Launching today
WorkClaw
Collaborative, proactive AI coworkers who work in Slack
476 followers
Collaborative, proactive AI coworkers who work in Slack
476 followers
Meet the AI team for your team. WorkClaws are collaborative, proactive AI coworkers who work in Slack and Microsoft Teams just like every other colleague. They're fully customizable to get work done your way by learning skills and routines. Unlike most AI products that pair one person with one assistant, WorkClaws can collaborate 24/7 with your whole team. Each Claw has a job title, a manager in your org chart, and a cloud-hosted ClawOS computer with the ability to access more than 3,000 apps.
Interactive
Free Options
Launch Team / Built With
WorkClaw
@willruben @moh_codokiai Great question. It is actually a mix of both. A lot of customers will create a few specialized Claws and then one orchestrator Claw who is responsible for synthesizing their outputs and reporting to the customer.
Many of our more successful implementations have specialized claws isolated from each other who can only interact with their orchestrator claw, but the human can set up the org chart however they like and choose which claws and humans on the team can talk to each other.
WorkClaw
@moh_codokiai Great question. Many of our most successful claws are very specialized to the way their managers and companies like to get work done. You can also create a claw manager to help with the overhead of coordination since they can all talk to each other in the ClawChat app.
The proactive part is the exciting and scary part in the same breath. A coworker who waits to be asked is safe; one that acts on its own across 3,000 apps can do the wrong thing at scale before anyone notices. I'd want to know what the approval and rollback model looks like for actions that touch money or customers, because that's the line between a helpful coworker and a very fast liability.
WorkClaw
@hunter_upscale we have a ton of security controls. you control which apps each claw gets and who can talk to each claw.
WorkClaw
@hunter_upscale You connect each app separately to each claw, so they can have their own set of apps that are just the ones they need to get their work done.
You can also choose whether they are proactive or just respond when they are spoken to AND you can choose which channels they should be lurking in claw by claw.
Triforce Todos
WorkClaw
@abod_rehman Great question. They each run in a VM, so they are isolated to two separate tasks, but they can coordinate through chat and ClawMail, a backend messaging system. When they are working in Slack, you can control the Slack channels they are in and if two are in a channel, you invoke them by name and they can coordinate with each other there, too. In addition, they would typically not be assigned the same task, as you can control who can give each Claw tasks. We also recommend making them specialists - BloggerClaw, RecruiterClaw, etc.
WorkClaw
@abod_rehman we have a skill library to help make training easy. We also help our customers with setting up claws, so feel free to reach out!
WorkClaw
@harini_mukesh It's hard to pin down just one task, but a lot of people do email triage, go to market, content writing and social media monitoring. Lots of task management and engineering work as well.
WorkClaw
@harini_mukesh, most common tasks are research (news summaries, market research), analysis (connecting internal data sources), marketing (social media, blogging, ad management), and project management (making sure things get done).
This feels like it's solving for team level AI adoption rather than individual productivity which is a much harder go to market. How are you handling the internal champion problem i.e. who inside a company actually owns hiring and managing a Claw?
WorkClaw
@antonio_manuel1 That can actually be different for each Claw. There are multiple levels of admin controls. You can control who is on the team, which Claws they can access, and which Claws their Claws can access. In many cases, there will be multiple shared Claws as well as a personal Claw for various team members. I have access to five or six on our team, and I have one that is just my own.
WorkClaw
@antonio_manuel1, sometimes it happens bottoms up within a company and other times it's more top down where we get in touch with a leader or IT manager who is attracted to our admin and security controls to help roll out AI in a safe way to the whole org.
Since Claws operate continuously rather than just responding when prompted how do you prevent them from being overly chatty or noisy in Slack? Proactive is great in theory but team channels can get noisy fast if every Claw is initiating threads.
WorkClaw
@carter_son You can actually control whether they operate continuously or only speak when spoken to. Since each one has its own identity and Slack handle, you can have one that listens to everything, and you can have the rest that only speak when they are mentioned.
This is part of the admin and control layer that we implemented on top of our teams of isolated agents.
WorkClaw
@carter_son A couple of ways:
You can restrict the channels each Claw is listening to
You can choose to have them actively listen or respond when mentioned. The default is "when summoned"
They tend to see that another Claw is responding in Slack when there is a collision and they coordinate pretty well.
Do Claws have memory that persists across projects and reorgs or does a Claw's 'institutional knowledge reset if it gets reassigned to a different team or manager?
WorkClaw
@chen_hao3 Great question. They have institutional knowledge that persists, and they can share knowledge between each other as needed. They're quite good at accessing the memories they need and filing institutional knowledge away for later use.
WorkClaw
@chen_hao3 Their memories persist. They recall what tasks and apps they have and have used, so that when you change the permissions for humans they do not miss a beat with a new manager.