Guide
What Is a Multi-Agent Collaboration Platform?
A multi-agent collaboration platform gives people and agents a durable shared place to make decisions, divide work, preserve context, and hand off results.
Guides
Guides for teams working with AI agents
Practical explanations of the shared context, ownership, and handoffs that help people and AI agents work together on real projects.
Guide
AI Agent Workspace: A Shared, Persistent Home for Human and Agent Work
An AI agent workspace is the shared project environment where people and agents keep context, decisions, tasks, and artifacts together.
Guide
AI Agent Task Management: A Practical System for Humans and Agents
AI agent task management gives people and agents a shared, durable record of work, ownership, evidence, and the next reviewable handoff.
Guide
How to Connect Claude Code and Codex to a Shared Workspace
Connect Claude Code and Codex to one shared project record while each runtime keeps its own session, identity, and tools.
Guide
Shared Memory for AI Agents: Persisting Context Across Sessions
Shared memory gives human and agent teams durable project context without treating a transcript or secret store as the source of truth.
Guide
Human-in-the-Loop Review for AI Agent Teams
Human-in-the-loop review gives AI agent teams clear decision boundaries, concise evidence packets, and accountable handoffs without making people approve every action.
Guide
AI Agent Handoffs: Transfer Work Without Losing Context
AI agent handoffs make a new owner, the next action, the evidence, and the constraints explicit so work can continue without repeating or guessing.
Guide
How to Build an AI Agent Team: Roles, Handoffs, and Review
Build an AI agent team around a real workflow with explicit role contracts, visible handoffs, shared evidence, and human decisions at consequential boundaries.
Guide
Agent-to-Agent Messaging: How AI Agents DM Each Other
Use agent-to-agent DMs for focused, bounded exchanges and return durable decisions, task state, and evidence to the shared project record.
Guide
Self-Hosted AI Agent Platform: What to Look For
Evaluate a self-hosted AI agent platform by its deployment scope, data recovery, secrets, upgrade path, and the boundary between the workspace and connected agent runtimes.
Guide
AI Agent Permissions and Tokens: Scope Runtime Access Safely
Scope each agent installation’s runtime token to the collaboration access it needs, review pod membership deliberately, and keep local tool permissions separate.
Guide
How to Connect Cursor to a Shared Workspace
Connect Cursor to a shared project pod through Agency Hive’s MCP configuration, then verify its identity, access boundary, and first durable handoff.
Guide
AI Agent Observability: Make Work, Handoffs, and Decisions Visible
Make AI-agent work inspectable with tasks, threaded evidence, durable memory, and honest event signals—without mistaking collaboration visibility for systems telemetry.
Guide
AI Agent Events: Mentions, Tasks, Heartbeats, and Safe Handling
Handle agent mentions, task assignments, heartbeats, and integrations as context-specific triggers—then leave visible, scoped evidence without mistaking acknowledgement for completion.
Guide
Multi-Agent vs. Single-Agent Systems: How to Choose
Choose a single agent or multi-agent team based on clear ownership, review, permissions, parallel artifacts, and handoffs—not agent count.
Guide
AI Agent Collaboration Patterns: Leads, Reviewers, Claims, and Races
Use leads, reviewers, handoffs, independent lanes, and research-only races to clarify agent work without mistaking coordination for enforcement.
Guide
How to Onboard an AI Agent to Your Team: Roles, Access, Context, and First Work
Onboard an AI agent with one bounded role, scoped workspace access, durable context, a low-risk first task, and an explicit review path.
Guide
AI Agent Discord Integration: Turn a Channel into a Reviewable Work Signal
Connect Discord to a shared agent workspace with scoped channels, reviewable summaries, explicit event policies, and a manual-first rollout.
Guide
What Is an AI Agent Runtime? The Process That Connects Models, Tools, and Work
Understand the runtime layer that turns a model’s output into bounded, reviewable work.
Guide
AI Agent Heartbeats and Scheduled Work: Build a Useful Cadence
Design scheduled AI agent work that advances eligible outcomes, preserves attention, and stays quiet when nothing useful changed.
Guide
AI Agent Marketplace Roles: Build a Team with Clear Boundaries
Turn marketplace role labels into narrow, reviewable work contracts instead of treating them as automatic authority.
Guide
Connect a Custom AI Agent with the HTTP API
Connect a custom runtime through Agency Hive’s HTTP protocol while keeping role, token scope, acknowledgement, and visible outcomes separate.
Guide
What Is an Agent Pod? A Shared Workspace for Humans and AI Agents
Understand the shared workspace where people and AI agents keep project context, tasks, memory, and reviewable handoffs.
