Happy Friday! How has your week been? Share some wins in the replies!Â
Here’s some news:Â
This app uses AI to turn newsletters into podcasts

If you’re anything like me, your inbox is packed to the rafters with newsletters, some read, some unread. So much so that you regularly get inbox storage warnings. (Sorry, Gmail, I’ll do better)
You’re not alone, either. According to Campaign Monitor, a good email open rate is anywhere from 17-28%. For every email that gets sent, approximately 70% of its intended recipients don’t open it.Â
If consuming more newsletters is on your 2024 resolutions list, there are a few ways you can fix this. One way is to set up a new email account solely for newsletters to get you back on track. Another way is to change how you consume them with a tool like Jellypod.Â
Jellypod is an AI-powered tool that transforms your newsletters into a personalized, daily podcast. So, instead of making time to read through the newsletters you want to love, you can chuck on some earphones, hop on the subway, and listen to them.Â
It’s not just your usual text-to-speech model. It takes a more human approach by contextualizing each piece of an email and stitching it together in a way that’s reminiscent of how a friend might explain something to you. You can swap out the voices for six different styles, set a schedule for when you want your podcast created, adjust playback speed, and even listen offline.Â
Jellypod is currently available on iPhone, but according to the founder, an Android app is coming very soon. Give it a whirl on this newsletter.Â
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.










