Skip to main content
This page explains how Hive is put together, for technical evaluators and developers. It follows data from your tools, through detection and planning, to a decision and an action — and shows where each safety control sits.

The big picture

The loop: sense, plan, decide, act, learn

Hive’s core is a loop that runs continuously for every workspace.
1

Collect

Every hour, and immediately after you connect a tool, workers read from your connected accounts through the connector platform. Some providers also push changes in real time through signed webhooks. Files from Google Drive, Dropbox, OneDrive and SharePoint are synced into the knowledge base with their permissions.
2

Sense

For each member on a Max seat, Signals reads what changed in their connected accounts into their matters and decides what needs them: a reply owed, an invoice to chase, a payment or deadline due, a slipping deal, a correspondent missing from the CRM. The officer also checks those members’ watches. Built-in detectors also watch email threads and specific business processes. See Signals.
3

Plan

For a signal worth acting on, the AI drafts a plan: a sequence of typed actions with structured parameters, grounded in evidence from your tools and the Business Brain.
4

Decide

A deterministic policy engine — code, not a model — checks the kill switch, the action’s autonomy rung, its blast-radius tier, confidence, spend caps, rate limits and error budgets. The outcome is run, ask a person, or simulate. See Safety and control.
5

Act

An isolated executor, the only component that can use your credentials, carries out the approved action and records a receipt. Reversible actions record how to undo them.
6

Learn

Approvals, denials and outcomes teach Hive rules. A rule Hive learns starts Off or Suggested and only takes effect when a person turns it on. See Rules Hive learned.

Requests from people

Ask Hive, the workflow builder and Agent Studio follow the same pattern. The API verifies your session and role, gathers the context the request needs, and calls a model. Anything that would change something in your tools becomes a typed proposal and goes through the same policy engine as the loop. Ask answers are written on the workers. The API checks your question and your limits, then hands it to a worker with exactly your access, and streams the answer back to you. When every worker is busy, the question waits for a free slot; see When Hive is busy.

Workflows and agents at run time

  • A workflow is a graph of steps compiled and validated at deploy time into an immutable release. Each run executes that release step by step on the workers, persisting every step so a run survives restarts. See Workflow builder.
  • An agent is a saved, versioned configuration — instructions, knowledge, tools and governance limits — that runs with a budget of time, model calls and actions. See Agent Studio.
  • Both can be started by people, schedules, forms or other agents, and every external action they propose passes the policy engine.

Where the safety controls sit

Security overview

The protections in plain language.

Infrastructure

Providers and regions.

Developer overview

What you can build on Hive.

Key concepts

The vocabulary of Hive.