
Grok Bot is no magic bullet. It's just refined and convenient. If you could run your own Agent Harness and stay in control of your data and setup, would you put in the work that is needed to make it work?

AI doesn't fix broken systems. It amplifies them. I help professionals build the system first.

Grok Bot is no magic bullet. It's just refined and convenient. If you could run your own Agent Harness and stay in control of your data and setup, would you put in the work that is needed to make it work?

In your opinion, what's the best Personal Knowledge Management tool, that's ready for 2027?

Google has been cooking...
Put Gemini to work for you with Tasks. While Chat is for quick back-and-forth answers, Tasks are for longer projects and recurring schedules. Beginning today, Tasks are now free of charge for hundreds of millions of eligible users, starting in the U.S., JP, KR, CA, AU & IN. 🧵

Claude doesn't have better tables, whiteboards, or docs than Google or Microsoft. In fact, Claude might be running up against the same wall as ClickUp: building an all-in-one solution that tries to replace them all. While in the end, serving nobody well.
ClickUp rose fast because of one talent: building any feature and cramming it all into one tool. That's how they outpaced the competition, with the slogan: One tool to replace them all. Spoiler alert: AI has since replaced their one unique advantage. Everyone ships fast now. And it turns out, that's not what people need anyway. One tool to rule them all means you either live with half-baked features inside ClickUp, or you use dedicated tools that mastered the job and still carry a bloated ClickUp setup on top. I remember the day they launched Whiteboards. I thought: this could replace Miro. It stayed an alpha version for years. No deep integration into ClickUp. They jumped to the next thing before finishing the first. Relational databases, the thing I appreciated in Notion, could have killed Notion. Nah. Relationships never worked in a way that made sense. Too complicated for the normal user, too minimal for the power user. Proper databases were promised again and again. They never came. Then they went after Slack. We moved our team from Slack into ClickUp Chat during the beta and stuck with it until today. Now we're back in Slack. Yes, team communication right inside the project management tool sounded great. Turning conversations into tasks was a good feature. But Slack could already do that through the ClickUp integration. Even better, it works with any project management tool. And bigger companies naturally run several, not one to replace them all. ClickUp Dashboards: another great idea, turning all the data in the one tool for everything into something visual. We never used them. Too glitchy, for years. Over time, the way features got built and connected made me think that, behind the scenes, they never understood how to set up project management in a tool-agnostic way in the first place. Their templates showed it too. Overloaded to look fancy on the outside, impractical once put into action. The template we provided over the years actually removed a lot of ClickUp features to make it usable and less confusing. After 7 years of using ClickUp nonstop, my conclusion: Use a set of tools, each made for one well-defined job or area of expertise in your productivity system. And in addition, since 2026, build even more specific solutions with AI to fill the gaps and remove friction from your workflows. After all those years, that's what brought us back to Asana, to see how far they've come. I have a lot of experience whitelisting Asana and rolling it out in corporate, as I mentioned here: x.com/TomSolidPM/status/2122… To me, Asana always took the Apple approach: ship new features only when they're thought through and refined. If you want big players to run real business on your tool, this is the way to go. Not turning people who need to get shit done into beta testers who never know whether everything still works and looks the same next week. Anyway, I'll keep you all updated on how the migration went and whether it was worth it. Not being sponsored by any of those companies gives me the freedom to speak up, unfiltered. Did you switch too? If so, what tool is your new home for business?

