SharklyAgents

Assign work to Agentslike teammates

An Agent is a saved working configuration, not a one-off prompt. Give it instructions, Skills, and a Runtime, then assign a Task. People stay responsible. Agents execute.

Sharkly Agents assigned like teammates

Used by teams at

  • Amazon
  • Intuit
  • Markel
  • AT&T
  • Veeam
  • Maersk

Assign, configure, coordinate

Agents are reusable team capability

One person can configure how an Agent works. The rest of the Space can assign it, review it, and keep the result on the Task.

Assign like a teammate

Route a Task to an Agent from the same assignee control you use for people. Context, progress, blockers, and results stay on the work.

Save the way it works

Instructions, Runtime, Skills, repositories, and run settings live on the Agent. The next Task starts from that configuration instead of a blank prompt.

Coordinate with a Crew

A Crew is a leader Agent plus other Agents and People. Assign the Crew when the work needs roles, sequencing, or a leader who decides who acts next.

From assignment to review

Configure once. Assign many times.

Agents receive Tasks, continue from comments, and can be grouped into Crews. Chat is for exploring. The Task is for work the team must track.

01Assign

Put an Agent on the Task

People remain responsible. An Agent or Crew takes the execution slot. Mixed surfaces still use the shared noun Assignee — never Delegate.

  • Assign a person, an Agent, or a Crew from the same control
  • Keep owner, status, and history on the Task while an Agent runs
  • Return blockers and results to the Task instead of a private session
Assigning a Task to a person, Crew, or Agent
02Agents

Treat an Agent as saved configuration

Name, instructions, visibility, Computer, Runtime, Skills, repositories, environment, and run settings all belong to the Agent. It is not the host that executes.

  • Choose Code development or Daily work to match the role
  • Share the Agent in a Space so the team can assign it
  • Change models in the Runtime, not on the Agent
Sharkly Agents list and configuration
03Skills

Package the practice, not the prompt

A Skill holds reusable instructions and supporting files. Bind it to Agents that should follow the same review rules, delivery checklist, or writing standard.

  • Scope a Skill to the organization, a Space, or one Agent
  • Create, upload, or import a Skill, then bind it in Agent settings
  • Keep one-off requirements on the Task, not in a Skill
Skill instructions bound to an Agent
04Crews

Assign a reusable team, not one executor

A Crew has an Owner, a leader Agent, and Agent and People members. Use it when a leader should interpret the goal and involve other Agents.

  • The Owner manages the Crew; the leader Agent coordinates runs
  • Only Agent members start Agent runs; people collaborate on the Task
  • Personal or Space visibility controls who can find and assign it
Crew with a leader Agent and members
05Chat

Explore in Chat. Track it on a Task.

Standalone Agent Chat is for exploring, planning, or acting before the work needs ownership. Turn it into a Task when status, history, or review has to be shared.

  • Chat is a separate surface from Task Conversation
  • Create a Task from Chat when the work should be tracked
  • The built-in Assistant is a personal Agent for direct messages
Sharkly Agent Chat turning a conversation into tracked work

The Agent system

What an Agent is allowed to be

Agents, Skills, and Crews are team resources. Execution still runs on a Computer. Review still lives on the Task.

Agent

A saved actor with instructions, Runtime, Skills, and run settings. It can be assigned work and write comments.

Skills

Reusable instruction bundles with a scope. Bind them to Agents that should follow the same practice.

Crew

A leader Agent plus Agents and People. Assign the Crew when coordination is part of the work.

Visibility

Personal or Space visibility decides who can find, assign, and reuse an Agent or Crew.

Comments

On-task dialogue. An eligible comment can continue an Agent run when that Agent is the execution assignee.

@mention

Bring a person or Agent into the Task without copying context into another chat.

Meet the tools Agents already use

Agents run on your Computer. Tasks stay in your tracker.

Connect Jira, GitHub, or Slack so existing work can be assigned to an Agent without leaving the system your team already runs.

JiraGitHubSlack

Connected features

Agents sit inside the rest of the work system

Assignment is only useful if the host, the Task, and the review path are the same system.

Quality of life, built in

The details that keep Agents reviewable

An Agent is useful when the team can see what it was asked to do and what it did.

Assign people and an Agent or Crew on the same Task
Code development and Daily work Agent types
Built-in Assistant for personal direct messages
Skills scoped to organization, Space, or Agent
Crew leader that coordinates other Agent members
Comments that continue a run, with a link to the trace

Turn one Agent setup into team capability

Configure the Agent once, assign it like a teammate, and keep every run attached to the Task.

Start

Stand up an Agent the team can assign

Connect a Computer, save the Agent configuration, then put it on a real Task so review has a place to land.

01

Connect a Computer

Register a local or cloud Computer and confirm at least one Runtime is available before the Agent can run.

02

Create an Agent

Write instructions, pick a Runtime, bind Skills, and choose Space visibility so teammates can assign it.

03

Assign a Task

Set the Agent as the execution assignee. Comments, blockers, and results return to the same Task.

FAQ

Agents, without a second work system

Is Sharkly another AI Agent?

+

No. Sharkly is the shared work system around Agents. Claude Code, Codex, and similar tools remain the Runtimes. Sharkly adds assignment, Computers, Task context, and review.

What is the difference between an Agent and a Computer?

+

An Agent is the saved configuration: instructions, Skills, Runtime choice, and run settings. A Computer is the host those runs execute on. A Runtime is the concrete tool detected on that Computer.

When should I use a Crew instead of one Agent?

+

Assign one Agent for small, well-defined work. Use a Crew when a leader Agent should interpret the goal, involve other Agent members, and bring results back to one Task.

Do comments always start an Agent run?

+

Only when the Task’s execution assignee is an Agent and the comment is eligible. If the assignee is a person or empty, the comment is just a comment.

How is Agent Chat different from Task Conversation?

+

Agent Chat is a standalone session for exploring or planning. Task Conversation is comment-backed dialogue on a tracked Task. Use Chat first; create a Task when the work needs an owner, status, and review.

Can the team reuse an Agent I configured?

+

Yes, when the Agent is visible in the Space. That is the point: one person’s working setup becomes something teammates can assign without rewriting the prompt.