Method·July 23, 2026 · 6 min read

Why no item reaches you without a human

The model drafts. It is structurally unable to publish. The database constraint that makes our review rule a fact rather than a promise — and why this audience should demand one.

By Connor Griggs — Regulatory & Quality Strategist

Every regulatory intelligence tool built since 2023 says some version of “AI-powered, human-reviewed.” The phrase is doing no work. It describes a workflow the vendor can quietly stop following on a busy week, and you would never know. So instead of asserting our review rule, this post explains how it is enforced — because “we promise” and “the database refuses” are different grades of claim.

The failure mode we are paranoid about

A generated recommended action that is plausible, fluent, and wrong is worse than no recommendation at all — because this audience acts. The reader of an FDA Radar item is not browsing; they are deciding whether to open a CAPA, review a risk file, or call their consultant. The failure we design against is not embarrassment. It is a professional acting on confident, wrong advice with our name on it.

What the constraint actually enforces

The language model in our pipeline drafts summaries. That is the entirety of its authority. An item cannot reach published state without three fields the model has no path to supply: a human-assigned urgency, a human-written recommended action, and the reviewer’s name. The rule lives in the database as a constraint, not in a process document — the publish simply fails without them. On a busy week the queue backs up; nothing unreviewed leaks past it. We consider that trade obviously correct, and we notice competitors making it the other way.

A monitoring product is a chain of claims. Ours ends with a person’s name on every link.

Two supporting habits

The raw archive is immutable. Every FDA document is stored as fetched and never edited. FDA does silently revise guidance pages; against an immutable archive, a silent revision becomes a detectable diff instead of a private memory. When the source changes under an item we published, that is a fact we can show you, dated.

Corrections are appended, never disappeared. When we get something wrong, the correction renders on the item’s permalink, above the fold, dated, next to the original claim. An intelligence product that silently rewrites its record is asking you to trust its present tense. We would rather show you our error rate and let the record argue for itself.

Why we publish the mechanism

Partly because this audience checks small things for a living, and deserves vendors who expect to be checked. And partly as a commitment device: having told you the constraint exists, we cannot remove it without the removal being a lie. The review rule costs us speed on exactly the weeks speed would be easiest to sell. That cost is the product.

Regulatory intelligence, not regulatory advice. This post describes method and published FDA records as of its date; decisions about a specific device belong with your regulatory professional.

Method
A Class I device, a Class I recall
Practice
21 CFR 820 didn't move. Its contents did.
Method
The product code that doesn't exist yet
Practice
The classification posts. The 483 behind it doesn't.
Method
A recall has three dates, and the pipeline had to pick one
Practice
The count is real. The rate is not.
Method
The firm on the record is not the firm on the box
Practice
Low confidence is an instruction, not a hedge
Method
The same company, spelled three ways
Practice
A device that was never a medical device
Method
FDA's warning letters, addressed by column number
Practice
Your regulation has a decimal. FDA's watch doesn't.
Method
Three letters is too short to search for
Practice
Most warning letters never close
Method
The guidance that skipped the draft
Practice
Ongoing, as of when?
Method
The least interesting fact in a 510(k)
Practice
No recall arrives with a product code attached
Practice
The deadline that doesn't email you
Method
The warning letter has two dates
Method
How to monitor FDA without drowning
Practice
Your predicate was recalled. Now what?