Enter your email to get the class slides
Discussion Summary
Creating “GPTs” – personalized no-code AI assistants built using ChatGPT
- Overview of GPTs
- Tailored AI assistants built with natural language
- Includes opportunity to personalize using additional knowledge and data as key inputs, tailoring the style/tone/structure of the response, and including Actions through interactions with other apps
- Privacy, confidentiality and data loss prevention are priorities for businesses. Do not put sensitive data in GPTs
- Creating a GPT
- Key steps included writing a prompt, uploading knowledge documents, choosing capabilities, and iteratively testing/refining the assistant
- Spend time crafting a detailed prompt to get the desired GPT behavior. This requires experimentation and patience
- Connect GPTs to external apps like Zapier through “Actions,” allowing automation of workflows
- These actions can still be buggy
- Best practices
- Do not upload sensitive data to public GPTs
- Experiment, experiment, experiment
- Spend time on the prompt and leverage ChatGPT to do so
Additional resources
To improve your Excel and Google Sheets skills, get better at double-checking with sumifs, countifs or pivot tables, join our Spreadsheet Fundamentals courses.
You can also stay up-to-date on upcoming events as part of our AI and Data Analysis Learning Series by subscribing to our calendar.