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 21–40 of 53
1 entry
3 entries
Dark Software Factories Still Need a Task Owner
Build a dark software factory around a concrete change request. Separate implementation from acceptance, preserve evidence and decide which decisions remain human.6 min readdark-software-factoriescoding-agents
Make Your Prompt Examples Agree With the Rule
An example can quietly contradict the instruction above it. The model then has two different versions of the job to follow.Quick thoughtopenaipromptingNotebook to AI Application: Build a Callable Contract
Turn a working notebook cell into a callable contract with declared inputs, rejected cases and stable outputs before another service depends on it.12 min readnotebook to AI applicationPydantic validation
16 entries
Agent Evaluation Environment: Freeze the Task Contract
An agent evaluation environment must freeze inputs, tools and an independent oracle, or the same message silently grades against two different answers.10 min readagent evaluationAI evaluation environment
Agent Memory Invalidation: Retire Stale Facts Correctly
A changed source revision should retire a stored fact without deleting its history. Here is how to tell which memories must go.11 min readagent memorycontext engineering
Agent Regression Dataset: Save the Failure, Not the Fix
Learn to turn one failed agent run into an agent regression dataset that tests recovery without pretending to know the original cause.12 min readagent evaluationregression testing
Agent Tool Idempotency: Reconcile an Uncertain Write
A timed-out tool call leaves you unsure a write happened. Choose an idempotency key, and reconcile the result before retrying anything.12 min readagent tool idempotencyreliability
AI Agent Approval Boundary: Draft Accepted Isn't Purchase Made
An AI agent approval boundary means accepteddraft carries no supplier receipt. Learn to separate validation from execution.13 min readAI agent approval boundaryagent validation
AI Agent Per User Credentials: Who Owns the Key?
AI agent per user credentials means separating who invokes an agent from which account its tools use, so one caller never inherits another's access.11 min readagent-securityidentity-and-access
AI Agent Preview Deployment: Test Without Real Side Effects
A new hostname doesn't mean new authority. Learn why AI agent preview deployment needs credential isolation, not just a branch deploy.11 min readAI agentsdeployment testing
AI Agent Retry Policy: When to Retry, Repair, or Stop
An AI agent retry policy must treat timeouts, auth errors, schema faults, and policy refusals as different problems, not one loop.12 min readAI agent retry policyerror handling
AI Judge Calibration: Read the Confusion Matrix First
AI judge calibration means checking a trace evaluator against blind human labels before routing any case on its verdict alone.12 min readAI judge calibrationevaluation engineering
AI Reviewer Context Isolation: What Actually Contaminates
AI reviewer context isolation starts with the actual request payload. Build a tested allowlist and separate primary evidence from prior verdicts.11 min readAI reviewer context isolationmulti-agent review
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
Continued on the next page.
To browse rather than follow: topics, all articles and all thoughts. To learn in order: courses and the book.
