Well with the LogAir.ai system and a little bit of AI know how you can do this easily.

First let’s ask NotebookLM, charged with your aircraft data, to give us the data needed to build a spread sheet. NotebookLM will know the recurring maintenance items and their Time In Service (TIS). It will also know recurring items like recurring ADs. To put this together we’ll ask the AI to output everything we need to build a spreadsheet. We ask this in JSON format — JavaScript Object Notation — a format well known to both AI systems and spreadsheet programs. Here’s the prompt:

Ok a slight twist now. One would hope you could go right to Gemini and ask it to make a spreadsheet. The only issue, Gemini doesn’t yet know how to make a spreadsheet. Oh well, let’s try OpenAI. Guess what? OpenAI will happily create and output a downloadable .xlsx file. It pays to shop around.

Ok so I paste my JSON data into the chat window of an OpenAI and ask for a spreadsheet to track aircraft maintenance. I asked for a set of cells in the upper left hand portion of the spreadsheet to enter the Hobbs time and date. It knows how to handle the items either by Hobbs time or calendar time.

Click for larger

OpenAI took a few minutes to return this file. Quite frankly, I am amazed at how good a job it did constructing the spreadsheet. The machine knows the difference between calendar time maintenance and operational hours (Hobbs) maintenance. The due soon feature is a nice touch. I didn’t ask for that. It would have taken me several hours by hand.

Now that you understand the process, it’s an easy matter to revise the resulting spreadsheet by prompting the NotebookLM model or OpenAI.

Let me know if you find this helpful…

–paul

Sun-N-Fun – Lakeland Florida, April 15-16 11:00am
I’ll be speaking at Sun-N-Fun on How AI is Bring Insights to Maintenance Logs. We’ll let you know where we are and where we’re headed.

Ariticles:

American Bonanza Society Magazine – February 2026 issue: How AI Unlocks the Hidden Intelligence in Maintenance Logs

I get a number of questions about scanning logs. The most important thing is to avoid procrastination and make some time to get the task done.

It’s really inexpensive to use a cell phone camera to PDF scanner application. Many modern cell phones have camera resolutions that will yield a greater than 300 DPI scan for an 8 1/2 x 11 in page. Remember to scan everything in your log. It’s a pain to unstaple the 8130 forms, scan and reattach them, but this adds value to the scanned record. In this way you get overhaul information including who overhauled the part and its serial number. Sometimes ADs pertain to certain serial numbered parts. The RAG-AI can keep track of it all.

Make sure the 8130 or other forms you find in your logbook are scanned in the order they appear in your logs. For best results scan those tags with a separate scan which will form a separate page. It’s best not to have any scan that is bigger than 8 1/2 x 11 inches.

Another consideration is that we don’t need to do Optical Character Recognition (OCR) on these files. Leave them as image PDFs. The Google AI API in the LogAir.ai system is by far the best OCR and the files will be converted on the fly when using the LogAir.ai system.

Their are various YouTube videos explaining using your phone to do the scanning. One of my favorite ones is here:

We’ll let you know how this goes.

–paul

Ok me in a weird space as one AI is complementing another AI. Interesting times we live in.

–paul

Ask yourself how long it would take you to look this information up in your aircraft logs:

Here’s a little exercise on what you can do with RAG-AI and ChatGPT. Total time to get this data in this form was about two minutes.

Let’s ask a simple question of LogAir.ai charged with my maintenance data, “Give me CSV values of the compressions on the right engine over the past six years.”

I get the values after a few seconds. I copy the CSV values and run them over to ChatGPT and ask it, “Graph these values” I get:

Wow, that last annual wasn’t so good. Truth be told, we had some major avionics work going on and the Baron had been sitting a lot, not being flown probably a month prior.

Ok, wow. Gives me an idea. When will this engine be totally done? I think the lower limit for cylinders is a compression value of 30 PSI. When is that going to happen?

I suspect the engine will be using so much oil by then, I won’t be able to take any long trips ;). Hopefully, the cam and lifters will hold up as well. I know I’m just playing here. But here’s the output:

Great in 2040 I’ll be 86. No reason to stop flying!

–paul

If you are using the FAA’s Dynamic Regulatory System to look up your aircraft’s airworthiness directives (ADs), did you know you are using a system that’s not an official source?

FAA documents explicitly state that the DRS is not the “official system of record”. The official record resides with the Office of Primary Responsibility (OPR) for each document according to FAA records management programs.

The only official source of information about ADs is the Federal Register.

The LogAir.ai staff have developed software to search the Federal Register for AD data. Only in this way do you know you have the unassailable answer.

PS: Both the DRS and Federal Register now appear to be offline as far as AD searches go. Ah Gov’t shutdowns.

PPS: Somebody wisely pointed out that having our app search the canonical Federal Register was as removed as having the FAA’s DRS search the Federal Register. Quite true. Our app will however produce the query used to get the data so you can apply it to the Federal Register yourself if you so desire.

–paul