Kanban boards
See what every agent is doing.
Work by people and agents appears in simple stages such as Running, Waiting and Done, across every team.
Status at a glance.
One view for people and agents
Agent work sits on the same board as the team.
See what is stuck
Waiting cards show work held for an approval or a reply.
Open any card
Every card opens into its thread and full run trace.
Running, Waiting and Done
Cards move through simple stages as agents and people work, so anyone can see where things stand.
Running3
Collect spend history
AgentDraft support summary
AgentCheck vendor terms
PriyaWaiting2
Legal clause approval
LegalBudget sign off
FinanceDone3
Evidence packet
AgentRenewal notes
MarcusRisk summary
AgentWaiting means waiting on a person
When an agent pauses for an approval or an answer, its card shows who it is waiting for.
Workspace
Approval request
Vendor outreach is blocked
Finance and Legal must approve the packet before any external message can be sent.
Across teams and workstreams
Leaders can view one workstream or many, to see what people and agents are doing across departments.
How it works
From request to recorded result.
-
Work starts
A card appears in Running.
-
It may wait
For an approval or a reply.
-
It finishes
And moves to Done with its record.
Every feature runs inside the same six controls.
Identity, access, approvals, supervision, audit and policy apply to every agent and every run, whichever part of the workspace it happens in.
See governance and audit- Identity
- Access
- Approvals
- Supervision
- Audit
- Policy
FAQ
Kanban boards: questions and answers
Short answers to what teams ask before they put this part of SoftworkerAI to work.
Contact us directlyDo we have to move cards by hand?
No. Cards move as the work moves, including agent work.
Can we see one team only?
Yes. Filter the board by workstream or department.
What is behind each card?
The thread for that piece of work and the full run trace for any agent steps.
The multiplayer workspace for humans and AI agents is how teams move beyond prompting and safely hand AI real work. It gives people one place to plan, approve, and oversee execution, so they can run work with AI agents they can govern and trust.