Insight SnAPP
Launch Date
September 2023
Role
Lead Product Designer
Website
Related Skills
Product Design, Project Management, Usability Testing, Factory Automation
Project Name
This is your Project description. Provide a brief summary to help visitors understand the context and background of your work. Click on "Edit Text" or double click on the text box to start.
PRODUCT BACKGROUND
​Background
Cognex is a leading provider of vision systems, software, sensors, and industrial barcode readers used in manufacturing automation. Cognex is a global company and throughout this project I collaborated with teams across America, Hungary, and Germany. The technology used as the foundation for the Insight SnAPP is called "Edge Learning".
​
Edge Learning is a subset of artificial intelligence (AI) in which processing takes place on-device, or “at the edge” of where the data originates, using a pre-trained set of algorithms. The technology is simple to setup, requiring less time and fewer images for training compared to other AI-based solutions, like deep learning. Target users for SnAPP were expected to be familiar with factory automation sensors and controls, but not machine vision or deep learning.
​
Goal
The goal of SnAPP was to create an easy-to-use, multi-app device that targeted a broad range of applications in the 2D Industrial Measurement Sensor market.
Problem Space
During the planning phase of the project it was important to identify areas of difficulty to be mindful of as we progressed. Defining the problem space ahead of time helped to manage expectations and mitigate risks.
​
Simplification
-
How to create a simple workflow for tools that are traditionally quite complex?
-
How to reduce setup time from days and hours to minutes?
​
Newness
-
How to design a product that fits with the rest of Cognex's product suite, without the resource of a Design System?
-
How to get stakeholders to embrace the first web-based product?
-
How to collaborate with and support engineers who are new to front-end and Angular development?
​
Technical Constraints
-
What can we achieve with the resources, time, and skillsets available?
-
What are the limitations of the Edge Learning tools?
-
How does training on the device impact speed and memory?
WORKFLOW MAPPING
After working with Product Management to develop the product requirements, I iterated through several workflows with key stakeholders and we decided on the following approach.
USER TESTING
Usability testing had not been performed at Cognex before; but since SnAPP was attempting to broach an entirely new customer market, it was important to the development process that we could continuously gather feedback from our target users and integrate it into the product before we launched.
​
As the resident subject matter expert on usability testing I designed the testing plan, wrote the testing script, created a standardized note taking document, ran the preliminary internal usability tests, and trained marketing and sales employees on how to conduct sessions with customers in the field.
​
After each phase of testing I worked closely with the marketing and engineering leads to analyze the findings and prioritize our backlog of work. Engineering teams were especially responsive to this process as it helped to focus their priorities and prevented last minute reworks and feature requests.
​
​
FINAL DESIGN
For this project I developed several different tools that the device would support - Anomaly Detector, 2-Class Classifier, 4-Class Classifier, and Count. Each of these tools have variations in their Train step, but they all share a common workflow and components. It was very important that these tools felt like one cohesive product.
​
Below you can follow the walkthrough for the 2-Class Classifier
If you'd like to see more about this product check out it's page on Cognex.com or any of the product walkthrough videos put together by the wonderful Marketing and TechDocs teams!