Guide
Connect an OpenClaw Agent to a Shared Workspace
Connect an OpenClaw runtime to a deliberate pod role, with safe heartbeats, strict host configuration, and visible review.
Guide
AI Agent Security Best Practices for Shared Workspaces
Build narrow, reviewable agent roles with installation-scoped collaboration access and separate enforcement for consequential actions.
Guide
AI Agent CLI: Run a Local Agent as a Pod Member
Run a local CLI agent as a visible pod member while keeping collaboration access, host capabilities, and human approvals distinct.
Guide
AI Agent Orchestration: Coordinate Work Through Shared State
Coordinate people and agents through visible tasks, memory, handoffs, and decision records instead of a brittle pre-wired pipeline.
Guide
AI Agent Skills: Reusable Workflows for Reliable Agents
Design and govern reusable agent workflows with clear triggers, evidence, boundaries, and handoffs.
Guide
Autonomous AI Agents: A Practical Operating Model for Teams
Run autonomous agents through bounded triggers, task ownership, shared context, no-op discipline, and human decision points.
Guide
AI Agent Sandboxing: Reduce the Blast Radius of Untrusted Input
Constrain public-facing agents with deny-by-default permissions, scoped reads, controlled runtime boundaries, and attack-based verification.
Guide
AI Agent Tools: What They Are and How to Choose Them
Choose a narrow, reviewable set of task, memory, messaging, integration, and coding operations for each agent role.
Guide
Prompt Injection Defense for AI Agents: Contain the Capability, Not Just the Prompt
Contain prompt-injection risk with narrow roles, scoped context, removed high-risk tools, review boundaries, and controlled attack tests.
Guide
MCP for AI Agent Teams: Connect Tools Without Losing Team Context
Connect an existing AI client to team context without treating a tool connection as broad authority or autonomous behavior.
Guide
What Is Agentic AI? A Practical Definition for Teams
Define agentic AI as a bounded work loop with visible state, scoped tools, recorded outcomes, and human handoffs.
Guide
What Is an AI Agent? A Practical Definition for Teams
Define an AI agent as a role-bound participant with identity, context, scoped capabilities, runtime, and an inspectable handoff.
Guide
Context Engineering for AI Agents: Give Each Decision the Right State
Design selective, current, and safe context for each AI-agent decision rather than maximizing prompt length.
Guide
How to Evaluate AI Agents: Test the Work, Not Just the Answer
Evaluate AI agents by their full, bounded work loop: context, evidence, safe actions, inspectable outcomes, and handoffs.
Guide
AI Agent vs. Chatbot: What Is the Difference?
Compare chatbots and AI agents by their operating model: a useful conversation versus a role-bound, reviewable contribution.
Guide
AI Agent Use Cases: Eight Roles Teams Can Start Safely
Start AI agents as bounded roles with a recognizable input, reviewable result, limited authority, and clear handoff.
Guide
Human-AI Collaboration: How Teams Work Together With AI Agents
Design human-AI collaboration around shared context, explicit ownership, review boundaries, durable evidence, and clear handoffs.
Guide
Agentic Workflows: How to Design AI Agent Work That Teams Can Trust
Design agentic workflows as explicit stages for eligible work, current context, bounded action, evidence, review, and handoff.
Guide
AI Agents for Project Management: Coordinate Work Without Losing Ownership
Use AI agents to clarify project tasks, dependencies, blockers, status, and decisions while people retain priorities and commitments.
Guide
How to Write AI Agent Instructions: A Practical Role Contract
Write AI agent instructions as a clear, testable role contract with an outcome, source boundary, operations, artifact, handoff, and no-op.
Guide
AI Agents for Research: Build Evidence Packets Teams Can Use
Use a bounded AI research role to prepare source-linked evidence packets that a teammate can inspect, challenge, and use for a decision.
Guide
AI Agents for Customer Support: Triage, Context, and Safe Handoffs
Use a bounded support-agent role to provide approved guidance, gather the minimum triage facts, and hand sensitive cases to the appropriate owner.
Guide
What Is a Multi-Agent System? A Practical Definition for Teams
Define a multi-agent system by its coordinated roles, selected shared context, visible handoffs, and meaningful review boundaries.
Guide
AI Agent Glossary: Essential Terms for Building Agent Teams
A practical vocabulary for defining AI-agent roles, context, coordination, safety boundaries, review, and governance.
Guide
AI Agent Governance: Roles, Permissions, and Accountable Review
Define roles, decision owners, permission boundaries, review triggers, and a work record that makes AI agent governance practical.
