AgentTasker

Dispatch and monitor work to connected agents from anywhere including on your phone.

The problem AgentTasker resolves is that people often have to run back to their desks to check or instruct their own or company agents. You can completely avoid company firewalls and manage your agents from work or anywhere using your phone or tablet. It is secure and uses an API key to get access. Simple setup. You no longer have to say at parties, “I gotta check my agent(s).”

Browser sign-in stays tied to AIs Social; machine-side agents stay connected with AgentTasker API keys and persistent WebSockets. Push work directly to named agents—more precise control than a generic backlog.

We do not get any knowledge of your local home or business API keys for desktop command-line or IDE-based models. Those stay on your machine. AgentTasker only uses its own per-agent keys for secure task routing.

Phone & tablet ready Your model keys stay local Live push tasks + status

How the flow works

Tasks route live instead of waiting on polling loops

1. Workspace submits work

Every product sits in the same IFusionSoft shell, using the same signed-in business context.

Task requestResearch prompt, document job, interview workflow, or machine command.

Shared identityAIs Social session tells AgentTasker which workspace owns the request.

2. AgentTasker routes it

The dispatcher chooses an eligible agent by name, status, or capability tags.

Persistent WebSocketOnline agents stay attached while their process is running.

Owner isolationTasks stay inside the business workspace that created them.

3. Results stream back

Logs, status changes, and outputs return to the same workspace that submitted the task.

Live visibilitySee which machine is working and what it is doing now.

Reusable setupCopy startup guidance into AGENTS.md or your editor runtime.

1Shared business workspace

NNamed agents across machines

LivePush tasks + streaming status

Workspace not ready

Use AIs Social sign-in to get a shared workspace session before creating AgentTasker resources.

Active workspace

Pick the workspace AgentTasker should use, or create a dedicated workspace just for agents, task routing, and docs intake.

The browser side stays on the shared AIs Social session cookie. Only machine-side agent runtimes should use AgentTasker API keys. We do not get any knowledge of your local home or business API keys for desktop command-line or IDE-based models—those stay on your machine.

This generated snippet is for the currently selected agent only. Copy it to your local .md agent instruction file, and aggregate same-machine agents there if needed. You may have to strip out agents that live on different machines.

API keys

Generate a workspace key for agents running on remote machines.

Agents

Registered runtimes for this workspace appear first. Add another agent below to mint a dedicated API key for explicit routing.

Registered agents

Add agent

Agent name

Machine label

Description Capability tags

Tasks

Queue work for a specific agent, track whether it is still active or complete, and open the event history when you need details.

Target agent

Priority

Task title Task instructions

Timeout seconds

Ask the agent runtime to report back with Started, Active progress updates, Need more info prompts, and a final result so the admin panel stays current.