Now that I use @resend inboxes - it's great, my agents love it. I needed a place to capture and monitor all the other adresses for and so I build ZeroInbox - a native client that uses Resend's API and iCloud to act as a inbox for the other emails you should be monitoring, with iCloudKit Sync between iOS and Mac, TLDR an email client for all the the other adresses such as hello, legal etc.

🆕 Designing for Agents Agent Experience is one of the most hotly contested topics of 2026, and increasingly critical for devtools/infra companies to get right. @ZenoRocha has been writing and thinking about this since 2024 and came on the pod to spill @Resend secrets! Key themes include: - Answer Engine Optimization (AEO): how AI models like Claude Code recommend email services and how product teams can design for these agents - Deliverability and Trust: The discussion delves into the complexities of getting mail into the inbox, including handling bursts, managing Gmail throttling, and the importance of domain reputation and anti-abuse measures - Developer Experience & MCP: A major focus is on building for both humans and machines. Resend utilizes the Model Context Protocol (MCP) to provide agents with over 80 named tools, allowing them to autonomously set up accounts, check pricing in Markdown, and send emails - Technical Infrastructure: React Email as a wedge for adoption and but Resend's commitment to owning the mail stack, including managing complex DNS hurdles and providing enterprise-level visibility

Companies start their global journeys from day 1. With the power of AI and easy-to-use developer primitives, localization shouldn’t be an afterthought anymore. @generaltxn makes it seamless. @archiemckenzie_ is a force of nature, so excited to be partnering with you & the team!!

We’re spending up to 100B tokens across 26,040 agent runs to answer one question: when you switch models, should you switch harnesses too? Our v1.0 FrontierHarness leaderboard ranked harnesses on a single model. V1.1 expands it to 21 harnesses × 5 models × 62 tasks × 4 attempts, 72x the size of v1.0. Results are coming in live. Link below🧵

Best bit of the whole convo imo. If you're a CEO hiring a CFO, you want someone who cares about the business as much as you do and wants to win just as badly. Bonus points if they can make it simple enough that everyone's running in the same direction. AI is making it easier for the CFO's team to be more strategic; today's CFO needs to have an automation-first mindset to get there. Praveer is such a sharp operator, so fun getting to pick his brain!

So honored to have @realchillben joining the team!! I first met Bill when he was a YC founder, and it hits differently when a founder you've known ends up on your team 🫶 We are so excited to have you on the team Bill!!

OpenRouter is the largest open market for tokens, and has been essential in bringing healthy competition to the LLM inference space. Inference is complicated and can be optimized on multiple axes (cost, throughput, accuracy), so as an exchange they have the difficult task of deciding how to route between providers. This update now allows providers to distinguish themselves across any/all of these axes, and has pushed providers like us to improve our serving engines in ways that actually help the end user. It's been fun trying to red team the algorithm as OR shipped some of the initial changes, and we've really appreciated how transparent the team has been throughout the transtion. If you haven't read up on the new system, you should check out the docs! It's really quite beautiful.

Normal onboarding: you sign up, then build. Upstash onboarding: your agent builds, then you sign up. Agent gets a free Redis DB, no account. You claim it within 3 days. curl -X POST

I built a notes app inspired by the 80s, when software felt simple and snappy. It launches in 2.6ms. I've taken notes for 10+ years, first in VS Code, then Obsidian. Sometimes I just want to jot down a thought and get back to work. Here's Noted: 🧵

@QuiverAI is criminally underrated 🤯 Made this anatomy plate with it: 100% SVG, every label and line editable. For @Doctopiaai no more licence fees per diagram. We make our own. Medical education just changed 🫀 @joanrod_ai please be friends before you get too big 😂

"just an AWS wrapper" that's how people kept calling Resend. not anymore. announcing Resend Forge: ∙ 129x faster at p99 ∙ 99%+ delivery rate across inboxes it's the fastest email engine in the industry. with best-in-class deliverability. and you can activate it today.

I feel like we're looking at something so much BIGGER than just better and more detailed SVGs. SVGs are essentially images made entirely from code. Instead of storing millions of pixels like a PNG or JPEG, it uses math instructions to describe shapes, paths, colors, gradients, etc.... and Quiver is now generating these incredibly detailed illustrations that look almost like polished 3D renders, except they're actually editable vector graphics. But what happens when these models eventually get so good that they can generate SVGs that are indistinguishable from photorealistic images? At that point, why would we need image models at all? and if you can create any image entirely through code, you could theoretically generate every frame in a video in the same way and suddenly, instead of generating a fixed sequence as an mp4, you would be able to generate fully editable programmatic scenes. I don't know what this means for the future, or if it will even work in this way, but holy molly, it's gonna be interesting