HiFoxAgents

Let Agentsexecute the work

An Agent is saved configuration, not a one-off prompt. Write instructions, bind Skills, pick a Runtime, and assign it repeatedly. A person stays responsible; the Agent executes.

How Agents work

How it works

Share an Agent with the whole team

Instructions, Skills, and the Runtime live on the Agent. Anyone in the Space assigns it and follows the run, and the result returns to the same Task.

One assignee field for people and Agents

The assignee field lists people, Agents, and Crews in one place, chosen the same way. Context, progress, blockers, and results stay on the Task.

The working setup is saved

Instructions, Runtime, Skills, repositories, and environment settings belong to the Agent, not to the host that executes it. The next Task starts from that configuration.

Crews coordinate several executors

A Crew is a leader Agent plus other Agents and people. Assign the Crew when the work needs roles, sequencing, and coordination.

What Agents do

From request to release, run by Agents

Agents take Tasks, continue from comments, and work in Crews. Use Chat to explore; put work the team must follow on a Task.

01Assign

Assign the Task to an Agent

The owner of a Task is always a person; an Agent or Crew holds the execution slot. The field is called Assignee whoever is picked.

  • People, Agents, and Crews share one assignee control
  • Owner, status, and history stay visible while an Agent runs
  • Blockers and results return to the Task, not a private session
02Agents

Share the Agent configuration

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

  • Two Agent types by role: Code development and Daily work
  • Shared to a Space, so any member can assign it
  • Swap models in the Runtime without touching the Agent
HiFox Agent configuration
03Skills

Turn a process into a team Skill

A Skill holds reusable instructions and supporting files. Turn one review rule, delivery checklist, or writing standard into a Skill and bind it to the Agents that must follow it.

  • Scope a Skill to the organization, a Space, or one Agent
  • Create, upload, or import one, then bind it in Agent settings
  • Keep one-off requirements on the Task
Skill instructions bound to an Agent
04Crews

Let a Crew of Agents run the Task

A Crew has an Owner, a leader Agent, and Agent and people members. Use one when the goal needs interpreting before executors are chosen.

  • The Owner manages the Crew; the leader Agent coordinates each run
  • Only Agent members start runs; people collaborate on the Task
  • Visibility decides who can find and assign the Crew
A Crew with a leader Agent and members
05Chat

Explore in Chat. Keep it on a Task.

Try unsettled approaches in Agent Chat first. Turn it into a Task when the work needs status, history, or review.

  • Agent Chat and Task Conversation are separate surfaces
  • Create a Task from Chat when the work should be tracked
  • The built-in Assistant is a personal Agent you can DM
HiFox Agent Chat turning a conversation into tracked work

The Agent system

Each part has a defined role

Agents, Skills, and Crews are team resources. Execution happens on a Computer; review lands on the Task.

Agent

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

Skills

Reusable instruction bundles with a scope, bound to the Agents that 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. When an Agent is the execution assignee, an eligible comment continues the run.

@mention

Pull a person or Agent into the Task without copying context into another session.

Connected features

Agents are one part of the work system

Assignment only works if the host, the Task, and the review path are one system.

Quality of life, built in

Agents stay inspectable and reviewable

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

One Task: a person owns it, an Agent executes
Code development and Daily work Agent types
Built-in Assistant as a personal Agent you can DM
Skills scoped to organization, Space, or Agent
A Crew leader that coordinates the other Agent members
Comments that continue a run and attach the trace

Turn one person's setup into team capability

Configure the Agent once, assign it repeatedly, and keep every run on 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 set 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

Use Agents without a second work system

Is HiFox another AI Agent?

+

No. HiFox is the team work system built around Agents. Claude Code, Codex, and similar tools remain the Runtimes. HiFox supplies 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 all comments 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 does not start a run.

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, once its visibility is set to the Space. That is the design intent: one person's working setup becomes something teammates can assign without rewriting the prompt.