A folder of documents becomes rows, the rows are processed in batches rather than one at a time, and nothing leaves until a person has marked it reviewed. The gate is the product.
Tag: Ai
2026
Running 7 scanners is a thread pool and an afternoon. Making them agree on what a finding is — one shape, one severity scale, one row per problem — is the whole product.
Arabic, English and Hebrew, collected and enriched by a worker with a queue per stage. The same 6 stages as everything else in this series, except a shift depends on them being up.
Six megabytes of exported messages, labelled and filtered by a few dozen keyword rules. No model, no API bill, nothing leaving the laptop — and every label traceable to the line that produced it.
The same 6 stages as a one-file watcher, except every one of them has grown into a component: continuous collection, cross-posting detection, machine translation, an AI pass, a map and a dashboard.
Four years of data on frontier AI releases and security. No breach wave followed each launch. Published flaws doubled in 2026, exploitation rose almost as fast, ransomware barely moved, and the PHP2Shell disclosure on 21 October showed how fast the gap between finding a flaw and using it can close.
Six rules for putting a model anywhere near an investigation: assume it will be confidently wrong, keep every claim traceable to a fetched artifact, and treat a page you collected as something that might be talking to your model.
One stage out of 6, and a short list of jobs inside it. The test that sorts the narrowing work a model can take on from the verification and attribution work it can only draft — and why that draft is a lead, not a finding, until a person has checked it.
Not AI, not robots. Six stages that every collection system turns out to be a version of — and the 4 cases where the right answer is to do it by hand.