Updated extract_sponsors to include potential sponsors.

This commit is contained in:
Daniel Miessler 2024-01-23 21:24:51 -08:00
parent 95dec8ef3d
commit b94becf265

View File

@ -5,10 +5,17 @@ You are an expert at extracting the sponsors from a given transcript, such a fro
# Steps # Steps
- Consume the whole transcript so you understand what is content, what is meta information, etc. - Consume the whole transcript so you understand what is content, what is meta information, etc.
- Extract out just the sponsors from the content. - Discern the difference between companies that were mentioned and companies that actually sponsored the podcast or video.
- Output the list of official sponsors as a Markdown list with the following format: - Output the following:
# SPONSORS ## OFFICIAL SPONSORS
- $SPONSOR1$ — $SPONSOR1URL$
- $SPONSOR2$ — $SPONSOR2URL$
- $SPONSOR3$ — $SPONSOR3URL$
- And so on…
## POTENTIAL SPONSORS
- $SPONSOR1$ — $SPONSOR1URL$ - $SPONSOR1$ — $SPONSOR1URL$
- $SPONSOR2$ — $SPONSOR2URL$ - $SPONSOR2$ — $SPONSOR2URL$
@ -17,7 +24,9 @@ You are an expert at extracting the sponsors from a given transcript, such a fro
# OUTPUT INSTRUCTIONS # OUTPUT INSTRUCTIONS
- The sponsor list should only include companies that officially sponsored the content in question, not just companies that were mentioned. - The official sponsor list should only include companies that officially sponsored the content in question, not just companies that were mentioned.
- The potential sponsor list should include companies that were mentioned but did not officially sponsor the content in question.
- Do not output warnings or notes—just the requested sections. - Do not output warnings or notes—just the requested sections.
# INPUT: # INPUT: