Knowledge archive / 19
Applied AI notes for systems that have to work
Long-form field notes on controlled AI workflows, agent architecture, evaluation, tooling, and the operating systems around them.
First-party knowledge hub
Articles and practical guides
01 / On this site
What an AI Automation Consultant Does, and When You Actually Need One
What an AI automation consultant does, the signs you need one, when a template or your own team is enough, and what the first weeks should produce.
02 / On this site
AI Automation Freelancer or Agency? Decide by What the Workflow Can Break
When to hire an AI automation freelancer or an agency, or train someone in house, decided by what the workflow can break and who owns it after launch.
03 / On this site
Silent Failures in AI Workflows: The Run Succeeded, the Output Is Wrong
Why an AI workflow can run green and still write wrong data, where silent failures hide, and the order I use to diagnose and fix one without a rebuild.
04 / On this site
AI Workflow Orchestration: Let Code Run the Workflow, Let Models Do the Work
What AI workflow orchestration is and how to split it: code owns order, state and retries, models do bounded steps, people approve the costly actions.
05 / On this site
OpenClaw on Telegram: Approving AI Coding Agents From Your Phone
How to connect OpenClaw to Telegram and use it as the approval channel for AI coding agents: setup steps, one agent on chat, and an escalation chain.
06 / On this site
Human-in-the-Loop AI Workflows: Where the Approval Belongs
Which AI workflow actions need human approval, what the reviewer must see, and how to keep the gate from becoming a rubber stamp.
07 / On this site
When an Agent Can Change Its Own Harness, Change Control Becomes Part of the System
A practical control path for agent-generated changes to prompts, skills, memory, and sub-agent setup, with risk-based review and versioned recovery.
08 / On this site
The Deterministic Layer: Where AI Workflows Need Certainty
Why models should interpret ambiguous inputs while deterministic workflow controls govern validation, state, permissions, approvals, recovery, and consequential actions.
09 / On this site
Inside my AI agent setup: LoopEngineering, Harness
A look inside a role-based AI agent environment connecting Discord, Obsidian, Hermes, OpenCode/Superset, persistent memory, and human review.
10 / Medium article
Why AI Coding Results Depend 80% on the Harness
A field report on how routing, memory, permissions, review loops, verification, and smaller agent responsibilities shape AI coding results.
11 / Medium article
Why AI Agent Harnesses Matter More Than Model Choice
A practical argument for focusing on harness design, feedback loops, tools, and evaluation instead of only swapping models.
12 / Medium article
How I Cut Token Usage in Half by Redesigning My Agent Architecture
A breakdown of how architecture choices, context management, and cleaner agent boundaries reduced token consumption.
13 / Medium article
How I Built a Second Brain for Claude Code
How I designed a knowledge workflow to make Claude Code more useful with persistent project memory and reusable context.
14 / Medium article
AutoResearch Beyond ML: How I Adapted Karpathy’s Loop to Trade Prediction Markets
An experiment applying iterative research loops beyond classic ML to prediction-market research and trading workflows.
15 / Medium article
The Impostor Loop: Why Vibecoding Made Me Feel Like a Fraud
A personal reflection on AI-assisted coding, confidence, skill development, and the tension between speed and ownership.
16 / Medium article
How I Keep Claude Code Fast With Zero Plugins
A lightweight workflow for keeping Claude Code responsive using repository structure, focused context, and simple operating rules.
17 / Medium article
How I use OpenClaw to ship MVPs
A practical article on using AI agents, a Python script, and a low-cost VPS to move faster from idea to working product.
18 / Medium article
How to Use Kimi K2.5 Free on OpenClaw
A hands-on guide to connecting Kimi K2.5 with OpenClaw and experimenting with low-cost AI agent workflows.
19 / Medium article
How I Turned Obsidian Into an AI-Powered Second Brain With Claude Code
A workflow for combining Obsidian and Claude Code into a practical AI-assisted second brain for notes and project memory.