A prompt is a suggestion, not a contract. Replit's agent wiped a production database mid code-freeze — proof that guardrails belong at the infrastructure layer, not the prompt layer.
A complete reference for AI agents writing, editing, or managing posts on this blog. Covers file structure, frontmatter schema, Markdown conventions, and validation.
Practice the diagnostic loop: Find a task your agent keeps failing in your project. Run it once, log the failure. Attribute it to one of five classes. Fix that class. Run it again. Repeat three to five…
Affordance analysis: Find a situation where an agent in your project 'wants to do something but can't' (e.g., knows it should use parameterized queries but doesn't know your project's ORM…
ACID assessment: Assess your project's state management using this lecture's ACID analogy. Atomicity — can agent operations be cleanly rolled back? Consistency — is there verification…
Verify the lost-in-the-middle effect: In a long instruction file, place an important constraint at the beginning, middle, and end in turn, running the same task set each time (at least 5 runs per position). See if compliance rates differ…
Mixed strategy experiment: In a 5-session development task, compare three strategies: (a) always start a new session + progress file, (b) do as much as possible in one session (context compaction),…
Initialization acceptance checklist: Design an initialization acceptance checklist for your project. Have a new agent session execute each item on the checklist and record which ones pass and which…
Completion Evidence Audit: Review the output of a recent agent run, classify each code change as 'completed behavior,' 'unfinished behavior,' or 'scaffolding.' Add the missing…
Single Source of Truth Audit: Review an existing agent project and check for scope information that conflicts with the feature list (hidden requirements in conversation, TODO comments in code, etc.). Design…
Multi-Layer Defense Experiment: Run three configurations on the same task set—(a) static analysis only, (b) adding unit testing, (c) full three-layer verification. Compare the rate of premature completion claims and the number…
Promote Review Feedback: Find a recurring type of comment from your code review history and convert it into an automated check using the five-step process. Compare the frequency of the issue before and after promotion.
Build a Task Trace: Record every step of an agent's operations during a complete coding task. Annotate with OpenTelemetry semantic conventions. Analyze the information bottlenecks…
Practice Harness Simplification: Choose one harness component, temporarily disable it, and run benchmark tasks. Compare results with and without it. Decide whether to keep, remove, or replace it.