“Daniel Blum uses Claude Cowork, Notion, Slack, Gmail, calendar data, and Granola meeting transcripts in a self-improving PM workflow that creates and maintains his weekly priorities, daily brief, context files, and task inbox; he says it lets him complete in one day work that previously took a week.”

#3 ▶️ I built a Claude Cowork system that does a week of PM work in a day How I AI Podcast Daniel Blum uses Claude Cowork, Notion, Slack, Gmail, calendar data, and Granola meeting transcripts in a self-improving PM workflow that creates and maintains his weekly priorities, daily brief, context files, and task inbox; he says it lets him complete in one day work that previously took a week. Daniel Blum’s Sunday “weekly prep” recurring task pulls from Notion, calendar, Slack, and Granola transcripts, recommends additions or removals for “Top of Mind,” “This Week,” and “Inbox,” prepares him for upcoming meetings, and writes the confirmed plan into his Notion board. His daily Claude Cowork morning brief reviews recent Slack messages, emails, and Granola notes; it identifies company terms, files, milestones, or goals missing from its context—such as “the settlement cap”—asks Daniel Blum whether to save them, and adds approved definitions to context files. Daniel Blum says he manages about 70% to 80% of his computer-based work through Claude Cowork; Melio’s “Workstation” plugin onboards employees in about 15 minutes by connecting tools, mapping colleagues and management, reviewing calendar and Slack context, capturing goals, and creating an individual writing voice.

“The Arlington Bagel research agent checks sources twice weekly and creates Notion cards; Make.com formats newsletter blurbs, Beehive sends the issue each Thursday, and the Gmail-connected sales agent found a local bagel-shop sponsorship lead.”

#13 ▶️ Making $$$ with Grok Bot Greg Isenberg Billy Howell runs The Arlington Bagel, a Thursday local newsletter for 6,000 Arlingtonians, with a Grockbot agent team consisting of a chief of staff, research, sales, Beehive, and other specialized agents. Billy Howell keeps one business per Grockbot account to avoid context bloat and token consumption; he pays $200 for a separate Grockbot account dedicated to a Shopify experiment. His four-week Grockbot workflow is: build the initial team in week one, execute without adding agents or tinkering in week two, add or remove agents for real gaps in week three, and add automated routines in week four. The Arlington Bagel research agent checks sources twice weekly and creates Notion cards; Make.com formats newsletter blurbs, Beehive sends the issue each Thursday, and the Gmail-connected sales agent found a local bagel-shop sponsorship lead.

“Riley Brown uses Codex skills to research YouTube videos, generate Remotion graphics and Excalidraw diagrams, draft Notion content outlines, and build Paper-based YouTube thumbnail variations for his 1.5M+ follower AI-content business.”

#3 ▶️ How I Run My 1.5M+ Follower Content Business With Codex | Riley Brown Peter Yang Riley Brown uses Codex skills to research YouTube videos, generate Remotion graphics and Excalidraw diagrams, draft Notion content outlines, and build Paper-based YouTube thumbnail variations for his 1.5M+ follower AI-content business. His YouTube researcher skill uses the Supadata API to pull a full transcript from a YouTube video in about one second; Codex sub-agents can scrape an entire channel in about 30 seconds. He chains an “internet image puller” skill using SerpAPI and Google Images with a Remotion best-practices skill: the agent pulls relevant logos from a video transcript, creates branded graphics, and exports them as overlays for edited video. For thumbnails, Codex scrapes high-performing thumbnails—including Alex Hormozi and Dan Martell examples—into Paper, then Riley Brown uses Paper’s built-in AI image generation to replace the original subject with his own image and iterates on details such as face smoothing, outline glow, text, and colors.

“Rohan Varma uses the OpenAI Codex app (agent control plane) to pull context from Slack, Notion, Linear and Google Drive; automate Slack reply triggers; prototype UI variants via the built-in ImageGen skill; and convert Notion documents into live Sites.”

#3 ▶️ OpenAI PM Reveals How He Uses Codex to Do Product Work | Rohan Varma Peter Yang Rohan Varma uses the OpenAI Codex app (agent control plane) to pull context from Slack, Notion, Linear and Google Drive; automate Slack reply triggers; prototype UI variants via the built-in ImageGen skill; and convert Notion documents into live Sites. Codex integrates with Slack, Notion, Linear, email and Google Drive to synthesize thousands of daily feedback messages, enabling onboarding to a new project with full context in 20 minutes. Invoking the "imagegen" skill with a single screenshot in Codex produced four distinct UI mockups for a project-selection interface in under a minute and then generated a live prototype via the Sites feature. Codex was instructed to schedule a daily automation that parses a Slack channel for feedback, creates or updates Linear issues, and posts a summary in Slack to Rohan Varma, deleting the automation after each run.

“Cursor now lets you delegate tasks directly from Notion using the Cursor SDK.”

