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 21–39 of 39
13 entries
Design a Cache Experiment That Measures the Right Thing
Prompt caching measurement means separating context size, billed usage and latency instead of reading one counter as proof of all three.11 min readprompt-cachingLLM cost
Durable Agent Execution: Resume Without Repeating Effects
A checkpoint that saves state is not the same as a receipt from the outside world. Learn what must persist before an actor is replaced.13 min readdurable agent executionidempotency
LLM Business Rule Validation: JSON Parses, Now What?
Check an LLM proposal against trusted stock, prices and budget after its fields validate, with explicit errors for wrong quantities and stale data.13 min readLLM business rule validationPydantic
LLM Duplicate Key Validation Before Dictionary Conversion
A dictionary of order lines can hide duplicate rows. Check the list for repeats before conversion, not after, to preserve evidence.11 min readLLM validationdata integrity
LLM Model Routing Evaluation From Accepted Work Cases
Evaluate model routes on ordinary tasks, missing data and policy conflicts, then set acceptance thresholds before comparing cost savings.11 min readLLM model routing evaluationagent evaluation
MCP Token Audience Validation: A Worked Denial Case
Validate an MCP token for the receiving service as well as its issuer, expiry and scope. Test wrong-audience denial before protected work executes.12 min readmcpauthorization
Pydantic Strict Validation: Choosing What an Input May Become
Learn Pydantic strict validation to decide which conversions a quantity field should accept, and which ones deserve a clear rejection.12 min readPydanticdata validation
RAG Access Control: Stop Leaks Before the Prompt Builds
RAG access control means filtering by permission before retrieval, not after the answer is written. A worked two-user case shows where checks belong.11 min readRAG access controlretrieval security
Scheduled publication timezone: the worked case
Why a date-only release rule needs one clock across build, request and cache before a scheduled publication timezone decision is trustworthy.9 min readschedulingtimezones
Stateless MCP Application State: Where Identity Really Lives
Keep MCP job state durable while connections change. Check authenticated identity and job permissions on each protected request before resuming work.10 min readMCPapplication stateUpdated
Translate a Coding Agent Benchmark Into a Release Decision
A coding agent benchmark evaluation measures one task distribution. Learn to check whether it matches your actual release decision.11 min readevaluation engineeringcoding-agents
Write an AI Agent Handoff Checklist That Actually Verifies
Learn to write an AI agent handoff checklist that lets a new engineer verify state and evidence instead of trusting a summary.13 min readAI agent handoff checklistagent memory
3 entries
Build a Working Agent with sovereign-agent
Clone it, install it editable, run the offline example, then read the 67-symbol API you'd actually build on. A working agent in about fifteen minutes, no API key required.13 min readagentsopen-source
Build Your First ZeoCore Tool and Check Its Failure Boundaries
Turn a small Python function into a typed agent tool. Follow its input and result contracts, reproduce the failure cases, and separate what validation catches from what it cannot prove.11 min readpythonopen-source
Govern a Multi-Agent Project With Zero-Employee
Install the zeo CLI, write a real Statement of Work, and hit the exact schema error a beginner hits first. This is the tool this site's own governance arguments run on.12 min readgovernanceopen-source
3 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
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
That is the first entry in the log.
To browse rather than follow: topics, all articles and all thoughts. To learn in order: courses and the book.
