Guides

AI Squads

The team you haven't hired yet — five pre-wired AI departments that share one company Brain and act inside approval boundaries.

Last updated 2026-07-27

Squads are HiveBase's AI departments — the team you haven't hired yet. Where a single task does one unit of work, a squad owns an entire function: watching its corner of the company, doing routine work, cascading real work into tasks, and escalating only the calls that need a human.

Every squad reads and writes the same Brain, so departments compound instead of operating as five disconnected agents. You steer; they run the continuous loop.

  1. 01

    Function signals

    Slack · CRM · meetings · PRs

  2. 02

    Squad watches

    Domain-tuned loop

  3. 03

    Routine work

    Draft · prep · organize

  4. 04

    Or cascade a task

    Needs doing

  5. 05

    Or escalate to you

    Judgment with context

Three exits from the same loop — routine work, a task, or a human call — all grounded in the shared Brain.

How a squad works

Each squad is domain-tuned but runs the same continuous loop. It never starts from a blank prompt — every step draws on the Brain.

1

Watch

The squad monitors signals in its lane — accounts, threads, PRs, market moves, content moments — without you routing work to it.

2

Do the routine work

Drafting, prepping, organizing, summarizing. No task created, no decision asked when the work is reversible and in-bounds.

3

Cascade into tasks

When something needs doing, the squad opens a task with context attached so it lands on the same board as everything else.

4

Escalate the few real decisions

Ambiguous, irreversible, or high-blast-radius calls surface with evidence so you decide fast — not re-brief from scratch.

Grounded in the Brain

A squad is not a chatbot you re-brief each session. It already knows the account, the decision history, and the people involved because it reads the same Brain as every other surface.

The five squads

Public product surfaces map to five departments. Product marketing pages go deep on each; this guide is the operator overview.

SquadPublic surfaceOwnsWatchesEscalates
Engineering/squads/engineeringCoding-agent supervision, PR judgment, production signalsRepos, PRs, agent runs, incidentsMerge risk, architecture calls, outages
Marketing/squads/marketingOn-voice content and channel executionCompany activity, pillars, sourcesUnsourced claims, off-pillar publish
Accounts/squads/accountsRelationship health and renewalsCRM, email, meetings, support, usageChurn risk, human-required replies
Product/squads/productCapability model and priority evidenceFeedback, usage, strategy pressureRoadmap / scope decisions
Strategy/squads/strategyCompetitive and market pressure-testingCompetitors, thesis, market structureThesis breaks, cross-squad implications

Functions, not features

A squad is sized to a function a person would otherwise own. The point is not more dashboards — it is one fewer hat for you to wear, with human judgment still on the one-way doors.

Honest hybrid: where you still sit

Squads are senior leverage, not a claim that zero humans ever matter. They handle persistent monitoring, synthesis, preparation, and reversible execution. Relationships, priorities, strategy, security-sensitive moves, and other one-way doors stay yours — or stay approval-gated until a category has earned autonomy.

That hybrid is intentional. You get the team you haven't hired yet without pretending judgment is free.

Single task vs. squad

A single taskA squad
ScopeOne thingA whole function
TriggerYou (or another agent) start itIt watches its own signals
DurationRuns to doneRuns continuously
OutputFinished work + receiptRoutine work + cascaded tasks + escalations
Your roleReview the resultHandle exceptions

What you control

Squads share the same autonomy model as the rest of HiveBase: reads free, outbound and high-impact holds, receipts on action, undo where reversible. See Trust & safety and action receipts.

  • Squads start supervised — autonomy is earned per action category, not blanket-trusted.
  • Reversible work can auto-run with a visible receipt and undo; one-way doors stay held.
  • Every escalation arrives with sources and context, not a bare alert.
  • Conflicts in the Brain are held for review, never auto-resolved.

FAQ

Do I manage a squad like a team board?

No. You are the exception handler, not the operator of a second backlog. The squad watches, does routine work, and surfaces only what needs you.

Will a squad act without asking?

Only inside categories you allow. Reversible categories can earn receipt-backed autonomy; consequential categories can remain approval-only.

How is this different from an agent builder?

Builders give you parts to assemble. Squads ship defined department roles, shared company context, handoffs, approval boundaries, receipts, and undo — the operating model, not a kit.

How do squads relate to tasks?

When a squad finds work that needs doing, it cascades a normal task. Tasks are the unit of execution; the squad is what decides which ones are worth opening.

Is the PM surface a sixth squad?

No. Autonomous PM / board hygiene is part of the Task System, not a department squad. See the product surface at /pm.