The class logbook
The Latest
Everything published on the site, day by day, newest first: guides, analysis, essays and quick thoughts in one running log. The shelves for browsing are elsewhere; this is where you see what is new.
The log
Entries 81–100 of 125 · by original publication date
1 entry
1 entry
Check What a Permission Rule Actually Allows
A permission rule is easiest to assess with two small examples: one operation you intend to allow and one nearby operation you intend to deny.Quick thoughtclaude-codepermissions1 entry
Test the Build Your Customer Will Receive
A development server passing its tests does not establish that a production bundle behaves the same way.Quick thoughtclaude-codeverification1 entry
Trace One Failed Request Through the Logs
A page can fail after three services have each logged something that looks successful. Start with one request identifier, not the loudest error message.Quick thoughtclaude-codedebugging1 entry
Preview Every Rename Before Moving Files
Renaming two hundred client documents is easy to request and surprisingly hard to undo when two names collapse into one.Quick thoughtclaude-codefile-operations1 entry
Give Claude a Broken Example Before a Fix
A useful bug report contains an input that fails and the result you expected. That gives Claude Code something firmer than “the report looks wrong.” Suppose a…Quick thoughtclaude-codetesting2 entries
Make Claude Preserve the Meaning of a CSV
A customer number such as 00127 is an identifier. Turning it into 127 can break a perfectly tidy spreadsheet export.Quick thoughtclaude-codedata-qualityWhy AI Agents Don't Dissolve the Firm
Ronald Coase asked in 1937 why firms exist instead of markets. AI agents revive the question — and the old answer says the firm concentrates, not dissolves.13 min readzeo-theoryorganization-theory
8 entries
Clean a Messy Customer List With Claude Code — and Prove Nothing Was Lost
Every business has one: the customer list that lives half in a spreadsheet, half in an inbox, and half in someone's head. Here is how to clean it in about twenty minutes, and — the part nobody teaches — how to prove the cleaning did not quietly drop forty rows.12 min readpracticeclaude-code
Give the Agent an Inspectable Check
You ask if it's done. It says yes. You check, and it isn't. A completion claim needs evidence you can inspect.Quick thoughtclaude-codeverificationPrice the Agent Work You Can Verify
Compare agent workflows by usable output, review time and the cost of the decision you are making. A token average alone cannot tell you what to build, route or keep running.8 min readzeo-theorycontrolling
What Claude Code Actually Changes — and What It Doesn't
Claude Code can shorten implementation while adding review and recovery work. Use four delegation habits and a whole-task timing check to decide whether an agent improves the work you hand over.10 min readclaude-codeverification
What Claude Code Actually Costs — and Which Dials Move It
Your lunch break has a token price. The model remembers nothing between turns, so every request re-sends the whole conversation — which means cost scales with context carried, not work requested. Here is the cost function, the dials that matter, and the ledger line worth keeping.17 min readclaude-codeharness-engineering
When Can You Actually Walk Away?
Choose an agent task you can verify, bound its effects, and plan the handover. A practical delegation grid, six operating modes, and checks that can miss the real failure.10 min readclaude-codeharness-engineering
Your Chat History Is Not a System of Record
Make agent work resumable from records: capture decisions, source revisions, test evidence and unresolved effects, then check whether another session can continue safely.10 min readclaude-codeharness-engineering
Your Claude Code Permissions Are Your Org Chart
Anthropic measured it: users approve about 93% of permission prompts. A gate that opens 93% of the time is a doorbell. Here is what the permission system actually enforces, what it cannot, and the standing rules worth adopting before you delegate anything that matters.18 min readclaude-codeharness-engineering
3 entries
After Repeated Corrections, Rebuild the Task Context
The agent repeats the wrong approach after two corrections. My rule of thumb is to stop adding conversational patches and restate the task from the evidence.Quick thoughtclaude-codecontextThe Content Kit: Every Block, and When to Use It
A working reference for the eleven content blocks this site can render. Each one is shown live and paired with the case it is for. If a block below looks broken, it is broken.6 min readhouse-noteswriting
What Is a Zero-Employee Organization?
A Zero-Employee Organization is a firm where headcount is no longer the unit of scale. Here is the definition, the eleven-theory audit behind it, and the finding that only four verdicts survived being checked three times.11 min readzeoorganization-theory
1 entry
Test Whether a Shorter CLAUDE.md Helps
Three hundred lines of instructions and it still breaks your conventions. So you add more rules. It gets worse.Quick thoughtclaude-codecontextContinued on the next page.
To browse rather than follow: topics, all articles and all thoughts. To learn in order: courses and the book.
