Ogment AI - Your AI coworker, in Slack. Just tag @O.
by•
@O is the ultimate AI coworker that lives natively in Slack.
Tag @O like a colleague, to ask anything or delegate daily tasks in plain English. It connects to 1,000+ tools your business runs on, does work while you sleep, and shares memory and skills across your whole team right in Slack, on any model you choose, including your own.
One-click install, and everyone is AI-enabled in under 5min, not just your power users. Zero friction, maximum adoption.
Replies
Such a cool idea and an awesome project! Wishing you the best of luck with the launch and continued success! 🚀
@O - AI coworker in Slack
@egorzolotukhin thanks Egor - much appreciated!
Love how it just slots into Slack without a separate dashboard or login. The fact that tagging it feels exactly like pinging a teammate is a small detail but it’s probably the real reason people will actually use it.
@O - AI coworker in Slack
@kezbankuldasmu - glad you like it! Thanks for your support Kezban!
Very cool! I use it to automate workflows that eat up my time, like adding call summaries, and tagging relevant people for action, or getting summaries of my day.
Cool stuff @ - AI coworker in Slack
@O - AI coworker in Slack
@therealmalo thanks Malo - excited to have you on board!
Model-agnostic is a strong claim since reasoning quality varies a lot across models. Can @O route different task types to different models, cheap one for routine CRM updates, stronger one for judgment calls, or is it one model per workspace?
@O - AI coworker in Slack
@christian_knaut you're right that reasoning quality varies enough that this matters. Honest answer: today it's set at the workspace level, not per-task. Task-type routing, cheap model for routine CRM updates, stronger one for judgment calls, is on our near-term roadmap and exactly the direction we want to go. The model-agnostic foundation is there; the smart routing layer on top is what's coming. Appreciate you pushing on it
Tool-calling is the sneaky failure with any bring-your-own-model setup. Providers each format function calls differently, so a harness tuned on one model's schema quietly drops args or mis-picks tools when you point it at a cheaper endpoint, and it still reads as working. That's the bug that ate the most of our debugging time building agent infra. How much of the agent quality actually holds when someone swaps their own model in versus your default?
@O - AI coworker in Slack
@dipankar_sarkar so true - tool-calling is where the trouble shows up first every time we test a new model: dropped args, wrong tool picked, and it still reads as working. Ate a lot of our debugging time too.
That's why we don't expose every model behind a switch. We test each one for tool-calling reliability and roll them out progressively, with some flagged as more recommended than others. Quality does vary by model - we're not going to pretend a cheaper endpoint always holds up like our default - but the recommended set has been through the wringer, so the swap is a known quantity, not a silent regression.
Slashspace AI
Does it use a specific model, or do we get configure it?
@O - AI coworker in Slack
@praneethpike It uses Opus 4.6 by default, but you can configure!
tagging it like a teammate instead of hiding it behind a slash command is a really clever UX move, it makes the bot feel like part of the conversation rather than a separate tool to context switch into.
@O - AI coworker in Slack
@pakizeycoa - yes, feels like a small difference but actually has really good shared "context-effect" while collaborating in threads!
Finally tried @O in our Slack and tagging it feels just like asking a coworker. Loved that it remembered context from earlier threads without me re-explaining.
@O - AI coworker in Slack
@nurcanboyu - thanks for your support Nurcan. Happy you liked the experience 🫶
Onepane
we basically live in slack so this makes sense to me. congrats on launching, will try it with the team
@O - AI coworker in Slack
@ashmil_hussain - we do too! ahah thanks for trying O out - hope it will be a good addition to your team!
Unslack
Really appreciate tools that meet you where you're at in your current workspaces instead of making learn a brand new platform. We recently went through a collaborative multi-team project in Slack and wish we had @O - it would have saved us a ton of time. Looking forward to trying it for our next project!
"Zero friction, maximum adoption" - cheers to this! 👏
@O - AI coworker in Slack
@ashamplifies Thanks so much 🙂 Multi-team projects in Slack are exactly where @O tends to earn its keep, lots of context flying around, lots of people who shouldn't have to re-explain things. Would love to hear how it goes on your next one. Cheers, and thanks for the kind words on launch day