PromptQL
Multiplayer AI that replaces Slack
Start new thread

PromptQL - Multiplayer AI that replaces Slack

by•
Stop splitting team knowledge between Slack and everyone's private AI chats. PromptQL is multiplayer AI for teams: think Claude or ChatGPT in shared threads. Tag teammates to review, correct, and refine answers without losing the reasoning. Connect databases, SaaS apps, coding agents, and events. PromptQL captures tribal knowledge and suggests shared-brain updates so context compounds. Scopes and multi-user permissions keep the right context accessible to the right people.

Add a comment

Replies

Best

Building shared context instead of forcing everyone to constantly repeat the same information feels like the real unlock for AI at work Most AI tools make individuals faster but PromptQL makes the whole team smarter That is a much bigger shift Looking forward to seeing where this goes

Congrats on the launch

Maker

   thanks! exactly right -- not having an AI that has amnesia everytime you talk to it is kind of nice :)

   love the idea!

cool video, shared context, skills and existing workflows to hyper automate development. dosent this reduce hiring needs

Maker
it definitely helps one person do the work of more people!

 isnt that waht codex is abt. is this more buisness ops?

Maker

 Codex is solo coding - this is the team layer where anyone can teach it and spin up live agents together, ops included.

Maker
correct. This is more for non-coding use cases. Data and Ops are great examples. Also, codex isn’t multiplayer. Meaning there are no shared threads in codex User 1: look logs and tell me what happened AI: Done, should I raise a PR to fix User 1: Yes AI: Done User 1: cool, @/user2 can you review and deploy. User 2: yeah looks good, let’s deploy. Soemthing like that. Typically it’s never that smooth in real life SRE incident. User 2 has many questions and goes back and forth with AI. You typically bring in more experts also. So on and so forth.

What's a use case you think most people don't know PromptQL can support but is really helpful?

Maker

 collaboratively going from question/answer to agent is my favourite.

Zach: "How many active users did we get from the PH launch"
AI: "hmm..not sure about active user definitiion. maybe @/tanmai knows"

Tanmai: "yeah, for social campaigns we usually do a has credit card on file and atleast one interaction in the first 6 hours"

AI: "ok, here's what that looks like"
Zach: "awesome, can you make that live refresh every hour and in case someone crosses more than 5 threads in the first 6 hours, help me draft a personal email to set up a call with them. ping me whenever this happens"
AI: "Done"


Collaboratively building an agent on the fly is just too much fun :)

if the AI 🤖 knew the answer, would it need to ask you? Is it now stored? So, if I ask the AI after Zach did, the AI will already know what you said, right??
Maker

  Yep - teach it once, hit add to wiki, and the next person already has it.

The "shared-brain updates so context compounds" framing is different from other team AI tools. One thing I'd be curious about—when corrections and learning flow back into the context, how do you prevent authoritative corrections from overweighting domain expertise that was already in the system? Like, if someone corrects a nuance mid-thread, does it need peer review before it locks in, or is the cost of outdated shared context higher than the cost of wrong-but-quick updates?

Maker

 changes are never automatically written back. changes are only suggested. a human always has to approve (or edit or reject) the changes. these changes are a precise set of bullets not a giant wall of text.

but most importantly the control mechanism is like wikipedia. so people who care about certain domains "follow" those topics. And that way any changes they get notified on. and if it changes then they can swiftly revert.

the last boss is that you can lock a page entirely, but that's usually not necessary. the more open the context is the more self-correcting it becomes.

And given the fact that every change has a human name attached to it, people don't want their names to be associated with sloppy or wrong info. The team and social dynamics keep things naturally clean :)

I use Slack every day for work, so this is a huge help.

Maker

 awesome! Try it out and let us know if you need any help getting set up.

Maker

 Try our Slackbot to start with: -- can slowly move over.

Congratulations ! This is amazing! Good luck with the launch :D

Maker

   Thanks Nikhil! Appreciate the support :)

It's impressive how quickly PromptQL became "the" place where work actually happens. Engineering, planning, tracking, collaboration, creating pull requests, deployments, monitoring, alerting — everything stays in one workflow instead of constantly switching between tools. It's been fun using what feels like the "final boss" of engineering tools over the past few months.

Maker

 yeah, so much of engg work ends up being the before (what should we build, why) and after (is it done, what should we do immediately after). the shared thread way of working really surfaces that in a whole new way.

Maker

   I have fomo from all the stuff that's not yet set up to optimize the sh** out of it :D

the scopes/permissions part is the sharp edge - if someone corrects an answer in a restricted-scope thread, does that correction ever bleed into the shared-brain for people outside that scope, or does it stay siloed to who saw the original thread?

Maker
it goes into the “shared brain”! That’s critical, otherwise multiplayer is useless. The clever thing is that it’s done with “scopes”. So you can decide if those learnings are for everyone, or maybe only for the finance team or maybe only personal to you.
oh, this is interesting 🤔 But do you have to manually set those settings for everything you write?

Been a user of PromptQL and it's an amazing re-invention of collaboration!

Maker

 Thanks for being an early supporter. I hope you've been able to unlock more usecases with PromptQL

how big does a company have to be to start feeling the value of ??
cc:

Maker
I would say a team of atleast 2! One other person is where you see the true value!
First
Previous
1234
Next
Last