How to fix indecipherable public data with AI
_**Make it Readable**_**, part one: using AI to bend data toward your questions. This part is inspired by the Netflix documentary Freefall.**
I viewed Freefall on Netflix. Relatives of victims were attempting to find answers to their questions partly via a governmental website. Row after row of capital letters. Zone numbers. Single character codes.
What was the database? It’s called Service Difficulty Report and is maintained by the Federal Aviation Administration. When technicians in the United States find an issue with a plane (e.g., a crack in a component; rust under a piece of equipment; or a failed seal), they file it. These reports are then made available to everyone. You don’t need to sign in, pay a fee, or submit a request for records. There are 1,541,548 of these reports from 2000 (I didn’t use earlier years) through today. They relate to 44,812 separate planes.
For researchers, the database is a nightmare. A report will never tell you that there was an issue with “the landing gear.” Rather, it will state “**ZONE 700**.” Emergency landing? That’s just an **A**. But if it pops up elsewhere in the document, it means Airline.
The FAA documents never tell you that “the crew made an emergency landing.” Instead, it will simply say “**A**.”
A n airline’s name is made up of letters such as CALA. The technician’s finding is a completely different code. The code used to identify how the technician found the issue initially is a third code.
When I attempted to conduct a search using a legitimate query, I encountered timeout and latency issues. Typical IT issues with software that has gone unmaintained for a considerable period of time. Creating links between two pieces of data were difficult.
Finding anything remotely resembling a “lead” was even more difficult. This leads me to ask the question of any public database: Who is responsible for developing the protocol? Who controls access to the data? If the answer is that the public controls both, is the data presented in a way the public understands it? The answer is often no.
There are questions I want answered. What types of defects were reported yesterday? Which companies reported the most? At what time did they report them? Who were the individuals involved? What location on the airplane was affected? What type of defect was reported?
What action did the crew take in response to the reported defect? Without knowing the “when,” “what,” “where” and “who,” I cannot begin to determine “why.” Why does a single operator send the same airplane out for repairs 60 times in a year? How can that occur?
The database does not provide an explanation for that. I wanted to uncover the hidden stories within the data.
In the past (read 2025), I would download all the data into a spreadsheet, create a pivot table, rotated it one direction, rotated it another direction, and hoped the spreadsheet did not crash due to its size. In 2026, I type what I desire in my own language and the system creates it for me. I build about two original, highly hyper-focused research tools a week for myself and my clients
Imagination is the limit to creating things, not your ability to remember formulas or knowing how to code. If you can express what you desire, you can create it. How does that work? How did I build a full fledged tool, as shown below?
**A black box with white letters**
A majority of users who use AI will probably be doing so by way of a chat box in their browser. If they paste a document into the chat box, the AI will read it. If they paste forty documents into the chat box, some will drop off. If they ask the AI to create a complex tool, they will receive code that they must save, install and run themselves.
But if the same AI is running within a terminal (Windows, Mac, no download needed) it can access your file system, download anything that is required for execution, execute it, observe any errors and correct those errors. The latter portion is the key to this process. After completing its task, the AI observes the outcome of its work and attempts to complete the same task again. You act as an intermediary to convey information: do this, do that. If the terminal and AI is installed on a server, you can post the output directly onto the web. So out of a window that looks like it came from 1989 (it does)) you get a working tool on your own machine, or a website anyone can visit. The limit is no longer what you can build. Can you describe what you want?
Let’s start building the tool in the Terminal app. For a researcher who cannot code, the barrier is never imagination. It was having to learn to speak Python, to structure a project, to know about fail-safes, to know how not to leak your own material. Some of that still matters. But the part where you personally type the lines of code is over. Here is how I started the project. I downloaded the brand new LLM, GLM-5.3 Flash Lightning.
I gave it a link to the public aircraft defects database and asked:
_Can I use the FAA database to answer the questions when where what and who?_
It answers back in the same green characters. _Yes, that is possible. Should I show you how_?
It warned me about two of my questions. The **who** means airlines, and the airlines are hiding behind odd-looking codes across 26 years of history, some of them obsolete and some not. The **what** means every engineer writing up a repair in a private thicket of abbreviations, which will all have to be looked up. The **where** is the awkward one, because a report will often describe a repair without ever saying where on the aircraft it happened. The location is implicit. The mechanic knew. The AI found a list of FAA codes, I checked it, and granted it to rebuild the public database in human language.
That was just step 1. I found the information still overwhelming. How do I change that? The first picture that arrived in my head was a schematic aircraft, seen from the side, sitting at the top. Can AI build that for me? And how do I explain what I want to see? I asked: