Page 10 of Will's Journal.
This is page 10 of Will's Journal — a later slice of the archive, not the hub.
Writing on AI visibility, automation, agents, and websites — from Spurlock Studios.
Which notes are on page 10 of Will's Journal?
AI Agents How do I write good tool schemas for AI agents
Write tool schemas as agent UX: honest required fields, enums for closed sets, descriptions that constrain, and one non-overlapping tool per side effect.
AI Visibility Entity Architecture: Making Your Brand a Thing Models Can Name
Entity SEO for AI search means consistent Organization, Person, and Product identity across your site and the web — so models can name you instead of hedging.
AI Agents How do I stop an agent from doing something destructive
Stop destructive agent actions with a blast-radius table, an allowlisted tool set, and dual control on money and delete, enforced in code before the tool runs.
AI Agents How do I test AI agents before they ship
Test AI agents before they ship on a golden set, staged tools, and shadow mode. Pass rate is not the gate — score cost, escalate, and known-bad fails too.
Websites Pre-Save Pages Convert Campaigns — Homepages Hold the Career
Put new releases on a pre-save campaign page for ads and bio links; keep the homepage as the career surface — then swap to listen/stream without breaking URLs.
Automation Idempotency Keys in n8n: Stop Double-Charging, Double-Emailing, Double-Everything
Same webhook event in, same outcome out: an n8n idempotency key stops a timed-out provider retry from charging, emailing, or creating a CRM row twice.
AI Agents How do I manage multiple AI agents in production
Isolate each production agent: credentials, write surface, named owner, and evals. Handoff with typed contracts. Do not share one god-agent across jobs.
AI Agents How do I keep the agent from emailing customers when injected via a ticket
Treat ticket text as untrusted data. Keep send-email off the reader, gate the proposed send in code, and require a human before any customer outbound fires.
AI Agents Sandboxed Tool Use: Letting Agents Act Without Letting Them Loose
Tool use without a sandbox is an API key with opinions. Allowlists, scoped credentials, blast-radius caps, dry-runs, and human gates earn a production write.
AI Agents How do I set policies for what agents can and cannot do
Write a named-owner catalog that returns allow, deny, or pending-approval before every tool, then fail closed if that catalog cannot load. Not legal advice.
AI Visibility GEO Explained: Generative Engine Optimization Without the Buzzwords
GEO is optimizing pages so generative engines can retrieve, compress, and name you. Treat it as AEO on those surfaces, not a third religion beside SEO.
AI Agents Single Agent First: Split Only When Trust, Audience, or Timing Conflicts
Start with one agent and many tools. Split only when trust, audience, or timing conflict—and prove that split with pass rate, cost, and escalate rate.
What should I know about this archive page?
- What is page 10 of Will's Journal?
- Page 10 of Will's Journal is a later slice of the archive, not the hub. The writing is on AI visibility, automation, agents, and websites — from Spurlock Studios.
- Where is the first page of Will's Journal?
- The first page is the hub at /blog. This URL is a later page of the same journal; previous and next links move through the rest of the archive.
- Is this a different journal than the hub?
- No. This is the same Will's Journal from Spurlock Studios — page 10 of the archive, after the notes on the first page.