Every Wednesday I share one lesson from running my own fleet of AI agents. This week’s is about the word “latest.” When your agent grabs the newest item, or the first one in a list, it’s following a priority rule. You just never wrote that rule down. Setting AI agent priorities on purpose means you decide what “next” means before the default decides for you.
The receipt: 47 long guides, 0 shares
Two of my agents write for this site. One publishes a long guide just after midnight, Bali time. The other publishes a short daily post like this one at 7:07 AM. Around 9 AM, my social agent wakes up, grabs the most recent post, and turns it into posts for five platforms.
Read that schedule again. At 9 AM, the most recent post is always the short one.
I counted everything published since August 28: 47 long guides and 61 daily posts. Then I checked the social log. All 61 daily posts got shared. 0 of the 47 long guides did. Those guides are the 2,500-plus-word pieces with real research and a stack of images. A different agent mentioned five of them later while covering related topics. The other 42 never reached a single social feed through my agents.
Nothing broke. Every run finished and logged a success. The instruction literally says “get the most recent published post,” and the request behind it asks WordPress for exactly one post, the newest. That’s a priority rule (“newest wins”), and nobody chose it. It came bundled with the query.
⚡ GET THE AI EDGE
Weekly AI tips that actually save you time and money. No fluff, no hype — just what works.
Today’s guide, a Kiro vs Claude Code comparison, went live at 00:12. This post goes live at 7:07. You can guess which one gets shared this morning.
Where hidden priority rules live
- “Newest first.” Sort by date and take one. That works for news. It’s wrong when your best work isn’t your latest work.
- “Top of the list.” Whatever sits first in a queue, sheet, or inbox. Usually that’s just the order things were added.
- “Just one record.” Any time an agent fetches exactly one item, something decided which one. Find out what.
- “Whatever ran last.” Run two agents on a timetable and the order of that timetable quietly becomes your strategy.
How to set AI agent priorities on purpose
- Find every “take one.” Search your agent’s instructions for “latest,” “most recent,” “first,” and “limit 1.” Each one is a decision someone made by default.
- Write the rule as one sentence. Mine should read: “Share the newest long guide that hasn’t been shared yet. If there isn’t one, share today’s daily post.” The agent can follow that, and I can check it.
- Count the leftovers, not just the picks. My logs only listed what got shared, and every entry looked fine. The problem only showed up when I listed what never got picked. Once a month, count what your agent skipped.
The honest part
I haven’t changed the social agent yet. Which posts represent the brand on social is my call. My agent shouldn’t rewrite that rule on its own at 7 AM, so the fix is on my list with the numbers attached. The lesson goes beyond one agent, though. An agent can do exactly what you said, every day, with zero errors, and still work on the wrong thing. It’s the same pattern as a human in the loop nobody actually closes or a timezone nobody set. In each case, a default made the call.
The takeaway: “latest” is a priority. So is “first.” Decide what your agents should pick, write it down in one sentence, and count what they leave behind.
If your agents look busy but you’re not sure they’re busy on the right things, book a strategy session and we’ll find the defaults that are making your decisions.
See you next Wednesday.
Jon
📥 FREE: THE AI PLAYBOOK
The exact tools and workflows I use to run a one-person agency. 25 years of marketing experience distilled into an actionable guide. Yours free.
AI & Digital Marketing Strategist
With over 25 years in digital marketing, e-commerce, sales, and international business, Jon Jones is a seasoned entrepreneur dedicated to empowering small businesses through innovative AI solutions. His journey began in investment banking on Wall Street, guiding companies through capital acquisition and complex markets, and has expanded to include expertise in web development, brand design, product development, and courses and training.
Fluent in Mandarin and with a rich foundation in both finance and tech, Jon launched JonJones.ai to provide accessible, transformative tools for small businesses to streamline operations, generate leads, and build sustainable growth. His mastery of AI, automation, and digital strategy has enabled numerous businesses to bridge the gap between traditional practices and modern technology, ensuring they thrive in today’s digital landscape.
