Timothy Wong

Topic dashboard

Decision Latency & Personal Knowledge Systems

Last refreshed July 9, 2026 · 20 concepts

Decision Latency & Personal Knowledge Systems

The bottleneck on smart decisions is no longer information - it’s the gap between capture and synthesis.

My take

The frame I use for my own work is decision latency: the time between a useful signal landing in my inbox and that signal actually changing how I think or act. That gap is where most knowledge work quietly fails. We have unprecedented access to information and unprecedented difficulty turning it into a position we can defend.

The naïve answer is “use AI to read more.” That makes the problem worse — it widens the funnel without improving the synthesis. The better answer is to wire AI into the synthesis layer: a personal knowledge system that ingests sources, integrates them into living concept pages, and surfaces contradictions when they appear. Build once, compound forever. That’s the system this site runs on.

What I’m watching: how attention management plays out when one person is orchestrating multiple concurrent agent sessions, and whether the next generation of PKM tools is built around durable concept graphs rather than another note-taking surface.

Everything above the divider is mine. Everything below is auto-assembled daily from my knowledge base — individual links and summaries may be stale or off-target. Last refreshed: 2026-07-09.

What’s shifted recently

  • Enterprise Context Layer For Agents (updated 2026-07-09)
    An enterprise context layer for agents is the governed infrastructure that sits between an organization’s data systems and any AI agent querying them, translating raw metadata int… — source · source · source

  • Agentic Rag Iterative Retrieval (updated 2026-07-07)
    Agentic RAG (retrieval-augmented generation) is a retrieval architecture in which the LLM does not retrieve once and generate — it loops: grading retrieved chunks, rewriting queri… — source · source · source

  • AI Knowledge Graph Second Brain Stack (updated 2026-07-07)
    A knowledge-graph-based second brain is a personal or organizational memory system that uses typed relationships, entity mapping, and schema-guided filing to make AI agents reason… — source · source · source

  • Agent Memory Architecture (updated 2026-07-06)
    Agent memory architecture refers to the set of mechanisms by which AI coding agents and AI coworkers maintain context that persists beyond a single session, enabling continuity ac… — source · source · source

  • AI Personal Second Brain (updated 2026-07-05)
    An AI personal second brain is a system that pairs a structured personal knowledge vault — typically Obsidian markdown files — with an AI agent (commonly Claude Code) that reads,… — source · source · source

  • Knowledge Base Personal Systems (updated 2026-07-03)
    Personal knowledge-base systems built on LLMs and Obsidian: practitioner setups, automation patterns, second-brain workflows. — source · source · source

  • Claude Code Personal Os Pattern (updated 2026-06-30)
    The Claude Code personal OS pattern is the practice of treating Claude Code not as a coding tool but as the primary coordination layer for a person’s entire digital life — managin… — source · source · source

  • Personal Second Brain LLM Stack 2026 (updated 2026-06-28)
    A personal second-brain LLM stack in 2026 is a local-first system architecture that pairs a knowledge vault (typically Obsidian, markdown, or plaintext) with an LLM agent that rea… — source · source · source

The ideas I keep coming back to

Currently active (last 30 days):

