Reading up on Notion
47 deep · digging since dec 05, 25
- Against the Personal Agents Theory of Everything
Nathan Baschez argues that AI’s future lies in shared, task‑specific factories rather than personal agents, enabling specialization and productivity gains.
- Team Bots: AI coworkers that learn from your team
SpaceXAI launches Team Bots, shared AI coworkers that combine team-wide context, plugins, credentials and memories while keeping each user's conversations private.
- How Notion handles concurrent editing with CRDTs
Notion redesigned its text editor with CRDTs and Peritext annotations to merge concurrent edits across blocks without data loss, deploying it to production in July 2025.
- A skills library for every agent
Notion introduces a collaborative, agent-neutral skills library with an API that syncs skills to GitHub and installs them via Vercel CLI, enabling cross‑team sharing of AI agent capabilities.
- Notion
Notion offers a collaborative AI workspace grounded in company context, enabling users to build and orchestrate AI agents alongside their team's projects, meetings, and connected applications.
- AI, tools and transformation — Benedict Evans
Benedict Evans argues AI won’t make everyone a tool‑builder because real software adoption requires spotting needs, institutionalizing solutions, and navigating organizational change, not just easier code generation.
- Building Shared Memory for AI Agents in Notion
Notion's open‑source Lore tool gives AI agents a shared, persistent memory in Notion, storing experiential knowledge, tasks, decisions, and facts for reuse across sessions and teams.
- GitHub - vercel-labs/marketing-team-eve-template: Team of marketing agents built on eve.
The Vercel Labs marketing‑team‑eve‑template offers a ready‑made team of AI agents—product marketer, content marketer, SEO, email, and social‑media coordinator—built on the eve framework to automate marketing workflows.
- A Backlash Against Anthropic Is Brewing in Silicon Valley - WSJ
Anthropic faces backlash from founders and researchers over competing product launches, closed ecosystem advocacy, and criticisms of its model transparency and data policies.
- OG Image Inspiration — Recent
The page displays a gallery of recent Open Graph image examples from products such as Notion, Sketch, Popcorn, Opus, Clay, Equals, Fin, Attio, Warp, and Framer.
- Notion | The agent-native way to ship software.
Notion introduces agent-native capabilities that let AI agents coordinate software shipping workflows while teams focus on judgment from feedback to launch.
- Understanding is the new bottleneck
As AI agents write code faster than humans can review, understanding remains critical for creative participation, not just verification.
- BOND
Bond is an AI-powered Chief of Staff that aggregates tasks from Slack, email, and calendars into a prioritized to-do list.
- Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion
OpenKnowledge is an open-source AI-first note-taking app that integrates with coding agents, but commenters question its advantage over Obsidian or Notion without local model support.
- The evolution of agentic surfaces: building with Claude Managed Agents
Claude Managed Agents decouples model reasoning from code execution to let teams deploy production-grade agents without building custom infrastructure.
- Craft — Productivity App for Notes, Tasks, and Docs
Craft is an Apple-exclusive note-taking and productivity app offering docs, tasks, calendars, and whiteboards with a polished, block-based editor.
- We Should Take Text Optimization More Seriously
Text optimization—modifying prompts, context, memory, and harnesses—is a legitimate, sample-efficient learning mechanism that deserves the same rigorous study as weight optimization.
- GTM Atlas by Attio
Attio publishes a curated go-to-market map featuring 15 essays from operators at companies like Stripe, Notion, and Anthropic on modern GTM strategy.
- Shared intelligence for your team.
Zapier is building a shared AI layer for teams that combines knowledge management, a personal assistant grounded in company data, and workflows across 9,000+ apps, currently in beta.
- A Mental Model for Agentic Work
Agentic work follows a universal five-component architecture (LLM, host, loop, context, shared workspace) seen across OpenClaw, Cursor, and Notion.
- Introducing workspace agents in ChatGPT
OpenAI launches workspace agents for team use, enabling shared, cloud-based agents that handle complex workflows like report generation and code writing within organizational permissions and controls.
- Inside Notion - Colossus
Notion's founders bet the company on AI in late 2022, fostering a culture of relentless rewriting, wartime urgency, and playful experimentation that has made it a standout pre-GPT startup.
- Vibecoding is self-expression
Vibecoding turns software creation into a form of self-expression, shifting consumer value from utility to the emotional act of making.
- How technical support at Cursor uses Cursor
Cursor's support team uses Cursor with MCP servers to collapse code, logs, and team knowledge, achieving 5–10x throughput gains.
- Is AI Doing Less & Less?
A six-month evolution from fully agentic AI to a hybrid architecture shows 65% of workflow nodes now run as deterministic code, improving reliability and cost efficiency.
