Vizard Agent

How to take a product's claims off its packaging instead of from memory

Last updated 2026-10-10 · 2 min read

Tell Vizard Agent to take every stated figure from the packaging in your own photographs. The panel is already in the picture at higher resolution than the finished video needs, so it can be enlarged and read rather than remembered. Remembering is how a wrong number gets onto a closing card in the first place.

What do you type into Vizard Agent?

Name the packaging as the source of truth, explicitly. Without that, a figure in your brief is the most authoritative thing Vizard Agent has, and a number you typed from memory will go onto the card faithfully and confidently. It also gives you a check: ask which photo a figure came from, and there should be an answer.

Make a reel for this protein bar from these photos. Take any nutrition figures from the packaging in the photos, not from what I have written.

What does Vizard Agent actually do?

It treats the photograph as a document. When a figure needs to go on a card, the relevant part of the original image is enlarged until the print is legible, then read, and the card is built from what it says, not from the brief or a plausible value. In the session behind this article it:

When does this not work well?

When the panel isn't legible in any photograph. A dim or angled shot of small print can't be enlarged into readable text, and Vizard Agent will say the figure is unreadable rather than supply one. The same product can also carry different figures in different markets, and reading a number correctly doesn't make it lawful to state in an advert.

Common questions

Does the panel need to be readable in the final video? No. Vizard Agent only needs it legible in the source photograph.

What if my brief and the packaging disagree? The packaging wins, and Vizard Agent tells you there was a conflict.

Will it invent a plausible number? No. Vizard Agent reports the figure as unreadable instead.