Each agent looked clean; the team crossed the line. Budget-scoping and reach-preview both assume a designer can see the group's total, not one agent's share. That view does not exist in most products today.
Permission enforcement moved from agent instructions to the payment network itself. The cardholder grants a box; the rail holds it. Designing the grant moment now matters as much as designing the agent.
Read the source ↗
attached to Approval →
established
watching → emerging → established
A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.
38 documented sightings since Jun 2026 — every one traces to a dated source.
See the evidence → The harness is the signal the reviewer depends on. If it's too expensive to run or too noisy to trust, the human's review step loses its foundation before it begins.
Vercel split the task at money: search is free, purchase needs your yes. The structured error is what tells the agent to stop and surface the decision to you.
Read the source ↗
attached to Approval →
established
watching → emerging → established
A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.
38 documented sightings since Jun 2026 — every one traces to a dated source.
See the evidence → The interface question flips here. A human is no longer directing one agent but setting rules for thousands. Patterns that assumed one-to-one contact need rethinking at population scale.
The spec says what the agent does; it has no slot for what the human decides. Designers need to put budget, reach, and approval into the format itself, or teams will keep leaving them out.
Read the source ↗
attached to Approval →
established
watching → emerging → established
A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.
38 documented sightings since Jun 2026 — every one traces to a dated source.
See the evidence → The setup screen is where humans decide what the agent is allowed to want. Most products treat it as logistics. This study, at 73k posts, says that is the wrong read of the moment.
The agent spent real money and the human found out afterward. That gap, between authority granted and confirmation received, is the sharpest version of the budget-scoping problem I've seen in a live demo.
Read the source ↗
attached to Approval →
established
watching → emerging → established
A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.
38 documented sightings since Jun 2026 — every one traces to a dated source.
See the evidence → The gap this paper names is real: an agent starts with approved access, then grabs more, and no one saw that happen. Any product with long-running agents needs a decision surface at acquisition time, not only at setup.
Read the source ↗
attached to Approval →
established
watching → emerging → established
A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.
38 documented sightings since Jun 2026 — every one traces to a dated source.
See the evidence → No spend cap, no checkpoint requiring human sign-off, no log of planned actions. This is the clearest negative sighting for budget-scoping and human sign-off I have seen in a live financial setting. Build those in before you ship.
Read the source ↗
attached to Approval →
established
watching → emerging → established
A stable convention across independent vendors. Safe to standardize on — deviating from it now carries cost.
38 documented sightings since Jun 2026 — every one traces to a dated source.
See the evidence → Context shape as cost control is the sharpest argument I've seen for treating the Context pattern as infrastructure, not afterthought. Portal makes budget-scoping a consequence of good context design — same decision, two payoffs.
This reframes permissions as a quantity, not just a binary. If I'm designing a delegation UI and I'm not surfacing effect limits alongside capability grants, I'm showing users half the picture.
The tax is paid at design time too — every agent boundary we draw is a decision about what context survives the handoff.