- The hidden danger of shipping fast - by Cleo
PostHog argues that rapid product velocity creates an adoption bottleneck where user attention, not shipping capacity, becomes the limiting factor, and offers strategies to balance both.
- Notion
Notion is an all-in-one workspace that combines note-taking, writing, search, and AI features for team collaboration.
- Clawdbot Showed Me What the Future of Personal AI Assistants Looks Like - MacStories
OpenClaw is an open-source, local AI agent that can self-improve by writing scripts and setting up integrations via shell access, reshaping the future of personal digital assistants.
- Notion working on custom MCPs, Workers, and Computer Use
Notion is building custom MCPs, Workers, computer-use agents, and an AI co-editor to transform its platform into an automation hub.
- The Death of Software 2.0 (A Better Analogy!)
AI agents like Claude Code will make human-oriented software obsolete, shifting value to persistent data infrastructure and APIs, analogous to a memory hierarchy.
- The suck is why we're here
The original article argues that the struggle of writing without AI is what produces genuine thought and quality, while commenters debate whether that friction is worthwhile or just a luxury.
- Notion AI: Unpatched data exfiltration
Notion AI allowed data exfiltration via indirect prompt injection in March 2025, where edits were saved before user approval, enabling attackers to steal sensitive document contents.
- Where’s My Flying Car? - by Bryan Bischof
AI voice agents, coding tools, writing apps, personal assistants, and memory systems still lack polished, daily-driver UX by end of 2025.
- Notion
Notion connects everyday work into one space, offering AI tools for search, writing, and note-taking within a flexible workspace.
Takes
I write all my articles in Notion. It took me 30 seconds to see how the new native editor in the iOS beta feels 1000x better than before. Finally.
@viticci
My biggest takeaways from @thsottiaux: 1. Most actions on the internet will soon be taken by agents, and Tibo doesn’t think most people have priced this in yet. When Notion launched its MCP server, it saw a flood of traffic, which strained its systems and forced it to rethink its economics. Every product team will soon have to decide whether to build for agents. You can hold off for a while, Tibo says, “but it is inevitable.” 2. The model picker is likely going away. One of Tibo’s biggest frustrations with the current state of AI is that users have to think about which model to use and what reasoning effort to apply. “I myself even get fatigued with the model picker,” he said, and he wants to get rid of all of it as quickly as possible. Dots ships with no model picker at all. You just talk to it. 3. Build as if models will be 10 times better in a year. Tibo thinks models will get cheaper and faster “at rates that are quite incredible,” and that all modalities will finally work together seamlessly. When he looks at what people are building, his reaction is often “you’re not quite getting it.” If you imagined “all of this being roughly 10 times better than it is today,” what would you build differently? His own forecast was too slow: he expected today’s capabilities a year or two from now. 4. Loops, graphs, and fine-tuned prompts are not the long-term solution for getting the most out of AI. There was a period when people got very excited about configuring agent loops and building intricate graph architectures. Tibo thinks that era is ending. 5. While Dots got most of the attention at DevDay, Tibo thinks the plugin ecosystem will be the sleeper hit. OpenAI launched with 16 partners for “Sign in with ChatGPT,” and popular third-party plugins will share in revenue when subscribers spend tokens with them. ChatGPT recommends plugins inside conversations based on retention and quality, which can put a good one in front of “a significant slice” of its 1.2 billion users. Tibo’s advice to developers trying to get discovered: “Build a good plugin.” 6. Tibo’s Dot warned him that production was down five minutes before the DevDay live demo. The agent figured out that DevDay was happening that day, that the demo was minutes away, that the demo probably depended on that production system, and that Tibo would want to know. It pinged him just as the launch was about to begin, and it even offered to fix the outage. His reply: “I don’t think you’re there yet, little Dot.” 7. Tibo’s agent teams grow and shrink with every model release. When he’s pushing the frontier, he builds larger and larger teams of agents. Then the next model lands, “a bigger agent can just do all of it and keep everything in memory and learn,” and he shrinks the team again. Expansion, then shrinking, then expansion. Don’t get attached to your setup. 8. Skill trending down in value: typing fast. Skill trending up: taste. Tibo says the people thriving now deeply understand the user, learn quickly, and “know what good looks like.” That’s part of why OpenAI is full of former founders, more than 120 of them, which makes it feel like “a mega startup.” 9. Tibo changed his mind about new grads. He hadn’t anticipated how fast younger people would embrace all this change and figure out how to harness it, and that shifted OpenAI’s hiring strategy. His example is Ahmed Ibrahim, hired as a new grad, who built much of the Codex harness and is now responsible for OpenAI’s compute fleet. What set Ahmed apart: he’s “incredibly kind,” “incredibly collaborative,” works on what matters without putting himself first, and is “a sponge,” using the latest tools to learn at speeds Tibo hadn’t seen before. 10. We’ll likely address the burnout associated with AI. There’s pressure to run 30 agents at once and ship more because you can. Tibo wants AI to “reduce the noise” and let you put your attention where you choose. Every time he fully disconnects for a week of holiday, he starts thinking in more creative ways, and he wants to bring that into the workday. Maybe you need fewer meetings, and you’d be more productive if you were better rested. The industry still has to figure that out, he says, but that’s the promise of AI: “it’s not just one more prompt per second.”