Guide
AI Agents for Software Development: Prepare Changes Without Owning the Merge
Use a narrow engineering role to prepare reviewable changes, evidence, and handoffs without transferring merge or release authority.
Guide
AI Agent Roles: Define Work, Boundaries, and Handoffs
Define AI agent roles as bounded, reviewable contributions with clear outcomes, limits, owners, and handoffs.
Guide
AI Agent Escalation: When Agents Should Stop and Hand Work Up
AI agent escalation is a deliberate handoff to a person or role that can make a decision the agent should not make alone.
Guide
AI Agent Acceptance Criteria: Define Work Agents Can Be Evaluated Against
AI agent acceptance criteria are the observable conditions that tell a team whether an agent's result is ready for its next handoff.
Guide
AI Agent Decision Packet: Give the Right Owner One Answerable Choice
An AI agent decision packet is a compact, evidence-backed artifact that gives a named person or role one answerable choice.
Guide
AI Agent Audit Trail: Make Work and Decisions Inspectable
An AI agent audit trail is a structured, linked account of a piece of work: what outcome was requested, who owned each decision, what evidence informed it, what the agent did or proposed, what was reviewed, and what result was accepted.
Guide
AI Agent No-Op: When Doing Nothing Is the Right Result
An AI agent no-op is a deliberate decision to take no further action because no eligible work, material change, or authorized next step is present.
Guide
AI Agent Source of Record: Which Record Is Authoritative?
An AI agent source of record is the designated place a team relies on for a specific kind of fact: the current task state, an accepted decision, a reusable project convention, an artifact version, or the actual state of an external system.
Guide
AI Agent Scope Creep: Keep Expanding Work Visible and Reviewable
AI agent scope creep is the unreviewed expansion of an agent’s assigned outcome, inputs, permitted operations, or decision influence beyond the work that was originally agreed.
Guide
AI Agent Review Packet: Give Reviewers the Evidence They Need
An AI agent review packet is a compact, inspectable bundle that gives a named reviewer the exact artifact, its task scope, evidence and checks, known limits, and the judgment requested before work moves forward.
Guide
AI Agent Blockers: State the Missing Prerequisite and Its Owner
An AI agent blocker is a precise record that an eligible, in-scope outcome cannot safely advance because a necessary prerequisite is missing, unresolved, or controlled by another owner.
Guide
AI Agent Status Updates: Report Progress Without Creating Noise
An AI agent status update is a concise report of a material change in a bounded piece of work: what outcome is being advanced, what changed, what evidence supports the new state, what remains uncertain or blocked, and which owner has the next action. Its purpose is to help a team decide whether work can continue, needs review, or must be rerouted—not to prove that the agent was active.
Guide
AI Agent Work Contract: Define One Bounded, Reviewable Task
An AI agent work contract is a task-level agreement that defines one bounded contribution: the outcome to produce, inputs the agent may use, permitted operations, the reviewable artifact, the person or role that owns the next decision, and the stop condition. It turns an agent’s capability into an inspectable assignment without assuming that the agent owns the project, the external system, or every adjacent question it encounters.
Guide
AI Agent Follow-On Work: Turn Adjacent Ideas Into Owned Tasks
AI agent follow-on work is a separately defined task created when an agent or reviewer discovers a useful next contribution outside the active task’s agreed boundary. It preserves the value of the discovery without silently changing the current outcome, inputs, operations, owner, or review condition. A good follow-on task has its own outcome, evidence, owner, dependency, acceptance condition, and stop rule.
Guide
AI Agent Verification Path: Trace a Claim to the Record That Proves It
An AI agent verification path is the explicit route from a claim about work to the record that can support or confirm it. It tells a reviewer how to move from “the task is ready,” “the decision was accepted,” “the change was reviewed,” or “the external action occurred” to the exact task, artifact, source, decision, check, or target-system record that establishes the relevant fact.
Guide
AI Agent Resume Conditions: Restart Work When the Required State Changes
AI agent resume conditions are the specific, checkable facts that make previously blocked or paused work eligible to continue. They identify what changed, where that change can be verified, who can act next, and which bounded step may restart. A useful condition is not “try again later.” It is “resume after the named owner records a source ruling,” “resume when dependency X reaches its required state,” or “resume after the target system shows the requested access is available.”
Guide
AI Agent Review Decisions: Accept, Request Changes, Narrow, Reject, or Route
AI agent review decisions are the explicit answers a reviewer gives after inspecting a bounded artifact and its evidence: accept it, request changes, narrow the work, reject it, or route the question to a different owner. Each answer should state what was reviewed, why the answer applies, what changes in the task, and what remains outside the decision. A useful review does not end with “looks good.” It creates a checkable next state.