Write the Table Before the Agent
If the agent can act, someone needs to write down where the line is.
Anthropic’s new threat report is easy to file under security.
That is too narrow.
The useful lesson for normal companies is simpler: the agent needs a boundary before it needs a bigger model.
Write a table that makes the boundary explicit.
What can it read?
What can it change?
What needs approval?
What gets logged?
That sounds almost too plain. Good. Plain is where control starts.
Teams fail when nobody can answer the practical questions after access is granted. Can the support agent see customer records? Can it edit them? Can it draft a refund? Can it issue one? Who checks the log on Friday?
Those answers define the workflow.
Agents inherit whatever mess already exists: shared accounts, old tokens, broad permissions, weird spreadsheet exports, tools nobody has audited in a year. Then they move faster inside it.
So slow the first step down.
Before the agent touches a live system, write the table. Put a name next to it. Review it after the first week of use.
If the table is hard to fill out, that is the warning.
The agent is not ready.
Neither is the workflow.