Aman Khan
Product leader; director of product at Arize AI in 2024, earlier an AI product manager on Spotify's ML platform, with product roles at Cruise, Zipline and Apple.
Aman Khan did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter All topics · Newest first
-
Their wordsOnce a benchmark becomes a target, it can pull optimization toward the test itself. That’s the concern behind Goodhart’s Law, and it’s a reason to check more than the headline score. None of that tells you whether the new model is better at reviewing your product spec or catching the bug in your pull request.
↗Build your own vibe check in an afternoonamankhan1.substack.com 1st of 3 in this piece
-
Their wordsI can judge a spec review because I know the product and the decisions I’m trying to make. The same goes for turning my rough notes into a pitch or catching a bug in a pull request. I have enough context to push back on the answer. That’s where I start when I’m trying a new model.
↗Build your own vibe check in an afternoonamankhan1.substack.com 2nd of 3 in this piece
-
Their wordsThe model is one choice. Your harness is another: are you using Claude Code, Codex, Cursor, or a chat window? Then there are the skills you’ve given it (a spec-review checklist, say) and the context it has to work from. A missing doc can matter more than which model you picked.
↗Build your own vibe check in an afternoonamankhan1.substack.com 3rd of 3 in this piece
- 6 months earlier
-
Their wordsAs a product builder or specialist in some way, one of the highest leverage things you could do right now is find ways to encode your knowledge into an agent for it to be used to take action. Skills are the perfect method of doing this.
↗Every PM Should Be Building Skillsamankhan1.substack.com 1st of 2 in this piece
-
Their wordsA well-written skill encodes how you think about a problem, what conventions you follow, what mistakes you’ve learned to avoid. My writing voice skill is 200+ lines of patterns, anti-patterns, and calibration sentences that encode years of figuring out what works. When I share that skill, I’m sharing my judgment, not just a prompt.
↗Every PM Should Be Building Skillsamankhan1.substack.com 2nd of 2 in this piece
- 2 weeks earlier
-
Our reading
Getting a personal AI agent running is 20% of the work; making it useful and safe is the other 80%.
Their wordsHere’s what I found: getting it running is maybe 20% of the work. The other 80% is making it actually useful, and making sure it doesn’t accidentally publish your API keys to the internet or respond to strangers in your group chats.
↗How to Make Your OpenClaw Agent Useful and Secureamankhan1.substack.com