> Content catalog. Every maintained wiki page is listed with a one-line summary.
> Read this first to find relevant pages for any query.
> Last updated: 2026-06-27 | Total pages: 52
Entities
addy-osmani — Author of X Articles on agent harness engineering, cognitive surrender, and loop engineering; frames agent work as model plus scaffolding plus human judgment.
armin-ronacher — Software engineer and writer of "The Coming Loop," arguing that harness-level loops are inevitable but risky for long-lived code unless they preserve human judgment, invariants, and supervision.
andrej-karpathy — Person referenced as the inspiration source for the LLM Wiki pattern.
bayer-prince — Bayer's PRINCE preclinical-research assistant: a production agentic RAG system with LangGraph orchestration, state persistence, citations, evaluations, and recovery paths.
christoph-nakazawa — Author of "Modern Engineering Values," arguing that agentic engineering shifts the bottleneck from hand-written code toward ownership, taste, guardrails, repo-local context, and judgment.
david-oks — Author of "Why Japanese companies do so many different things," explaining Japanese corporate diversification as an organizational bundle.
enpire — NVIDIA/CMU/UC Berkeley harness framework for agentic robot policy self-improvement in the real world.
garry-tan — CEO of Y Combinator; argues personal AI should be a compounding operating system made from fat skills, fat code, thin harness, and a fat data layer.
gbrain — Garry Tan's personal brain/knowledge infrastructure extending the LLM Wiki pattern into a large structured repository.
hermes-agent — Agent framework used here to ingest, query, lint, and maintain the markdown wiki.
jack-maguire — Author of "AI Job Grief," framing AI displacement as a grief-like loss of professional identity.
liberman-brothers — Serial entrepreneurs arguing that AI should be understood as infrastructure whose compute layer must not be monopolized by a few corporations or states.
jaya-gupta — Author of "The next biggest moat in AI," framing company shape and talent systems as the durable moat in AI.
mark-erikson — Author of "My Thoughts on AI," describing a personal transition into AI-assisted software development.
matt-van-horn — Author of "WTF Is a Loop?," framing agent loops as cron plus model decisions, feedback, budget caps, and reusable skills.
milan-jovanovic — Author of "DRY Is the Most Misunderstood Rule in Programming," arguing that DRY is about duplicated knowledge rather than similar-looking code.
noam-brown — Author of "Implications of Large-Scale Test-Time Compute," arguing benchmark and safety evaluations should measure performance against inference budget.
peter-yang — Author of "The Chat Era is Coming to an End," arguing chatbots should evolve into personal agents.
shopify-river — Shopify internal Slack-based AI agent that works in public channels and turns agent use into organizational apprenticeship.
sopra-steria — Consulting, digital services, and software company cited for agentic AI in retail and commerce.
thariq — Author of "Using Claude Code: The Unreasonable Effectiveness of HTML," arguing for HTML artifacts as richer agent output surfaces.
tobi-lutke — CEO of Shopify; argues River turns public agent work into a company-scale teaching workshop.
Concepts
agentic-ai-in-retail — Retail shift from AI dashboards and recommendations toward governed agents that execute inventory, pricing, commerce, and customer-service decisions.
agentic-rag — Retrieval-augmented generation wrapped in an agent workflow with planning, tool routing, evidence reflection, and answer synthesis.
agent-loops — Programmatic wrappers and loop-engineering systems that prompt, schedule, delegate to, evaluate, and supervise coding agents with durable memory, verification, and stopping conditions.
agent-operable-environments — Task environments whose reset, rollout, verification, logging, safety, and permissions are exposed as callable interfaces for AI agents.
ai-assisted-software-development — Human-in-the-loop use of LLMs and coding agents for codebase research, implementation, tests, debugging, and tooling.
ai-compute-infrastructure — Physical and market layer of AI access: GPUs, data centers, energy, inference budgets, provider lock-in, and compute governance.
ai-job-grief — Psychological and social grief response when AI threatens professional identity, autonomy, and future prospects.
ai-labor-market — Economic and organizational impact of AI on work: productivity, displacement, job redesign, exposed knowledge-worker tasks, and the shift toward judgment-heavy skills.
cognitive-surrender — Failure mode where AI output replaces the engineer's independent judgment, creating cognitive and comprehension debt.
decentralized-ai-compute — Open-protocol approach to AI compute where participants provide hardware and earn tokens, aiming to make inference a public competitive layer rather than a closed cloud monopoly.
dry-principle — Software-design principle that avoids duplicating knowledge, not merely similar-looking code; premature extraction can create hidden coupling.
harness-engineering — Discipline of improving prompts, tools, context, hooks, sandboxes, memory, and feedback loops around AI agents.
japanese-corporate-diversification — Japanese firms diversify because lifetime employment, horizontal coordination, internal finance, and survival-oriented governance form a coherent organizational bundle.
html-artifacts — Browser-viewable agent outputs for specs, reviews, reports, prototypes, and custom editing interfaces.
llm-wiki-pattern — Persistent markdown knowledge base pattern built from raw sources, maintained pages, and schema.
loop-dependent-software — Codebases and engineering workflows whose creation, review, diagnosis, or maintenance assume continuing machine-loop participation, raising comprehension and reliability risks.
lucid-dream-problem-solving — Use of lucid dreams for puzzle solving, skill rehearsal, and two-way communication with sleeping participants.
organizational-moats — Defensibility created by organizational shape, talent density, status, authority, and institutional design.
personal-agents — AI systems that move beyond chat to delegated online action while hiding technical setup from users.
physical-autoresearch — Agent-driven real-world experimentation loop where coding agents improve robot policies through physical rollouts, automatic reset, and automatic evaluation.
production-llm-reliability — Engineering patterns that make LLM systems bounded, observable, recoverable, evaluable, and verifiable in production.
public-agent-collaboration — Practice of doing AI-agent work in visible, searchable team spaces so patterns, judgment, and skills diffuse through an organization.
self-improving-knowledge-base — Knowledge base workflow where an agent maintains links, summaries, index, and lint health over time.
skillification — Workflow pattern for turning repeated agent tasks into durable, reusable skills that compound over time.
speedup-illusion — Miscalibration where AI assistance feels easier and is expected to be faster, even when measured task time does not improve.
sleep-learning — Modern evidence and ethical limits around learning, memory cueing, conditioning, and problem solving during sleep.
targeted-memory-reactivation — Sleep-research technique that replays cues linked to prior learning to bias memory consolidation.
test-time-compute-evaluations — Model-evaluation frame that plots performance against inference tokens, cost, or time instead of relying on single scalar benchmark scores.
Comparisons
llm-wiki-vs-obsidian — Tradeoffs between an agent-maintained LLM Wiki and an Obsidian-centered workflow.