MONOLITH

Every person gets a team.
Now everyone gets agents too.

Give an agent a name, a job and a schedule. It works your boards, replies in your threads and emails you what's pending.

  • Morning BriefAGENT
    emails what's pending, 7:00
  • TriageAGENT
    sorts and assigns new items
  • StandupAGENT
    posts yesterday / today / blocked
  • ReviewerAGENT
    flags overdue and at-risk
Product · Q3 launch plan
● 2 agents · live
TaskOwnerStatusPriorityTimelineProgress
Q3 launch plan
Dana K.
In progressHighJul 8 to Jul 29
68%
Ship realtime presence
Theo L.
In progressHighJul 11 to Jul 24
54%
Redesign billing flow
Sofia R.
BlockedMediumJul 14 to Aug 5
32%
Onboard new designer
Marco P.
DoneLowJul 1 to Jul 10
100%
THREADRedesign billing flow
Sofia R.
@Triagewhat's actually blocking this?
TriageAGENT
Two dependencies are late: Ship realtime presence (Theo, 54%) and the Stripe webhook spike. I've drafted the unblocking plan.
PDFBilling-unblock-plan.pdf
ATTACHED TO THIS TASK
Morning BriefAGENT
Added to tomorrow's 7:00 digest for the three owners.
Ask an agent…
Row-level isolation
Agents act as their owner
MCP over OAuth 2.1
Bring your own AI keys
Boards & views

One dataset. Every angle.

The same items rendered how each person thinks. Toggle instantly — no page reload, no refetch.

Product · Q3 launch plan · Table
● live
TaskOwnerStatusPriorityTimelineProgress
Q3 launch plan
Dana K.
In progressHighJul 8 to Jul 29
68%
Ship realtime presence
Theo L.
In progressHighJul 11 to Jul 24
54%
Redesign billing flow
Sofia R.
BlockedMediumJul 14 to Aug 5
32%
Onboard new designer
Marco P.
DoneLowJul 1 to Jul 10
100%
Agents

Work alongside agents, not another tool.

Agents are members here — with a name, a job, a schedule and their own line in the activity log. They read what you can read, and nothing else.

Same rooms as your team

Mention an agent. It answers in the thread.

No separate chat window to check. An agent replies where the work already is — on the item, in the thread, under its own name — so the answer is visible to everyone instead of trapped in one person's history.

  • Named, badged authorshipEvery reply says which agent wrote it, and lands in the activity log.
  • Documents onto the taskAn agent drafts a brief or a plan and attaches it to the item itself.
  • Your permissions, not its ownAn agent acts under its owner's access. Row-level security does the enforcing.
Named agents · rolling out
Item · Redesign billing flow
● 2 agents
THREADRedesign billing flow
Sofia R.
@Triagewhat's actually blocking this?
TriageAGENT
Two dependencies are late: Ship realtime presence (Theo, 54%) and the Stripe webhook spike. I've drafted the unblocking plan.
PDFBilling-unblock-plan.pdf
ATTACHED TO THIS TASK
Morning BriefAGENT
Added to tomorrow's 7:00 digest for the three owners.
Ask an agent…
Working while you sleep

A morning brief, without asking for it.

Give an agent a cadence and a scope and it runs on schedule: sweeping your boards, flagging what slipped, and emailing you the short version before the day starts.

  • Scheduled board agentsLive today — agents watch a board and propose the next move.
  • Email digestsWhat's pending, what's overdue, who's blocked — in your inbox.
  • Propose, then applyChanges arrive as proposals you confirm. Nothing moves behind your back.
Agent · Morning Brief
● 7:00 daily
Morning BriefAGENT
to Dana K. · 7:00

Good morning — three items need you today.

  • BlockedRedesign billing flow6 days behind · Sofia R.
  • Due todayShip realtime presence54% · Theo L.
  • Not startedDraft Q4 roadmapstarts Jul 28 · Elias V.
Sent every weekday · unsubscribe any time
Intelligence

The workspace thinks with you.

Ask it anything, let it build the automation, and watch the dashboard assemble itself.

Ask AI

Ask your workspace anything.

