Every 📧

We’re hiring a talent producer at @every. Work with @danshipper and our team to turn ideas from the edge of AI into video for YouTube, LinkedIn, and X. Apply here: modern-ton-234.notion.site/02aca4f355ac83…

Full story from Katie + a starter prompt for building your own ChatGPT project manager agent: every.to/working-overti…

How to set up your own AI project manager, via @kplikethebird: 1. Give it context Feed the agent your OKRs, strategy docs, project briefs, recurring workstream docs, and a stack-rank of what matters most. The stack-rank is key. Your agent needs to know which project you would protect if everything else slipped. 2. Connect where work happens Task manager, calendar, Slack/team chat, and Drive/docs. Your task manager becomes the source of truth. If the deadline moved in your head but not in the system, your agent will be wrong. 3. Tell it the job Organize each week. Keep quarterly objectives on track. Flag slipping work. When you ask what to work on now, recommend one next action.

More from this week’s Context Window, including Codex for knowledge work, agent-native product management, AI cost discipline: every.to/context-window…

A few updates from the Every Bundle this week: @TrySpiral added version history, so you can browse old drafts and restore one with a click. @CoraComputer added a starred view for important threads, voice dictation, typed snooze durations, and a smoother compose box. @usemonologue now hands recordings from Apple Watch to iPhone without interruption.

@MTSlive @danshipper Looking for a better way to do great writing with AI? Start a free trial for @TrySpiral, our AI writing partner with taste, trained on your style: writewithspiral.com

We talked to @danshipper about what makes great writing great. Dan, CEO of @every, says AI writing won’t feel alive until models learn continuously. "It comes from a unique person in a unique circumstance expressing their unique view on the world in words that are theirs." "The problem is not the specific, it's not X, it's Y, it's that the model, because it's not changing, it's going to use similar language in similar situations." "It's actually not at all about writing quality to me for models... is it using sentences that change and feel alive? I don't think that will happen until the models are learning continuously."

What everyone should do today, start DREAMING! Schedule the new `/ce-product-pulse` to run every day and post a report to slack and store it to a place. You will compound user feedback/signal into the place you built it in without having to do ANY work.

Get the full step-by-step guide to using agentic capabilities for better product management from Marcus 👇 every.to/guides/ai-prod…

Marcus Moretti uses this workflow to run @TrySpiral as a one-person team with Claude Code. The fastest way to get started is by installing the compound engineering plugin and running each skill. Your agent will take you through a guided interview to define your product strategy and set up your metrics reporting flow. github.com/EveryInc/compo…

Our compound engineering plugin now has two installable skills for agent-native product management: ce:strategy ce:product-pulse ce:strategy interviews you and creates docs with the target problem, approach, audience, key metrics, and what you’re explicitly not working on. ce:product-pulse sets up your reporting flow. It generates a single page with key headlines, usage data, system performance, and follow-ups to investigate next. Saved pulses become the product’s memory.

must read Marcus went from product manager to shipping product like a madman @every with coding agents he wrote the definitive guide for how to do it: every.to/guides/ai-prod…

work directly with me to make more awesome videos apply here: #open-roles" target="_blank" rel="nofollow noopener">every.to/careers#open-r…

We're hiring a Talent Producer that will work across @every to bring stories to life. Here's how I think about it: if you loved how The Browser Company brought all of us into their business and took us with them on their journey, and think you have the chops to do that too, this role is perfect for you. Apply here → #open-roles" target="_blank" rel="nofollow noopener">every.to/careers#open-r…

Full episode on the agent economy with Emily: youtube.com/watch?v=-gOyup…

LLM traffic to @stripe docs is up 10x year over year. @emilygsands, who leads data and AI at Stripe, explains how agents are reshaping the developer experience.

Agents who can buy, sell, and trade on our behalf are becoming a major part of the economy. But what exactly are they doing? Stripe sees 2% of global GDP, so they’re the company with the best view of what’s going on in the earliest innings of the agent economy. That’s why I had Emily Glassberg Sands, who leads data and AI at @stripe, on @every’s AI & I. We covered: - Most of us still don’t trust AI with larger online purchases. People are hesitant to let AI make expensive purchases like a vacation or a couch—just like the early days of online shopping. But a superhero outfit for a kid who needs one stat? Sure, let the agent handle it. - Fraud is moving up the stack. It used to mean stolen credit cards. Now attackers are stealing free-trial tokens and compute credits. Free-trial abuse has 4x-ed in the last six months.. - AI is on both sides of fraud. Fraudsters are using it to scale attacks, while Stripe is using it to detect them. They’re blocking 250,000 fraudulent free trials a week for one large customer. - AI companies are growing faster than any cohort Stripe has ever tracked. Top companies hit $30M ARR in 18 months—3x faster than the 2018 SaaS class. So far, it’s net new spend instead of cannibalized software budgets. If you want to understand how AI is reshaping online commerce, this one deserves your time. Timestamps Introduction: 00:00:45 New rules for an agent-driven economy: 00:01:27 Compute theft is the new payment fraud: 00:03:57 How Stripe expanded fraud detection from checkout to the full customer lifecycle: 00:10:00 Why AI companies are scaling way faster than top SaaS companies: 00:19:48 Outcome-based billing is replacing seat-based pricing: 00:23:27 Where AI spending is coming from: 00:29:57 How the developer experience changes when agents are the builders: 00:36:45 The agentic commerce spectrum, from assisted buying to autonomous purchasing: 00:41:00 Meet Link, a consumer wallet for delegated agent purchases: 00:51:06

Monologue by @naveennaidu_m from @every is one of my favorite products. It's simple at its core and does exactly what it sets out to do. 10/10 👏

im writing an essay in proof using codex's in-app browser. i type directly in the document, and codex loops in parallel on the left, collaborating with me in realtime. this is obviously the future:

Two new commands in the Spiral CLI: personalize and humanize. spiral personalize "your_text" – rewrites the given text in your voice spiral humanize "your_text" – removes common AI tells according to your Account > Writing Rules