My AI doesn't know what time it is
On a show day my AI assistant told me we had 25 minutes to air. We had about 85. Every clock in the building was right. The fix was not a better rule. It was a fact on the screen.
On a show day my AI assistant told me we had 25 minutes to air. We had about 85. Every clock in the building was right. The fix was not a better rule. It was a fact on the screen.
Customers are asking AI where to eat, who to hire and what to buy. This five-part checklist shows a small business owner what to check, in order, with sources.
A sourced timeline of the November 12 Microsoft 365 and Exchange Online outage (EX1550543, MO1550821): what Microsoft said, when it said it, and what admins should and should not do.
Google is handing more of your search campaigns to AI, and ChatGPT has an ads manager. Here are the dates, the defaults, and the questions to ask.
AI assistants read your reviews so your customers don't have to. Here is what that changes, what the rules are, and a routine any business can run.
If Google, Bing and Apple disagree about your hours or address, an AI assistant has to guess. Here is how to claim and match the three listings that matter most.
AI can only repeat what it can read. Here is what Google, OpenAI and others say their systems need from a small business website, and what you can skip.
OpenAI just opened a front door for businesses inside ChatGPT. Here is what claiming your listing does, what it does not do, and how to do it this week.
In July I wrote a guide to the AI pipeline that edits my weekly shows. Four months and 100 code changes later, the biggest change is not a feature. It is where the humans sit.
A local news outlet streamed election night with live results from the official county count, a rotating cast of hosts, and candidates joining from home. Nine AI sessions ran the back of house. Here is what worked, the one wrong number that aired, and what changed the next morning.
AI-assisted coverage of public meetings, built for a world that rightly distrusts AI-written news: local transcription, draft articles where each claim maps to a moment in the recording, and two human gates before anything publishes.
A weekly live production has a dozen stages, hard deadlines, and one operator. The fix was not more effort. It was a production ledger that always knows exactly where every episode stands, so a crash costs nothing but the restart.
Case Studies
A phone problem can live in any of six layers owned by five different vendors. This is how the ops stack from the earlier case study actually works: a diagnostic ladder that walks the whole call path from one conversation.
Case Studies
A watch-everything intelligence engine for one geographic market: public sources in, deduplicated and relevance-scored items out, a cited morning digest by 7 a.m. Adding a second market took a JSON file and zero code changes.
Case Studies
A one-person operation cannot afford a two-week rebuild after a dead machine. So both machines rebuild from one encrypted off-site copy, one script, one passphrase. Then the backups started failing on exactly one machine, and that was the point.
Case Studies
Every consultant hates timesheets, and every consultant leaks billable hours to bad memory. This system reconstructs the workday from evidence the tools already emit, and a human approves every entry before it becomes money.
Case Studies
A hyperlocal news platform: one weekly livestream becomes a week of short videos and articles, and a daily community brief drafts itself by 7:20 every morning. Humans still make every editorial call.
Build Logs
Per-minute AI clip tools make sense until you publish weekly. Then the math flips, and owning the pipeline wins on cost, quality, and control. Here's the math from my own show.
Case Studies
How AI tooling lets a single architect operate a multi-tenant cloud voice fleet, dozens of client networks, and a full security posture that used to need a team.
Playbooks
Phone systems taught me a standard: when it breaks, someone can't call 911. AI automation deserves the same discipline, and almost nobody builds it that way.
Case Studies
An auto dealer group was burning 20 to 30 staff hours a week transcribing vehicle titles onto state forms. Now an AI pipeline does it overnight, and review takes about 4 hours a week. A human still checks every title that deserves a second look.
Playbooks
Every automation I run can draft an email, a reply, a report. None of them can hit send. That one design rule is why I can run AI against real business email without losing sleep.
News
Build logs, playbooks, and case studies from AI systems that actually run in production. Written by the one person who builds and operates all of them.