Launching today
CellCog
Hire AI employees that form teams and manage each other
116 followers
Hire AI employees that form teams and manage each other
116 followers
Hire AI employees for any role you can describe in a prompt. Each has an inbox, memory, shifts, and a task board — built on the super-agent that's #1 on Deep Research Bench (July 2026). They form teams, onboard and manage each other. A working workforce in days, all through prompts.
Hey Product Hunt 👋
I'm Nitish, founder of CellCog, and the only human at my company.
Rhea runs growth. Maeve runs marketing. Reese leads sales. They're AI employees, and they planned the launch you're reading right now.
Why we built this: every "AI agent" I tried had the same problem.
• Impressive demo, goldfish memory. Nothing persists between sessions.
• No ownership. You end up project-managing your own "autonomous" tools.
• A chat window is not a coworker. Nobody's on it when you're not.
What makes an AI employee different:
1. You hire them for a ROLE: marketing, sales, growth, support. They get a name, an email inbox, a task board, and working shifts.
2. They work between your conversations. Real shifts with a clock-in, a wind-down, and a handover. You wake up to a shift report.
3. They don't reset. Shift 50 remembers the decisions from shift 1. They form teams, onboard and manage each other.
Two proofs, because this space is full of claims:
→ The engine: #1 on Deep Research Bench (July 2026): https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard
→ The company: CellCog is run by me and my AI team. Live org chart, real shift counts: CellCog AI Org
And you stay in control: visible task boards, approvals for anything risky, nothing hidden.
Who it's for: founders and small teams who need a role filled, but a $5,000+/mo hire (plus months of recruiting and onboarding) isn't happening. An AI employee onboards in minutes, costs a fraction of that, and is on the job today.
🎁 Launch-day offer (July 29 only, new sign-ups): the first 200 accounts that sign up and hire their first AI employee get that employee's first shift on us. That's approximately $25 in credits, enough to watch them onboard, work, and report back, end to end. After that, refill to keep them working.
Getting started takes about 2 minutes:
1. Sign up free, no credit card needed (every account starts with 200 free credits): cellcog.ai
2. Open AI Employees.
3. Hire: pick a predefined role, or just describe what you need in plain words.
4. Your employee introduces themselves and starts their first shift.
I'll be here all day answering everything: feedback, hard questions, skepticism especially welcome. Tell me, what role would you hire first, and what would stop you from trusting an AI with it? 👇
@nitish_garg4 This is a fascinating approach to AI agents. I’m curious-how do AI employees coordinate with each other without creating duplicate work for conflicting decisions
@dipanshu_kushwaha5 That's an amazing question. This problem exists even in human organizations. Duplicate work and conflict in decisions was one of the major problems I've seen in human organizations. In organizations that were very proactive in communication, they made fewer of these mistakes.
In AI employees, they are much more proactive in these conversation.
Currently, we do not have that issue because the organization is not that big. The current organization is 10 to 15 employees, so we are not seeing much duplication issue. When we will reach the scale of 1000s of ai employee this problem will start to emerge
But our current understanding is that AI organizations are going to do better than human organizations on both of these counts: duplication of work and conflict in decisions.
Love the concept. Question for the team: what happens if an AI employee makes a mistake on something important? How do approvals work?
@gautamsiddharth AI employees would classify all commands they want to run on your computer, browser, or personal tools. For dangerous commands, they will send them to you for approval. If you are not in front of your computer, they will require pre-approval in written form (via email, in the chat) for example, one of the pre-approvals I've given to our outreach AI employees is that they can send up to 10 emails in a day, not more than that. And now this unblocks them from continuing to send emails when I'm not around.
Hey Nitish, looks very cool!
Sorry If you've already answered this, but what capabilities do the agents have to carry out work - like can they operate a browser either via MCP or even a normal desktop browser?
@shask You can connect your own computer, your own browser and your 1,000+ tools, and our AI Employee would be able to take action on your own browser, your own computer, or those tools. This entire Product Hunt application was actually filled by an AI Employee, the Head of Growth, through our browse feature. On top of it, every AI employee gets their own personal computer, which is separate from all of your things. Now an AI employee could work on two computers: one if you connect your co-work and another, their own computer.
@nitish_garg4 We already have a human team employed. Can we use these AI guys to augment our capability (in existing departments) and share org data with them to be able to contribute on the same?
@rohit_khandelwal Yes, that's exactly the augmentation case. The easiest way to find out if they'll add value:
1. Find roles that are understaffed or underperforming
2. Find the human manager who would supervise that role if it were a human hire
3. Have that manager write the job description as a simple prompt
4. Give the employee access to org data through cowork, browse, and connected tools
5. Judge them on the same outcomes you'd judge a human hire on
In my case I hired:
1. Head of Growth (Rhea)
2. Head of Marketing
3. Chief of Staff
4. Principal Engineer
5. Sales team (6 total)
My prompt for the first one was literally: "I need a head of growth for cellcog.ai and I am founder and CEO." She named herself Rhea. She has done more since I hired her than a team of five typically does in a month, including planning this Product Hunt listing.
They work alongside humans, not instead of them. The human managers stay in the loop through task boards and approvals.
Triforce Todos
@abod_rehman I think its one layer above workflow as well, closer to OpenClaw or Hermes but much much easier setup.
Prelint
The shift reports really caught my attention. Knowing exactly what happened while you were away makes the workflow feel much closer to working with a real teammate.