ClickUp rose fast because of one talent: building any feature and cramming it all into one tool. That's how they outpaced the competition, with the slogan: One tool to replace them all. Spoiler alert: AI has since replaced their one unique advantage. Everyone ships fast now. And it turns out, that's not what people need anyway. One tool to rule them all means you either live with half-baked features inside ClickUp, or you use dedicated tools that mastered the job and still carry a bloated ClickUp setup on top. I remember the day they launched Whiteboards. I thought: this could replace Miro. It stayed an alpha version for years. No deep integration into ClickUp. They jumped to the next thing before finishing the first. Relational databases, the thing I appreciated in Notion, could have killed Notion. Nah. Relationships never worked in a way that made sense. Too complicated for the normal user, too minimal for the power user. Proper databases were promised again and again. They never came. Then they went after Slack. We moved our team from Slack into ClickUp Chat during the beta and stuck with it until today. Now we're back in Slack. Yes, team communication right inside the project management tool sounded great. Turning conversations into tasks was a good feature. But Slack could already do that through the ClickUp integration. Even better, it works with any project management tool. And bigger companies naturally run several, not one to replace them all. ClickUp Dashboards: another great idea, turning all the data in the one tool for everything into something visual. We never used them. Too glitchy, for years. Over time, the way features got built and connected made me think that, behind the scenes, they never understood how to set up project management in a tool-agnostic way in the first place. Their templates showed it too. Overloaded to look fancy on the outside, impractical once put into action. The template we provided over the years actually removed a lot of ClickUp features to make it usable and less confusing. After 7 years of using ClickUp nonstop, my conclusion: Use a set of tools, each made for one well-defined job or area of expertise in your productivity system. And in addition, since 2026, build even more specific solutions with AI to fill the gaps and remove friction from your workflows. After all those years, that's what brought us back to Asana, to see how far they've come. I have a lot of experience whitelisting Asana and rolling it out in corporate, as I mentioned here: x.com/TomSolidPM/status/2122… To me, Asana always took the Apple approach: ship new features only when they're thought through and refined. If you want big players to run real business on your tool, this is the way to go. Not turning people who need to get shit done into beta testers who never know whether everything still works and looks the same next week. Anyway, I'll keep you all updated on how the migration went and whether it was worth it. Not being sponsored by any of those companies gives me the freedom to speak up, unfiltered. Did you switch too? If so, what tool is your new home for business?
click ups downfall needs to be studied.

Update on the issue with uploading files in fields: We raised the upload endpoint's timeout from 3 seconds to 15 minutes in a fix that's already live. Since then we've verified 1–20 MB uploads in production (including on slow connections).

Webhooks are so powerful. Not only in Grok Bot.
Grok Bot tip that saves usage 👇 Switch your routines from schedules to webhooks so your Bot only wakes up when something actually happens > Ask your Bot to add a webhook trigger to the routine > Open the routine on desktop and copy the URL and key from the Webhook section > Have your other app POST to that URL with the key in the header > Send a JSON body and the Bot gets it along with the routine’s instruction

Sam, you won't get my RAM for that.
Theo - t3.gg @theo 20h Why I hate GPT-6.2 Astra During early testing, I found myself so frustrated with this model that I spent a day writing a letter to OpenAI about it. They fixed a small handful of my complaints, but not enough for me to

So we’re all faking work now, thinking that the elder won’t find out? Like, “Oh sh… forgot to do my homework. Quick, let me copy yours!”
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…

Releases like this are why Claude keeps winning the game. Not just because it has good models, but because the orchestration behind the scenes is so damn well refined. It’s hard to catch up without reverse-engineering how Anthropic did it.
Check out Code Mode, a new, experimental way for Claude Code to work with tools. Claude writes scripts that chain your tools together in sophisticated ways, and it can answer you while long commands are still running. Opt in with CLAUDE_CODE_EXPERIMENTAL_CODE_MODE=1 code.claude.com/docs/en/code…

If you let AI rephrase your content, AI watermarks will be applied. That’s why I write everything myself and only check the spelling and grammar, without changing any words or phrasing.
X actively checks accounts and content for LLM slop and marks them internally as “llm_slop_user”. So if you use AI for comments and content, I have very bad news for you. You can very quickly get the “SpamHighRecall” label, and your posts will end up in a shadowban. Therefore, create content yourself - especially when it comes to comments.


We have external agents in staging and shipping that this week or next week. Fully agree on that.

This! Our co-founder @PacomyICOR keeps saying the same!
@linear They know their craft They have a vision for the future Trust me I have used click up, or tried at least You can fuck with linear primitives Even if you try

Still true by a mile! Openwho?
opus 5.5 is still the best model right now

The one staying strong in line, though, is Todoist. It's probably at the other end of the spectrum from ClickUp.
All the todo apps have scope creep. The irony