Learn to build with AI

Bank reconciliation is the task everyone wants to automate, and before today's AI tech, nobody could. Alane Boyd and Micah Johnson explain why it stayed manual for so long, then walk through the exact prompt that turns eight to ten hours of line-item matching into a short 10 min review.

When you export your statements from your bank and QuickBooks (or another accounting platform), there are no matching IDs, no shared descriptions, and nothing a traditional automation could key off; somebody had to sit down and compare them line by line, and that somebody was expensive.

In this episode, you’ll learn:

• Why rules-based automation could never reconcile your books and what changed when AI could read AWS, Amazon Web Services, and Amazon Web SVCS as one vendor
• The three-rule starting prompt that matches on description, amount, and a three-day date window
• How to read the exceptions when AI explains that a check has not cleared or a bank fee has not hit QuickBooks yet
• How to turn the first run into a reusable skill so you never re-explain your setup again
• Where the human stays in the loop, because the matching is low-value work and the exceptions are not
• How the same approach applies to investment property statements, media buys, and anything else with two lists that should agree

Reconciliation might be a boring task, but that's exactly why it is a great place to point AI first. Press play and start automating your reconciliation workflow this week.

Automate Your Agency is taking a short break and coming back as something different. Alane Boyd and Micah Johnson are reimagining the show to match where AI actually sits (and shouldn't sit!) in a business today.

The questions listeners send in have moved well past “how do I automate this workflow.” They now cover finance, marketing, executive teams, and everything in between, and the show is being rebuilt to match.

What’s changing:

• A new name and a new brand for the show, arriving after a couple of weeks off recording
• Same feed, same place to listen, so there is nothing to re-subscribe to
• Every past episode stays available; the back catalog is not going anywhere
• Deeper use-case episodes across finance, marketing, and executive teams
• An open call for topics, because the next format is being shaped around what listeners ask for

Send over the topics you want covered!

Someone on your team ran a task through AI and forwarded the output without reviewing it. That person was a Meat Proxy and just generated Workslop. Yuck!

Alane Boyd and Micah Johnson break down these two terms, which sound like they should be in food manufacturing, and describe exactly what can go wrong inside AI-forward companies.

In this episode, you’ll learn:

• How to tell a meat proxy from someone using AI well and why knowing the desired outcome is the whole difference
• What your colleagues actually think when they spot unread AI output, backed by the numbers on trust and credibility
• The tells that give workslop away, from verbose answers to ignored brand guidelines
• Why “train your team” isn’t enough unless you define what the right way to use AI looks like at your company
• How making AI use visible turns a shameful shortcut into a useful handoff
• The one requirement that forces people to read the output before it leaves their desk

If your team is moving fast with AI and you’ve started to notice the quality slipping, this conversation names the problem and gives you several things to change today.