AGD Intelligence

De-nest and handle single tortillas from a stack

Reser's produces enormous tortilla volumes (historically reported at roughly five million tortillas a day) under its Don Pancho and Baja Cafe brands, and tortillas are a key input to downstream burrito and wrap assembly. Separating a single thin, limp, and tacky tortilla from a stack and transferring it without tearing, double-picking, or wrinkling is a classic deformable-handling problem: the object has near-zero bending stiffness, variable moisture and tack between sheets, and shifting geometry as it lifts. The task sits upstream of assembly/folding and ahead of packaging, where a mis-pick stalls the line or wastes product. Vision can locate the top sheet but cannot confirm that exactly one was separated or that it lifted cleanly. This is a high-frequency, repetitive manual or mechanically fixtured operation today. We identified this through our own research; we have not confirmed the specifics with the customer directly. This page is our researched read — a starting point for that conversation.

Readiness
build now
Demand
weak
Source
researched
Failure tol.
high
Tactile value
high
i

What the task is

RESEARCHED · our reconstruction

Reser's produces enormous tortilla volumes (historically reported at roughly five million tortillas a day) under its Don Pancho and Baja Cafe brands, and tortillas are a key input to downstream burrito and wrap assembly. Separating a single thin, limp, and tacky tortilla from a stack and transferring it without tearing, double-picking, or wrinkling is a classic deformable-handling problem: the object has near-zero bending stiffness, variable moisture and tack between sheets, and shifting geometry as it lifts. The task sits upstream of assembly/folding and ahead of packaging, where a mis-pick stalls the line or wastes product. Vision can locate the top sheet but cannot confirm that exactly one was separated or that it lifted cleanly. This is a high-frequency, repetitive manual or mechanically fixtured operation today.

To confirm with the customer

Is this the actual task and sequence? What are the real tolerances, cycle rate, and reject criteria, and which steps are today's manual bottleneck? Answering these is what turns this from a researched signal into a validated use case.