Notion is referenced as the place where users can delegate work to Cursor agents. The item implies a bridge from documentation/planning to execution.

“An EM built “Hot Potato,” a Notion AI agent that at 9 AM auto-scans Slack, GitHub, Honeycomb and yesterday’s transcript to prep standup notes so he can code until kickoff.”

#10 𝕏 claire vo 🖤 An EM built “Hot Potato,” a Notion AI agent that at 9 AM auto-scans Slack, GitHub, Honeycomb and yesterday’s transcript to prep standup notes so he can code until kickoff. #11 𝕏 Thinking Machines published a technical report on “Interaction Models,” detailing their modular agent framework—combining persistent memory, retrieval-augmented generation, and reactive planning—and shared early evaluation results demonstrating marked improvements in long-con...

“Notion’s design team built a minimal LLM-friendly terminal playground to prototype AI chat interfaces, moving initial design work from Figma into code.”

#8 ▶️ Why cultivating agency matters more than cultivating skills in the AI era | Max Schoening (Notion) Lennys Podcast Notion’s design team built a minimal LLM-friendly terminal playground to prototype AI chat interfaces, moving initial design work from Figma into code. The playground consists of a small codebase created by two designers and Max Schoening, optimized for one-shot interactions with LLMs and operated entirely via the terminal. Using vibe coding tools such as Cloud Code and CodeEx, designers and PMs at Notion prototype AI features in code, reducing terminal intimidation and accelerating iteration.

“#22 in Greg Isenberg urges PMs to rebuild every SaaS tool—Notion, Slack, Stripe, etc.—as agent-native (payments, communication, memory) because the coming machine-to-machine economy will feature billions of software agents as customers.”

#21 in Marc Baselga notes product leaders now see lack of Claude Code access to repos as a red flag when choosing a company. Connecting Claude Code lets PMs get instant, structured answers to deep code queries instead of lengthy engineer discussions. #22 in Greg Isenberg urges PMs to rebuild every SaaS tool—Notion, Slack, Stripe, etc.—as agent-native (payments, communication, memory) because the coming machine-to-machine economy will feature billions of software agents as customers.

“#9 ▶️ Notion’s AI-powered prototype playground: How designers are building better products faster How I AI Podcast Notion AI’s design team uses a Next.js monorepo called Prototype Playground, powered by Claude Code (Opus-4.5) and Cursor, to rapidly build production-ready prototypes with AI-assisted tooling.”

#9 ▶️ Notion’s AI-powered prototype playground: How designers are building better products faster How I AI Podcast Notion AI’s design team uses a Next.js monorepo called Prototype Playground, powered by Claude Code (Opus-4.5) and Cursor, to rapidly build production-ready prototypes with AI-assisted tooling. Prototype Playground is a Next.js app deployed on Vercel, with an app directory namespaced by designer under app/[username], standalone pages without a global layout, and shared Notion UI templates importing colors, typography, and a library of over 5,000 icons. Designers run Claude Code in plan mode within Cursor’s terminal UI, enter voice prompts via Monologue, and rely on a global cloud.md and an uncommitted cloud.local.md file to configure project tools (Bun, Tailwind), workspace paths, and MCP server settings for Figma and Chrome Dev Tools. Custom slash commands and Claude skills include /create-prototype (auto-generates page.tsx and metadata), /figma (imports a Figma frame via Figma MCP, generates code, then loops with Chrome Dev Tools MCP for up to three verification iterations), a find-icon skill (writes a TypeScript script to scan 5,000+ icon files for correct names), and /deploy (uses GitHub CLI to create a branch, commit, open a PR in the browser, and poll CI and Vercel deployment statuses every 60 seconds until all checks pass).

“Notion AI’s design team uses a Next.js monorepo called Prototype Playground, powered by Claude Code (Opus-4.5) and Cursor, to rapidly build production-ready prototypes with AI-assisted tooling.”

GenAI PM Daily February 24, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 23 insights for PM Builders, ranked by relevance from Blogs, YouTube, X, and LinkedIn. OpenAI Updates SWE-bench Verified Metrics #1 📝 OpenAI News Why SWE-bench Verified no longer measures frontier coding capabilities - OpenAI explains why the SWE-bench Verified benchmark is no longer used to measure frontier coding capabilities, outlining limitations of the metric and reasons it can misrepresent real-world model performance. The piece describes the rationale for retiring or deprioritizing the benchmark and points toward alternative evaluation approaches for assessing coding ability. Also covered by: @Sebastian Raschka #2 📝 Simon Willison Ladybird adopts Rust, with help by AI - Andreas Kling describes using coding agents (Claude Code and Codex) to port Ladybird's LibJS JavaScript engine from C++ to Rust, producing byte-for-byte identical output and completing ~25,000 lines of Rust in about two weeks.