Drug-Safety Agent on Databricks · Business flow
Why it matters: the business flow, end to end
An agent is only useful inside a flow: something sets it going, and someone receives what it produces. This page shows the whole flow, so you can see where the agent sits, what it replaces, and what stays with people.
The business problem
A drug-safety team keeps watching medicines already on the market. For each drug and side effect an analyst pulls the report counts, works out whether the pair stands out, checks the label, and writes a note. It is repetitive and the numbers must be exact. A missed pair or a wrong number can reach patients.
The advantage is not that the agent decides. It is that the analyst starts from a checked draft with the numbers already in it, and sees only the pairs that need judgement. The work that remains for a person is the part only a person should do: decide.
What it replaces, and what it does not
| Step | Who does it now | Status |
|---|---|---|
| Look across all pairs every week and pick those worth a look | The weekly screen, by plain code. 10 of 80 pairs qualify in this data. | built |
| Pull counts, work out PRR, check the label, write the note | The agent. Code reads and computes the numbers; the model writes the words. | built |
| Decide: approve, edit or reject | A named person, on the desk. The agent has no way to do this. | built |
| Take a case the agent could not finish | A person, from the hand-off list. | built |
| Put an approved item into the company's safety record | Not part of this agent. | not built |
| Tell a regulator | A person, outside the agent. It never files. | by design |