  • Enterprise Context Layer For Agents — An enterprise context layer for agents is the governed infrastructure that sits between an organization’s data systems and any AI agent querying them, translating raw metadata int…
  • Agentic Rag Iterative Retrieval — Agentic RAG (retrieval-augmented generation) is a retrieval architecture in which the LLM does not retrieve once and generate — it loops: grading retrieved chunks, rewriting queri…
  • AI Knowledge Graph Second Brain Stack — A knowledge-graph-based second brain is a personal or organizational memory system that uses typed relationships, entity mapping, and schema-guided filing to make AI agents reason…
  • Agent Memory Architecture — Agent memory architecture refers to the set of mechanisms by which AI coding agents and AI coworkers maintain context that persists beyond a single session, enabling continuity ac…
  • AI Personal Second Brain — An AI personal second brain is a system that pairs a structured personal knowledge vault — typically Obsidian markdown files — with an AI agent (commonly Claude Code) that reads,…
  • Knowledge Base Personal Systems — Personal knowledge-base systems built on LLMs and Obsidian: practitioner setups, automation patterns, second-brain workflows.
  • Claude Code Personal Os Pattern — The Claude Code personal OS pattern is the practice of treating Claude Code not as a coding tool but as the primary coordination layer for a person’s entire digital life — managin…
  • Personal Second Brain LLM Stack 2026 — A personal second-brain LLM stack in 2026 is a local-first system architecture that pairs a knowledge vault (typically Obsidian, markdown, or plaintext) with an LLM agent that rea…
  • AI Employee Fully Autonomous Worker — An AI employee is a persistently autonomous agent system positioned and priced as a full-time role replacement, not a tool or copilot.
  • Graphrag Enterprise Rag Evolution — GraphRAG is the architectural shift in enterprise retrieval-augmented generation from pure vector similarity search to knowledge-graph-backed retrieval, where the system indexes e…
  • Cross Agent Persistent Memory MCP — Cross-agent persistent memory via MCP is a local-first infrastructure pattern in which a single SQLite-backed store — exposed as an MCP server — gives every coding agent on a mach…
  • Karpathy LLM Wiki Workflow — Karpathy’s LLM wiki workflow is a system architecture for personal and organizational knowledge management in which LLMs maintain a persistent, interlinked markdown-based knowledg…
  • LLM Knowledge Management — LLM knowledge management is the practice of using language models as the primary agent for building, maintaining, and querying a personal or organizational knowledge base — typica…

Established:

  • Notebooklm As Research Substrate — NotebookLM (backed by Google Gemini) is a document-grounded AI workspace that accepts sources — PDFs, URLs, YouTube videos, articles — and enables chat, synthesis, and audio overv…
  • LLM Personal Knowledge Base Stack — The LLM personal knowledge base stack is the concrete tooling architecture through which individuals implement Karpathy’s raw-to-wiki-to-query pipeline — most commonly pairing Obs…
  • AI Personal Brand Funnel — The AI personal brand funnel is the repeatable playbook by which a solo creator builds an audience on X, then converts that audience into B2B revenue rather than C2C subscriptions…
  • AI Prompt As Curriculum — Prompt-as-curriculum is the practice of using structured AI prompts — rather than purchased courses or fixed institutional syllabi — as the primary mechanism for designing and del…
  • AI Attention Management — AI-induced attention deficit is a cognitive overload pattern that emerges when a single person orchestrates multiple concurrent AI agent sessions.
  • LLM Hallucination Citation Verification Benchmark — A citation-verification benchmark jointly produced by EPFL and the Max Planck Institute uses 950 questions across legal, medical, research, and coding domains to measure how often…
  • Agent Session Memory Loss Project Context — Coding agents and LLM-based assistants, including Claude Code, discard all conversational state when a session ends — there is no native mechanism to carry forward decisions made,…

Who I’m watching

  • Andrej Karpathy (person) — Andrej Karpathy is a researcher and educator who co-founded OpenAI and led Tesla’s Autopilot vision team.
  • Andrew Ng (person) — Andrew Ng is a long-standing AI researcher and educator — co-founder of Coursera and Google Brain, founder of DeepLearning.AI, and a frequent commentator on practical AI deploymen…
  • Garry Tan (person) — Garry Tan is the president and CEO of Y Combinator, and one of the most visible public commentators on AI coding tools, startup strategy, and AI security risk.
  • Jensen Huang (person) — Jensen Huang is co-founder and CEO of NVIDIA, which under his leadership became the world’s most valuable company by capitalizing on the AI infrastructure buildout.

Sources I’ve been drawing on

  • www.snaplogic.com — cited in Enterprise Context Layer For Agents
  • atlan.com — cited in Enterprise Context Layer For Agents
  • atlan.com — cited in Enterprise Context Layer For Agents
  • hex.tech — cited in Enterprise Context Layer For Agents
  • dev.to — cited in Enterprise Context Layer For Agents
  • dev.to — cited in Enterprise Context Layer For Agents
  • x.com — cited in Enterprise Context Layer For Agents
  • x.com — cited in Enterprise Context Layer For Agents
  • x.com — cited in Enterprise Context Layer For Agents
  • www.techcompanynews.com — cited in Enterprise Context Layer For Agents
  • ohsem.me — cited in Enterprise Context Layer For Agents
  • www.freecodecamp.org — cited in Enterprise Context Layer For Agents