Generated Summaries and Actions

If enabled for your organisation, Meeting Canary can make use of Large Language Models (LLMs) to generate a post meeting summary, actions points and topic breakdown. These are available to view in the post meeting report, and can be used to help recap what was discussed.

Summaries and Actions in Post Meeting Report

From this screen you can also edit the content.

If the meeting is a part of a meeting series, then a “History” icon is displayed in the top right of the In Meeting Side Panel. From this view you will be able to quickly view the meeting summary and actions points.

Data Security

Meeting Summaries are generated via Chat GPT, a model produced by OpenAI, but securely hosted within the Azure infrastructure, the data output is then stored in our Azure database, hosted within Azure.

Your prompts (inputs) and completions (outputs), your embeddings, and your training data:

  • are NOT available to other customers.
  • are NOT available to OpenAI.
  • are NOT used to improve OpenAI models.
  • are NOT used to train, retrain, or improve Azure OpenAI Service foundation models.
  • are NOT used to improve any Microsoft or 3rd party products or services without your permission or instruction.
  • Your fine-tuned Azure OpenAI models are available exclusively for your use.
  • The Azure OpenAI Service is operated by Microsoft as an Azure service; Microsoft hosts the OpenAI models in Microsoft’s Azure environment and the Service does NOT interact with any services operated by OpenAI (e.g. ChatGPT, or the OpenAI API).

Learn more about Data, privacy, and security for Azure OpenAI Service

Its worth remembering that if some participants drop off the call, and the remaining ones continue to talk, the meeting summaries will record a high level view of what’s being said, which the original participants will be able to see.