Tana meeting + Claude Code or ChatGPT desktop + good colleagues = a fantastic pair-design session.
Either working directly in local worktree or with local MCP to @paper for example. Feels truly magical. Of course any other MCP you’ve already set up works too.
Share screen, talk, explore variations, point and discuss, iterate.
Everyone with their own local powerful agents working collaboratively on shared context and vision.
UPDATE: @claudeai and @OpenAI Codex can now work MULTIPLAYER, with vision 🤯
I vibe code my website through @tana_inc and just ... chat. No screenshots, no "see image 2". The agents are in the meeting, with full context, know exactly what I'm showing and talking about.
Works with Meet, Zoom or Teams meetings too, with the Tana companion.
(Claude and ChatGPT today. More agents coming.)
Theo retweeted
Tana is becoming a really interesting "hub" for all the insights, decisions and designs in an organization. Having a meeting with a designer, pulling up documents that organize user input, sharing screen and knowing that we not only get transcript but screenshots...
Which makes it an incredibly rewarding problem to work on @tana_inc!
Knowledge work is SO much harder to automate with agents than code
We underestimate how easy software development is for agents
- Tons of high quality automated feedback loops (types, tests)
- Well-organized free documentation, searchable on the web
- Simple-to-use workspaces with version control (i.e. repositories)
- Long history of systematising and delegating work (i.e. sprints, tickets, specs)
Knowledge work has none of these advantages
Started bringing a little utility application I've dreamed of for years into existence today. It's insane how much progress you can make in only a few hours, with some clarity and excitement.
Going to share a little a long the way on this one!
its current nickname is Branch.
We do this every day *collaboratively* at Tana. Conversation is the future of collaboration between humans and agents.
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Theo retweeted
Replying to @benhwx @zarazhangrui
Agreed, need to be able to document context on the fly without extra effort in a collaborative space with dynamic permission settings 😉
Theo retweeted
Replying to @carsonarkova @rich_odinn
But what if your meetings, notes, CRM, and ai were all in the same place? 😉
Theo retweeted
We are in the running for Product of the Year on Product Hunt!
If you haven't supported us yet, now is the time...
producthunt.com/products/tan…
This was a lot of fun!
Tana Annual Review Session xitter.cf/i/broadcasts/1jMKgRvbr…
Tana advent calendar now banned in 15 countries for too much festive spirit :D

















