A recent blog post by Pete Koomen about how we still lack truly "AI-native" software got me thinking about the kinds of applications I’d like to see. As the blog post says, AI should handle the boring stuff and leave the interesting parts for me.
I listed down a few tasks I've dealt with recently and wrote some system prompts for potential agentic AIs:
-
Check that the GDPR subprocessor list is up to date. Also, ensure we have a signed data processing agreement in place with the necessary vendors. Write a summary of what you did and highlight any oddities or potentially outdated vendors.
-
Review our product’s public-facing API. Ensure the domain objects are named consistently. Here's a link to our documentation describing the domain.
-
Conduct a SOC 2 audit of our system and write a report with your findings. Send the report to Slack. Once you get approval, start implementing the necessary changes. These could include HR-related updates, changes to cloud infrastructure, or revisions to documentation and process descriptions.
-
Facilitate retrospectives for the team. Note down all actionable items and ensure the team changes its behavior. If agreed-upon actions aren’t being followed, raise the issue in Slack. You need to nag a bit while still being understanding.
-
Monitor our competitors and their products. Write a daily report of your findings and suggest action points and feature focus areas for our weekly meetings.
-
Reach out to startups that could be potential customers. Before contacting them, create a tailored solution that addresses likely challenges using our <secret feature>, and include it in a personalized message.
Personally, I’d love to have this one too. Not sure if my boss would, though. 😉
- Create a steady stream of monthly income for me. You can use my existing company. My bank account number is XYZ, and here are the company details. I've created your accounts on...
Comments
Post a Comment