We gave an AI a single research brief — carefully engineered across 8 iterative prompts — and it returned the complete regulatory schema for Florida private schools: 72 requirements, 11 agencies, every validation rule expressed as boolean code ready for a compliance engine to run.
A private international school in Florida is simultaneously subject to Florida state statutes, federal immigration law, labor regulations, IRS tax code, EPA asbestos rules, OSHA standards, FTC data privacy guidelines, and Department of Health inspection requirements — each enforced by a different agency, each on a different cycle. Nobody in the school has a complete picture. The regulations aren't secret. They're just scattered.
For Nord Anglia Education — which operates schools across 35 countries — the question was pointed: do we actually know everything we're required to comply with in Florida? And more pressingly: is there a way to verify compliance automatically, against actual school documents, rather than relying on institutional memory?
The answer required a prior step. Before any software could check compliance, every regulation had to be extracted from legal text and expressed as machine-readable logic. That extraction is what this story is about.
The method was 8 prompts — a deliberate, iterative sequence run in a single Gemini Deep Research session. Each prompt had a specific purpose. The result was not a report. It was a schema: 72 rows of compliance logic, ready to be loaded into a software engine and run against school documents in real time.
Most AI research is a single query. This was a structured methodology — each prompt building on the last, each one serving a specific function in a pipeline designed to turn statute language into executable code.
The most important upgrade across 8 prompts wasn't the scope — it was the format. The same regulatory content, expressed two different ways, produces a document versus a database. Only one of those can power software.
The structured prompt approach didn't just retrieve known regulations faster. It surfaced regulatory nuances that a manual research process — or a generic AI search — would likely miss entirely. Here are the five most consequential findings.
Below is a direct sample from the final compliance matrix — exactly as it emerged from the 8-prompt Gemini session, organized into the uniform 6-column schema enforced in Step 7. Each row is loaded into the compliance engine as a discrete check.
Below is the expert-engineered research brief from Step 3 — the one that did the core work. Copy it into Gemini Deep Research and follow it with the four expansion prompts listed at the bottom. Adapt the school names and state for your context.
The regulations governing a Florida private school were never secret. They are published in Florida Statutes, the Code of Federal Regulations, Department of Health guidelines, and scholarship provider handbooks. The problem was never access — it was structure. Every rule existed in legal prose. No software can evaluate legal prose directly. Software needs logic gates.
The 8-prompt methodology above is a translation pipeline. It takes statute language — "schools must maintain a register of daily attendance" — and returns code: Sum(Instructional_Days) >= 170 OR Sum(Net_Hours) >= Grade_Threshold. That code is what a compliance engine runs against a school's uploaded documents. Every row of the schema is a test. Every test returns compliant, partial, or non-compliant — with evidence cited from the document itself.
The same methodology applies to any jurisdiction, any school system, any regulatory domain. The prompts change. The output format stays the same. And the output format is the whole game.