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.
Very innovative product, and it really defines the future of team collaboration. I am quite curious about how you handle company memory. If different teams have asymmetric information, how does the agent handle that problem?
@llma Thanks, Long- great question, and it's the one we think about most. Memory in Velozity isn't one shared pool. It follows the same boundaries your team already has:
Personal memory stays personal. An agent working for you only draws on what you've connected and approved: your own mail, calendar, meetings and notes. It doesn't quietly pull another person's private context into its answers.
Shared memory lives in Spaces. A Space is where a team's files, notes and decisions sit, and an agent in that Space only sees what's been shared into it. Different teams get different Spaces, so they naturally hold different information.
Nothing crosses over without a person. When an agent wants to save something to memory, or act on someone's behalf, it proposes it and the owner approves it first. Information doesn't leak from one team to another on its own.
Agents say what they don't know. If the answer lives in a Space or source they can't see, they say so and don't guess to fill the gap.
So the "asymmetry" is deliberate: each team keeps its own view, and an agent reflects that view without flattening it. When something needs to be visible to everyone, a person promotes it into a shared Space. Happy to go deeper on any part of this.
@stormshot Yes, we built on open standards wherever one exists, so nothing here is a proprietary lock-in:
Tools for agents: Model Context Protocol (MCP). Everything an agent can do inside Velozity (read a space, post a message, drive the browser) is offered to it through MCP, the same standard Claude Code and Codex already use.
Talking to agents: Agent Client Protocol (ACP). Gemini, Kimi, OpenCode, and Cursor agents run over ACP. Claude Code and Codex are run through their own official command-line tools, unmodified.
Sign-in and connected apps: OAuth. You log in on the provider's own page, and we never see your password.
Calls and screen sharing: WebRTC.
If you meant a specific standard, such as a security certification or a data regulation, tell me which one and I'll give you a straight answer.
@stormshot
Yes. Data is encrypted in transit (TLS 1.2+) and at rest (AES-256), connected apps sign in through OAuth with limited scopes, and we follow GDPR and CCPA. Your data is never used to train AI models, and the cloud infrastructure we run on is independently audited (SOC 2 Type II, ISO 27001).
Details: velozity.ai/privacy
How much time does your team spend repeating the same context to different AI tools?
Congrats @ishudarshan & team!
Thanks for sharing @rohanrecommends!
@hamza_afzal_butt Thanks, Hamza. Honestly, it varies, and sometimes it still takes longer than you'd expect. What's changed for us is that there's no back-and-forth anymore.
Everyone works in the same space, so it feels like one ongoing conversation, a bit like a WhatsApp group where the whole team and their agents are talking together. The agents feel like teammates, and everybody stays in the loop the whole time.
@hamza_afzal_butt
Adding to what Ishu said, Hamza: the repeating mostly goes away because the context lives in the Space, not in each person's chat with a tool. The files, the conversation and the call transcripts are already there, so any agent you bring in starts from the same picture as the team. You brief once, and the next person or agent picks up where the last one left off.
The shared context between the team and AI agents is what caught my attention. Love it
@shahriardgm Thank you, Shahriar! 🙌 Shared context was the whole reason we built it. When the team and the agents work from the same conversation, files, and tasks, nobody has to explain things twice. What would you want your agents to remember first about your team's work?
@shahriardgm
The context builds up on its own as the team works, so there is no separate step of briefing the agents. A new teammate or a new agent joining later starts from the same history as everyone else, which is where it really starts to pay off.
Are we planning to support integration with other tools, like GSuite, Slack, WisprFlow, Zoom etc? Leaving the favorite tools would be a pain for any team, I believe.
Darshan, I wish you the best. I have a question: As a founder, I have set some guidelines for my business (i.e. in marketing). Could the Velozity keep these central directions "in mind" when my team ask it to do a task for them? Or it applies the separate system setups and instructions of each individual user? I mean... could it centralize the strategic directions with Velozity?
The part I like is that agents sit alongside my teammates, so I don't have to move work between tools by hand.
@shreya_verma12 Thank you, Shreya! That's the part we care about most. Moving work between tools by hand is a hidden tax on every team, and it disappears once agents sit in the same place as your teammates. Which handoff has saved you the most time so far?
@shreya_verma12 Adding to Ishu's note: the reason it works is that the agent already has the context your teammates have, so there is nothing to copy over or explain again. A decision made in a call is already where the agent picks up the task. Curious which hand-off you would like us to make smoother next.