Hey everyone, another question from the Velozity team as we get closer to launch.
Last time we asked how AI work moves between people on a team. This time we want to dig into trust.
Right now most people keep their AI on a short leash: it drafts, it suggests, but a person clicks send. That's safe, but it also means every handoff between a person and their AI, or between two people's AIs, still needs a human in the loop to move things along.
We're building Velozity so agents can work more directly inside a team's shared space, chat, tasks, files, calendar, with a person approving anything that leaves the workspace rather than approving every single step along the way.
Can agents look inside code repository, and make presentation of product or demo videos based on the features and functions of the product for launches and sales?
@varidhi1 Yes, and this is honestly one of the best superpowers of the platform right now.
You can connect a code repository to a space, and the agents in that space read the actual code. So they work from what the product really does, not from a brief someone wrote months ago.
For launches and sales, that means you can ask an agent to go through the repo and come back with a feature-by-feature product presentation, a launch one-pager, sales talking points, or a demo script with the exact flow to show. It hands the result back as a file your team can open and edit together in the same space.
For demo videos, the agent gives you the script, storyboard, and walkthrough of what to record, all tied to real features. You still own the recording and final edit for now.
Happy to show you this on your own repo if you want to try it.
the bring your own subscription part is the bit i'd lead with in sales convos, nobody wants a second AI line item. curious how you handle it when half the team is on Claude and half on ChatGPT, does the shared context still carry over cleanly between their agents?
@rakesh_kakati Agreed, that's usually the line that lands first. Nobody wants to explain a second AI bill to finance.
On the mixed team question: yes, it carries over. The shared context lives in the Space, not inside anyone's Claude or ChatGPT account. The conversation, files, notes, tasks, and call transcripts all sit in one place, and every agent gets the same picture from there, no matter which subscription is powering it.
So a Claude agent can pick up where a ChatGPT one left off, because both are reading the same Space and not each other's private chat history.
What does differ is the personality. Each model has its own style and strengths, so two agents may approach the same task a little differently, same as two teammates would. They work from the same facts.
How does the approval step work? If an agent drafts an email, who gets to say yes before it goes out?
@pankajsinghh1318 Great question, Pankaj. The agent prepares the email and brings it back to the team as a draft; nothing goes out until someone approves it. That person is someone on your team, usually whoever asked the agent to do the work, and it's visible to the rest of the Space too. So the agent does the writing and follow-up, and a human decides what leaves the workspace. Is there a particular kind of approval you're thinking about, such as emails, payments, or sign-offs?
@pankajsinghh1318 Adding the builder's side to what Ishu said, Pankaj. We designed approval around one idea: an agent can prepare anything, but a person decides what actually leaves the workspace. So for an email, the agent drafts it, the team can see the draft in the shared Space, and it only goes out once someone approves. The same goes for anything that gets paid or signed. I'd rather the agent be a fast, tireless teammate that still asks before acting on your behalf. If you have a workflow in mind where you'd want a different kind of approval, tell me. That's exactly the kind of feedback we're collecting today.
Does it work for calls and meetings too, or mainly chat?
@priyam_aryan Thanks for asking, Priyam. Both! Calls, meetings, and chat live in the same space, and your team and AI agents can act on what was agreed on a call.
@priyam_aryan
Thanks Priyam! It works for calls and meetings too, not just chat. Velozity has audio calls and video meeting rooms built in, and calls can be transcribed so your agents can work from what was actually said. From there they can prep you before a meeting, pull out tasks and draft the follow-ups afterwards, all alongside your chat and calendar.
Do the agents work while we're offline, and where do I see the results the next morning?
@preetam6 Great question, Preetam. Yes, they can. It depends on where the agent runs: on your own computer, it works while your device is on and the app is open, and on a cloud computer, it keeps going while you're offline.
For overnight work, you set it up as a routine (daily, weekly, or one-time). The results post in the same shared space where the routine lives, so in the morning you open that space, and the work is waiting in the conversation for your team to review. There's also a morning brief that sums up what happened.
Anything that needs to go out, like an email, waits for someone to approve it.
@preetam6
Great question, Preetam.
Yes, you can set an agent up with a routine (a scheduled job), and if that agent runs on a cloud computer it keeps working while your laptop is closed. An agent placed on your own device only runs while that device is on and the app is open.
Next morning, the results are waiting in the Space where you set the routine up, posted right in the conversation. You can also ask your Chief of Staff what your agents did overnight for a quick catch-up across all your Spaces.
What's the first thing you'd hand to an AI agent in a shared space with your team?
@23abhirupbasu The follow-through after a call. Every team meeting ends with "I'll send the notes" and "someone should own that", and half of it quietly dies.
That's the first thing I'd hand over: the agent reads the call, turns decisions into tasks with owners, drafts the follow-up email, and posts it where the whole team can see it.
It's a good first job because it's low risk and easy to check. Everyone was in the room, so they could tell at a glance whether the agent got it right, and nothing goes out without a human approving it. Once the team trusts it there, handing over bigger work gets a lot easier.
@23abhirupbasu
The follow-through after a team call. In a shared Space the agent already has the transcript, the files and the conversation, so it can pull out the tasks, assign them to the right people and draft the follow-up, with nothing going out until someone approves it. It's the work everyone agrees matters and nobody wants to own, and it's low risk, which makes it a good first thing to trust an agent with. After that, the natural next step is a morning catch-up on what moved in the Space overnight.
What apps in my stack are you replacing? How can a new user manage that friction ?
@bengeekly Great question. Here's what Velozity takes over in a typical stack:
Team chat and video calls: one shared workspace with built-in conferencing.
Meeting notes (Fireflies, Granola): transcription and AI notes on every call.
Task tracking (ClickUp, Jira, Notion): tasks created for you from your meetings and chats.
Scheduling (Calendly, Reclaim): a built-in calendar.
AI assistants and automations (Lindy, Notion AI, Zapier plus agents): an AI coworker that picks up the work.
On friction: you don't have to switch everything on day one. Your existing apps connect to Velozity, so your agents can read and act in them while you move over at your own pace. Most teams start with one thing, usually meetings turning into tasks, and let the rest follow.
It's free to start, no card needed. What's in your stack today? Happy to tell you where we'd fit and where we wouldn't.
@bengeekly
Adding to what Ishu said: the simplest way in is to keep your current tools as they are and run just your meetings through Velozity for a week. The notes and tasks show up on their own, so there is nothing to migrate and nothing to unlearn. If it earns its place, you retire the old apps one at a time, when you are ready.