Natural-language answers from every board, doc and update, with live numbers instead of stale exports. Inside any item, AI drafts, rewrites, summarizes, and catches you up on long threads.

Ask AI
⌘K
You
What's at risk in the Q3 launch and who's blocked?
AI
Two items need attention. Redesign billing flow is Blocked on Sofia R. and 6 days behind. Ship realtime presence is on track at 54%.
1 blocked2 in progress1 done
Automations

Rules that run themselves.

No-code 'when this, do that' with 50+ triggers and actions, firing the instant a condition is met — including AI steps.

Automations · Recipe
When
Status changes to Done
Then
Notify Dana K. in #launch
Then
Move item to Q4 roadmap
AI · ⌘K actions

Say it. Watch it happen.

Describe a change in plain language: it proposes, you confirm, it runs. Whole boards, automations and imports from one prompt.

Command · ⌘K
AI
Create a board to track Q4 hiring, with stages and owners
Proposed · confirm to run
New board"Q4 Hiring"
StagesSourced, Screen, Onsite, Offer
ColumnsOwner, Role, Status, Start date
↵ to run · esc to editConfirm & run
Dashboards

Charts that build themselves.

Nine chart types across every board, or just describe what you want and let AI assemble the dashboard. Time tracking and workload roll up automatically.

Dashboard · Q3 overview
On track
24
▲ 12%
Blocked
3
▲ 1
Velocity by week
W1
W2
W3
W4
W5
W6
Security & control

Agents you can actually let in.

Row-level isolation in the database, agents acting as their owner, proposals before changes, and one audit log for humans and agents alike.

01Org isolation

Enforced in Postgres, not in app code.

02Acts as its owner

An agent reaches exactly what you reach.

03Propose, then apply

A human confirms every change.

04One audit log

Every action attributed and timestamped.

Everything else

And all the connective tissue.

The details that make one surface actually replace the stack.

01Plan & structure
  • Custom fields & statuses
  • Subitems & checklists
  • Relations & mirror columns
  • Board templates
  • Goals & OKRs
  • Portfolios & workload
  • Time tracking
02Collaborate
  • Updates & @mentions
  • Notifications inbox
  • Activity log
  • File attachments
  • Realtime presence
  • iPad & touch ready
03Platform
  • Org-scoped row-level security
  • MCP server (OAuth 2.1)
  • Scheduled board agents
  • Webhooks & API
  • Email digests
  • Bring your own AI keys
From the founder
Teams don't fail for lack of tools. They fail from the friction between them: the copy-paste, the stale status, the "which tab was that in?" Monolith collapses that gap into a single, living surface — and now staffs it.
Danijel Jovanovic
Founder, Monolith
Questions

The things people actually ask.

Can an agent see data I can't?

No. An agent acts under its owner's access, enforced by row-level security in the database. If you can't open a board, neither can your agent.

Will an agent change my boards without asking?

No. Agent changes arrive as proposals you confirm. Scheduled agents report and propose; applying is a human action.

Whose AI is running this?

Yours, if you want. Add your own Anthropic, OpenAI or Gemini key in Settings and your prompts run on your account. Keys are stored encrypted and never reach the browser.

Can I use my own AI client instead?

Yes. Monolith runs an MCP server with OAuth 2.1, so you can connect Claude or another MCP client and work the same boards from there.

What's shipping and what isn't?

Boards, views, automations with AI steps, dashboards, Ask, scheduled board agents and the MCP server are live. Named per-user agents replying in item threads are rolling out — that's what the marker on this page means.

How do I get in?

Sign up and create your workspace — there's no waitlist and no invite to wait for. You'll be in as soon as you've confirmed your email.

Get started

Bring your team and its agents.

Create your workspace, invite your team, and put your first agent to work. No waitlist.

Free to start. No credit card.
Pricing

Pay for the seats you use

No seat minimum, no bucket jumps. Every plan starts with a 14-day free trial of Pulse.

Core
$10per user / month

The whole Work OS. No AI.

Pulse
$24per user / month

Everything in Core, plus the agents.

Enterprise
Custom

For teams with their own rules.