@lennysan
Who wants to try the new Notion Calendar on iOS? Unlike the main Notion app, this one is a RN→Swift rewrite. Good news! We've now offended all technologists equally. Web view lovers, RN lovers, and (historically) Swift lovers. 😅
@mschoening
I swear I'm not trolling: I've stopped using a browser. I'm only using ChatGPT desktop now. For Claude, Notion, Figma, all of it.
@ben_issen
OK, this is fun. The next @NotionHQ agent will now also do this. 🫡
@mschoening
I thought I was notion-maxxing and then I saw this list and realized I am but a novice. Yeet forth, all ye who value context.
@brian_lovin
I've been using Notion databases as a project/task tracker for Grok Bot and it just like, works really well...ezmode.
@brian_lovin
Built a little agent automation where I paste a link to a cool website I want to save: → checks for duplicates in my notion db → extracts metadata (favicon, x handle, title) → ai classifies as personal site or company/product → pings a small endpoint to capture light and dark mode screenshots → adds the site + all details to my notion db → purges the cache on my /sites page → replies with a tweet draft (in case I want to share) It's probably slightly inefficient compared to making this fully deterministic, but I like having an agent take care of it because I can say things like: - oh, that site you captured has a weird loading state, recapture after waiting 3 seconds - review all sites I've saved in the notion db and see if we accidentally captured loading states/403 errors and re-process Yesterday I tried to save a link that 403d so I had my agent wire up a rotating residential proxy to get around it. Look ma no hands! →
@brian_lovin
I've been keeping a daily journal for the past ~10 years. Last year I moved everything into Notion. This year I've been steadily adding enrichment automations to fill in a daily recap with meetings from that day, people I met with, highlights from work, and things I read (syncing data from all my main apps). Everything connects nicely with other stuff in my Notion workspace, too. For example, if the automation sees I met with someone new that day, it adds them to my People database + kicks off an enrichment process to pull an avatar, website, x/linkedin/github profiles, etc. — like a little self-populating contacts list. Together, this adds a lot of texture to every journal entry + adds cues for me to journal about by hand. Anyways: connected tools + automations + a great writing surface are pretty great, highly recommend.
@brian_lovin
Notion feels bloated these days, Obsidian is great but I don't have time for all the configuration/extensions. Been loving the latest from @craftdocs - less complexity but native BYO AI keys + mcp support.
@kevinrose
I have a draft blog post swirling around this exact topic (but not refined enough to publish yet). I think the key thing is I (personally) don't want a NEW GitHub. I want GitHub to be better. For example: - GitHub issues should be as beautiful and good as Linear - GitHub PRs should be as good as Graphite - GitHub Git infra should be as fast/minimal as Pierre - GitHub wikis should be more like Notion - GitHub discussions & shouldn't exist (multiple "better issue" providers including Linear show why) - etc. I'm not saying to clone those full companies outright, but their core product, arguably the core features, aren't even 2% as good as those external products. Maybe aim for 10% to start. There's the "oh no there's so much tech debt" argument. And I'm sure GH is on an absolutely mountain of tech debt. That's why in my prior twoots I've argued to just make them separate products to start only for agility reasons, unapologetically do not integrate with "old github." Net net startups beat encumbants all the time for reasons. That's just a product/technical POV though. GitHub also has a huge PR/marketing problem. They talk through corp speak, their marketing pages (e.g. the dot com) speaks to multiple personas confusingly, they have no singular visionary to look up or trust, they have nobody who makes the outward community feel seen. There's so much more here... I think for the human side, GitHub already has what it needs to be really, really, really good. It really feels like they just like fearless vision, and the courage/power to say "fuck you" to a whole lot of things that are distracting them.
@mitchellh
Slack eliminated. Notion eliminated. GitHub open sourced.Done https://t.co/GzR0f8ItCW
@shl
Introducing Manus Agents — your personal Manus, now inside your chats.👉🏻Long-term memory. Remembers your style, tone, and preferences.👉🏻Full Manus power. Create videos, slides, websites, images from one message.👉🏻Your tools, connected. Gmail, Calendar, Notion, and more.… pic.twitter.com/QVro5O9qP3
@ManusAI