What's new in Prompt Builder
Words: | 3,206 |
Duration: | 00:18:15 |
Recorded On: |
|
Uploaded On: | about 2 months ago [Wed, 18 Sep 2024 17:55 UTC] |
Transcribed On: | about 2 months ago [Wed, 18 Sep 2024 17:56 UTC] |
At: |
|
Using: | uploaded [What's new in Prompt Builder.mp4] |
Language: | English (US) |
Channels: | 2 |
Sample Rate: | 44100 Hz |
Shareable Link: | |
Speakers: | A - 55.27% B - 44.73% |
Notes:
- Welcome to what's new with Promptbuilder. Salesforce is a publicly traded company, so please make your purchasing decisions based on what is publicly available today. We hope you're having an amazing first day with many more to come.
- PromptBuilder is focused on data, trust and availability. We are constantly striving to improve prompt accuracy. Today I'm going to show you two demos, one with our new data, uh, provider record snapshot, and the other Einstein search.
- A record snapshot is a combination of all of the relevant fields on an object on the running users page. It will combine all the fields that are most relevant. Only the fields the user has access to will be included and sent to the large language model.
- The next thing I want to talk to you about is Einstein search. Einstein search is retrieval augmented generation. What this means is the retrievers that you set up in data cloud can now be used in prop builder. For this demo, let's pretend that we've created a wine recommender app.
- Field based masking uses metadata in salesforce fields that you specify an object manager to mask. Pattern based uses a combination of patterns, regular expressions, and machine learning models to automatically detect certain fields. This is really, really exciting because you all now have more opportunities to protect your data through the trust layer in prom builder.
- All right, good there. Please feel free to take a picture of this as well if you want to go deeper, dives into how promptbuilder works. So we look forward to seeing you at some more of these events, uh, in the next couple of days.