Operator Chat Widget
  • 26 Jun 2024
  • 3 Minutes to read
  • Contributors

Operator Chat Widget

Article summary

The Frontline Copilot® Operator Chat Widget is designed to empower your users to swiftly navigate from problems to solutions in a secure, scalable, and efficient manner. Leveraging Tulip tables, which serve as the primary data repository for Tulip customers, including rich media such as PDFs and images, the Operator Chat Widget equips your users with the superpower to extract answers from diverse data sources within the product.

Frontline Copilot® Operator Chat Widget in action

This widget learns from both the raw data stored in Tulip tables and the information contained in documents within those tables, presenting it to users through a simple chat interface. Whenever records are created or updated within a Tulip table, the Operator widget automatically retrains to incorporate the latest information, ensuring that responses are always based on the most up-to-date data available.

Example Use Cases

The flexibility of this search functionality opens up a wide array of potential use cases:

For Maintenance Departments:

  • Quickly look up error codes from machine manuals.
  • Retrieve recommended actions for machine repairs.
  • Identify necessary supplies for specific machines.

For Quality Teams:

  • Provide safety data sheets in response to queries.
  • Conduct rapid audits of work instruction documents.

For Production Teams:

  • Guide users to solutions using an Issue:Solution table.
  • Direct supervisors and trainers to relevant work instructions on the production floor.

For Engineering Teams:

  • Search through existing training documents.
  • Look up available materials or supplies.
  • Retrieve print specifications.

For Best Results

The Operator Chat Widget is designed to extract information from tables and excels at specific tasks.

In manufacturing, where extensive documentation and information exist, the Operator Chat Widget is built to find and deliver this information to users in natural language. It is particularly useful for tasks such as retrieving relevant information from PDFs or identifying past solutions from tables of previous issues and resolutions.

However, the Operator Chat Widget cannot answer questions like:

  • "How many scrapped parts did I have yesterday?"
  • "What is our biggest scrap rate today?"
  • "Make me a paredo breakdown of Scrap"

For these kind of questions, we recommend using Chat with Tables.

This limitation is intentional. Frontline Copilot® aims to provide users with enough information to validate accuracy of any Frontline Copilot® response. Operators closest to manufacturing seldom have the access to confirm the accuracy of aggregated data before acting on it.

How To

Add The Widget

  1. Select the "Frontline Copilot®" from the Embedded section of the widget selector.

  1. Resize and position the widget.
  2. Select which table the chat experience should learn from.
  3. Click "Train".

If the table is not yet being used elsewhere, training will begin, and can take up to 24 hours. When a table is being used elsewhere training will complete in a few seconds.

Hovering over the pill in the "Training" state will show progress.

  1. When the "Training" pill turns to "Trained", the widget is ready to use.

Operator Chat Widget Statuses

UntrainedFrontline Copilot® is ready to learn
TrainingFrontline Copilot® is ready to learn
TrainedFrontline Copilot® is ready to be used. All records and documents have been learned
Partially TrainedFrontline Copilot® is ready to be used, but some documents or records could not be trained.
UpdatingFrontline Copilot® is learning new or updated information.
FailedReach out to support@tulip.co for more information.


The following limits are in place for all Copilot Agents

  • PDFs in the following languages can be read by the operator widget: English, Spanish, Italian, Portuguese, French, German.
  • For each table: the first 10,000 Records will be encoded (by creation date)
  • For each PDF: 500 page limit, encoding will fail on larger documents.
  • For each instance:
    • Count of Tables that can be trained
      • Essencials: 1
      • Professional: 3
      • Enterprise and Regulated Industries: 10
    • Maximum count of updates that will be retrained monthly. This excludes initial training.
      • Essencials: 20,000 Updates/Month
      • Professional: 60,000 Updates/Month
      • Enterprise and Regulated Industries: 100,000 Updates/Month

Other Limitations

  • CSV files uploaded to tables after the chat widget has been trained will not be atomatically processed and may not be accessible to operator chat.
    • Subsequent edits to these records will lead to them being accessible to operators.
    • Any CSV upload before the operator chat widget is trained will be processed.
  • All PDFs must not be password protected.
  • Only Image and PDF file types can be trained upon, not CSV, Text, gcode, or other file types that can be stored in tables.
  • Images must be below 5MB to be processed.

Was this article helpful?