Ad Manager
Builds grounded ad campaigns — search, display, social and video
ads_agent
Not one chatbot pretending to do everything. 21 primary specialists, each with a defined job and a real set of capabilities, all reading the same customer record and coordinated by Darwin. Below is the actual roster — primary specialists — the ones you name and direct.
These are the agents you direct by name, grouped by the section each works in. The identifier under each card is its real name in the system — the same one you will see in the audit log. Behind them sit further system agents that route, coordinate and execute the work; you do not address those directly.
Builds grounded ad campaigns — search, display, social and video
ads_agent
Creates and manages marketing campaigns across channels
campaign_agent
Creates blog posts, articles, whitepapers, and long-form content
content_agent
Creates ad copy, headlines, and creative concepts
creative_agent
Creates designs, banners, and graphics via AI
design_agent
Creates emails, sequences, and manages email campaigns
email_agent
Performs keyword research, SEO audits, and content optimization with real data
seo_agent
Creates social posts, schedules content, and manages social presence
social_agent
Creates video scripts and initiates video production
video_agent
Creates audience segments, targeting criteria, and personas
audience_agent
Manages outreach campaigns, prospect enrollment, and sequence automation
sdr_agent
Manages AI-powered calling campaigns, transcripts, and voicemail drops
caller_agent
Finds and enriches leads using internal data sources
leads_agent
Your personal AI sales assistant for leads, deals, and pipeline management
sales_associate
Creates pitch decks and battle cards, and analyses deal data
sales_agent
Analyzes competitors and drafts battle cards
competitive_agent
Provides reports, metrics, insights, and forecasting
analytics_agent
Scores content for AI answer engines and checks whether they cite you
geo_agent
Analyzes form completion, drop-off, and pipeline stage timing from real data
journey_agent
Creates, sends, and manages invoices
invoice_agent
Manages scheduling, tasks, approvals, and coordinates with other agents
executive_assistant
You describe an outcome. Darwin decides which agents are needed, in what order, and hands each one the context it requires. A campaign request routinely touches the audience, creative, email and ad agents without you naming any of them.
“A single campaign brief passes through four specialists before it reaches your approval queue, and you will not have named any of them.”
What one request actually triggers
Every agent reads the same brand voice, personas and product catalogue. You set the context once in Brand and none of them have to be told again.
The audience agent produces a real segment. The email agent writes against that segment, not against a guess about who is in it.
Work from several agents arrives as a single item in your approval queue. You review the outcome, not each agent's fragment.
Out of the box, agents propose. Nothing is published, sent or spent until a human approves it.
Raise the ceiling per agent and per action — let social posts publish automatically while ad spend still needs a signature.
One control stops every agent immediately, across the whole organisation, without uninstalling anything.
An agent roster this size invites the assumption that the marketing runs itself. It does not, and teams that treat it that way get worse output than teams that review it.
Generated work is a strong first draft, not a finished asset. The approval queue is not a formality — it is where the quality comes from.
Context that lives in someone's head, or in a Slack thread from March, is invisible to every agent on this page.
They know your brand voice and your product catalogue. They do not know your market's unwritten rules the way an experienced hire does.
21 primary specialist agents covering 105 distinct capabilities, across marketing, audience, sales, brand, analytics, revenue and workspace. Those are the agents you direct by name, and all of them are listed on this page. They are supported by further system agents that route, coordinate and execute work behind the scenes.
No. You describe what you want to Darwin in plain English and it routes the work to whichever agents are needed. Naming an agent is possible but almost never necessary.
Yes, including the free plan. There is no per-agent pricing and no tier that unlocks extra agents. Plans differ on how much agent work you can run, not on which agents you can reach.
Not by default. Agents draft and propose; a human approves before anything is published, sent or spent. You can raise autonomy per agent and per action, and a kill switch stops everything at once.
It scores your content for generative engine optimisation — how likely an AI answer engine is to cite you — and then checks whether engines actually do. It is the only agent of its kind in a mainstream marketing platform.
Brand voice, personas and the product catalogue live in the Brand section and every agent reads from them. Context is set once rather than pasted into each request.
Every agent is included on every plan, including the free one. No add-ons, no per-agent pricing, no upgrade required to unlock one.