Introducing: Ask Product Hunt ๐
Today, weโre introducing Ask Product Hunt, a new community-powered product search engine.
As with many things we build, the idea was inspired by you. ๐ค Every day, people ask for product recommendations, often cc'ing @ProductHunt on Twitter. Now you can ask the community directly.
For the past 4 weeks, we've been sharing recommendations with a small group of beta testers in response to questions like:
๐ฑ What's one app you use a lot, that most people don't know about?
โ๏ธ What's the best app for writing on MacOS?
โ๏ธ What's the easiest way to create GIFs for the web?
Check it out! We'll be featuring some of the most popular questions and recommendations throughout the month.
As with many things we build, the idea was inspired by you. ๐ค Every day, people ask for product recommendations, often cc'ing @ProductHunt on Twitter. Now you can ask the community directly.
For the past 4 weeks, we've been sharing recommendations with a small group of beta testers in response to questions like:
๐ฑ What's one app you use a lot, that most people don't know about?
โ๏ธ What's the best app for writing on MacOS?
โ๏ธ What's the easiest way to create GIFs for the web?
Check it out! We'll be featuring some of the most popular questions and recommendations throughout the month.
Highlight
On Friday we launched The Parking Bookย (as an April Fools joke). There were enough pre-orders to make it a #1 Best Seller, so now we're actually going to write it. Get The Parking Bookย on Amazon.
Ad
Your agents stopped answering and started doing
Your agents call tools, write to databases and move money, so a wrong answer is now a wrong action, which is a considerably worse meeting. Arcjet runs policy before every LLM call, tool call, query and API request: prompt injection, sensitive data, bots, rate limits, spend quotas, and your own rules in Rego on top. It reads the OpenTelemetry you already emit, so switching it on is one environment variable, no code changes and nothing to deploy. Each check also reads the earlier steps in the same workflow, so an agent's tenth action gets judged against the first nine and not on its own. JavaScript, Python and Go SDKs all at 1.0, agent framework guards included, free tier to start on.



