Guide: From Stateful to Stateless Without Just Updating the SDK

MCP 2026-07-28 is a protocol-era migration, not a package bump. This guide covers modern-first negotiation, dual-era serving, session and state migration, authorisation hardening, CIMD and DCR, and the correct deprecation paths for Roots, Sampling, Logging, and legacy HTTP+SSE.

Read more EN

AI Aug 18, 2026

Stateless MCP Architecture Part 02 | How Does MCP Stay Interactive Without Sessions? MRTR, Tasks, Headers, and Caching

MCP 2026-07-28 removes the long-lived protocol session, then separates multi-round input, long-running work, gateway routing, caching, and tracing into distinct mechanisms. This article explains MRTR, requestState, Tasks, HTTP metadata, ttlMs/cacheScope, and Trace Context by responsibility and failure boundary.

Read more EN

AI Aug 18, 2026

Stateless MCP Architecture Part 01 | Where Did the State Go? From Sessions to Explicit State Handles

MCP 2026-07-28 removes the protocol-level session, not application state. This article separates explicit state handles, durable backends, round-robin routing, serverless hosting, and the gateway boundary.

Read more EN

AI Agents Jul 31, 2026

Moving to Codex and the Product Map Part 04 | ChatGPT Chat, Work, or Codex: Which Should You Open After July 2026?

Do not choose a ChatGPT surface from a feature list. Start with the evidence you would need before you could call the work done.

Read more EN

AI Jul 19, 2026

LLM Wiki: Theory part02 | How Does an LLM Wiki Work? From Markdown and Google OKF to Obsidian and Knowledge Graphs

How does an LLM Wiki actually run? Seven layers cracked open — raw sources, Markdown, OKF, links and the graph, search indexes, the Harness — plus how Obsidian and Sigma.js serve humans and AI from the same substrate.

Read more EN

See all posts

Explore by topic

Browse the archive by category

A structured path into essays, notes, and observations across the ideas that shape Daniel’s work.

AI AI Agents PM Startup Business Web3 Travel Murmurs

Not here to sound smart.Here to make things work.

Ask the archive

Maybe you'd like to ask...

Answer results

Latest

Agent-Ready Tools Part 01 | Building a Local-First Job Scraper

Stateless MCP Architecture Part 03 | MCP 2026 Migration Guide: From Stateful to Stateless Without Just Updating the SDK

Stateless MCP Architecture Part 02 | How Does MCP Stay Interactive Without Sessions? MRTR, Tasks, Headers, and Caching

Stateless MCP Architecture Part 01 | Where Did the State Go? From Sessions to Explicit State Handles

Moving to Codex and the Product Map Part 04 | ChatGPT Chat, Work, or Codex: Which Should You Open After July 2026?

LLM Wiki: Theory part02 | How Does an LLM Wiki Work? From Markdown and Google OKF to Obsidian and Knowledge Graphs

Browse the archive by category

Not here to sound smart.
Here to make things work.