Say hi to Poke! Now part of @Cognition 🦦🌴
Palo Alto, California
Joined December 2012
- Tweets2.4K
- Following28
- Followers26.1K
- Likes18.9K
Pinned Tweet
After almost two years in Palo Alto, @Interaction is moving to SF.
Some opportunities are bigger than sunshine! 🌴
Cognition is acquiring @Interaction, the makers of Poke.
If you've ever used Poke, you know why we're so excited.
Poke retweeted
still find it genuinely crazy how @interaction were the ones to kick off this whole wave
Poke retweeted
it's still crazy to me how the email monitoring from poke by @interaction is still superior to any other agent i've ever used
Poke retweeted
I think @interaction has the best system still with Poke Human
Poke retweeted
I tried to bribe Poke to engage in our launch post.. he said nah but tweet at @interaction and maybe they will
Poke retweeted
meanwhile @interaction
Poke retweeted
@interaction saw this way earlier than everyone else fr
Poke deserves more credit for seeing this early.
Before every major AI lab started shipping personal agents, Poke was already exploring what it meant to have an AI you could simply text.
Now look at how far the idea has evolved:
• Poke: personal agent through messaging
• Instinct: personal agent with deeper capabilities
• Grok Bot: multiple personal agents that can coordinate
• Muse: Meta’s version of a personal agent
• Dots: OpenAI’s version of a personal agent
• Coral: a shared agent for the entire family
We’re moving towards agents that don’t just answer us, but know our context, access our tools, coordinate with others and actually get things done.
The personal agent era is here.
Poke retweeted
It's insane how early Poke was to personal agents playing with the idea of texting an agent.
Look at how far we've come:
- Flip: personal finance AI with text
- Fo: agent which can call, schedule and work
- Kat: fastest email reading and sending agent via imessage
- Instinct: one of the first iMessage agents to do real work
- Ecomerate: the first constant stock and supply chain research and monitoring agent all through text
The era of messaging is finally here.
Poke retweeted
Poke deserves more credit for seeing this early.
Before every major AI lab started shipping personal agents, Poke was already exploring what it meant to have an AI you could simply text.
Now look at how far the idea has evolved:
• Poke: personal agent through messaging
• Instinct: personal agent with deeper capabilities
• Grok Bot: multiple personal agents that can coordinate
• Muse: Meta’s version of a personal agent
• Dots: OpenAI’s version of a personal agent
• Coral: a shared agent for the entire family
We’re moving towards agents that don’t just answer us, but know our context, access our tools, coordinate with others and actually get things done.
The personal agent era is here.
Poke retweeted
We created a list of the most notable AI agents that can live in your text messages, from general assistants to agents designed for families, travel, and work.
spr.ly/6013BGClIf
Poke retweeted
It’s interesting that no one has built an all-in-one tool for personal agents (like @Muse, @instinct, @bot, @interaction) that hold all connections to third party companies. Convinced that this should be an independent product.
That way you can keep auth separate, audit what the agent does, set fine-grained permissions and easily switch between the agent apps.
I built it over the last few days with @hkonsti_. It’s open source and easy to self-host.
Now my Instinct has exactly the same tools as Claude Code on my laptop.
Poke retweeted
Not enough hype on @marvinvonhagen, @felixms and the entire @interaction team
It’s now obvious they were very early (and right!) to a massive new form factor and way of interaction
Thank you for your work in enabling consumer agents 🙏
Poke retweeted
One reason why I use iMessage agents like @interaction Instinct for daily stuff is the launch time. The ChatGPT app takes like forever to boot and by that time I have already sent that message in iMessage. And also the responses are shorter and quicker.
Poke retweeted
bought the @clickskeyboard power keyboard for $10 out of a bin and somehow still feel financially violated
BlackBerry muscle memory in 2026 is pure psychological warfare
@interaction was right, some hardware belongs in the museum
Poke retweeted
my agent stack
@DevinAI: makes me stuff
@interaction: day-to-day
@hark_labs: tasks that require a computer, brainstorming
My agent stack:
- @instinct - on-the-go purchases, form fill, local recs
- @Muse - mini-apps that require reliable connectors (ex. "track my sleep and movement, send me a survey daily")
- @tomo - motivation + goal tracking, also want to try their Interest Groups
- @bot - X feed monitoring + alerts
- Dots (@OpenAI) - deep, long-running projects...I'm currently making it start a business 👀
- @townai - everything work-related in email, Slack, docs
- @Tabdotbot - outbound phone calls / appts
Poke retweeted
asked poke for the top 20 bay area hikes. it built and published a site with webly
bay-area-hiking-field-guide.…
how’d it do? what’s missing?
Poke retweeted
personal update: I've joined @Hone, and we're launching today!
my belief: if you want to solve a problem, solve the hardest version first.
> GPS was first built for the military. Now it guides every ride and delivery.
> Computers were built for governments. Now there's one in every household.
> Gmail was first built for consumers. Now millions of businesses run on it.
building AI at @interaction taught me how much agents can do for one person. I wanted to see what they could do for a whole company.
that's a whole new set of problems. people who want different things. goals that take months. info that's outdated or stuck in someone's head.
booking the wrong flight is annoying, sharing the wrong file with the wrong person can end a company
i joined to work on that, with people I'd bet on!
come build with us!
Today Hone launches Engines: AI that owns business outcomes.
Chatbots give answers. Agents do tasks. Engines deliver outcomes, and we hold them responsible for creating real value, measured in actual dollars instead of tokens or vibes.
You point it at a business metric, and the Engine figures out the rest. It onboards itself, builds the necessary agents, skills, and memories, collaborates with the right people, and gets better with experience.
From AI leaders to global enterprises, our customers have already used Engines to:
• Uncover millions in procurement savings
• Optimize product funnels
• Manage credit risk
• Increase qualified pipeline in new territories
• Accelerate implementations and improve account management
To scale this impact across the economy, we’ve raised a $60M seed led by Benchmark and Index with participation from Elad Gil, Hanabi, Definition, Diffusion, Lux, SV Angel, and Align.
AI’s raw capabilities are far ahead of the value it creates in the real world, and Engines will help close the gap.
Here’s how they work…