Director
Plans the day against your goals, splits the brief across the other agents — in parallel or in sequence — and reports back in plain language.
Budget cap$250/mo defaultConfigurable AI agents that read your live go-to-market data and execute real work — grounded in your company, capped to a budget, held for your approval. Operators, not chatbots.
14 days free · no card · every agent capped at $250/mo by default · nothing public sends without you
A chatbot answers; an agent acts. Each one is named, given a role and a system prompt, pointed at the tools it may touch, and capped to a monthly budget. They read your GA4, Search Console, Gmail, LinkedIn and CRM data, call 91 real tools to execute the work, and put every run on the record.
Plans the day against your goals, splits the brief across the other agents — in parallel or in sequence — and reports back in plain language.
Budget cap$250/mo defaultDrafts posts, landing copy and articles in your voice — grounded in your docs, your site and your data — then queues them to publish.
Budget cap$250/mo defaultBuilds nurture and broadcast email off your CRM segments, writes the subject line and the body, and holds every send for you.
Budget cap$250/mo defaultResearches the accounts, writes the first touch and prepares the sequence. Nothing leaves your mailbox until you approve it.
Budget cap$250/mo defaultReads the replies landing in your connected inbox, drafts the answer, and puts the meeting on your calendar once you say yes.
Budget cap$250/mo defaultEvery agent is yours to build: a name, a system prompt, a model, one of five roles — general, listener, topic, creator, analyst — the integrations it may touch and the money it may spend. No code, no per-seat tax.
Budget capyours to setInternal, reversible work — drafting, planning, opening a task — runs the moment an agent decides to do it, because undoing it costs nothing. Anything public or irreversible is prepared and queued instead. These are human-in-the-loop AI agents: fast where it is safe, stopped where it counts.
The agent reasons over your live data and stages the action — a drafted email, a campaign, a post — without sending anything.
Anything public or irreversible lands in Approvals. You read the exact message, change a word, and approve it — or send it back.
On your approval the agent runs the action through your own connected accounts — Gmail, LinkedIn, your CRM, your calendar. 30 connectors read and write.
The result is written to that agent’s run history with timing, output and any error, then tied back to your funnel.
A single agent is a head start; a team is a campaign. A Director coordinates member agents — in parallel or handing off in sequence — so a whole motion (research → content → outreach → analysis) executes as one deliverable with shared context. That is multi-agent AI for go-to-market, not a chat window.
Every reply and every action reads your company context, playbooks and knowledge first — so output sounds like you and stays inside the facts.
Grounded AIAI agents for sales work your outbound, deals and accounts, with intent-signal lead scoring behind them.
AI Sales & CRMThe same team runs campaigns, broadcasts and journeys, and publishes the content that feeds them.
AI Marketing AutomationRuns land on one TOFU/MOFU/BOFU funnel with a 30-day baseline, correlation and multi-touch attribution — so “sent 40 emails” becomes “moved MOFU health”.
Funnel IntelligenceThe whole motion in three steps, with the approval gate sitting exactly where it matters.
How it works
Carrying the whole go-to-market motion with one or two people? Agents are how you cover more ground without losing control — shaped for lean teams and startups.
Each marker is one of your agents. Its ring says what it is doing right now, and the Director keeps the brief moving between them.
The roster at a glance.
What an agent is, what it may do on its own, and what it costs you to run.
An AI agent for marketing or sales is software that reads your live go-to-market data and takes action on it — not just a chatbot that answers questions. In dolv an agent has a role, a tool set and a model, and it can call 91 real tools to compose content, prepare emails, create campaigns, schedule events and create tasks. Every action is grounded in your company context by default.
Both, by design. Internal and reversible actions — drafting, planning, creating a task — run immediately because undoing them costs nothing. Public or irreversible actions are prepared and queued in Approvals, where a human reviews and clicks approve before anything leaves your account. That is human-in-the-loop AI, not autopilot.
Each agent is configurable: you set its name, its role, its system prompt, the integrations it works across and its monthly budget cap — all without writing code. The hard limits that actually constrain an agent are the ones enforced by the platform, not by prompt: anything public or irreversible is queued for your approval, spend stops at the cap, and every action is scoped to your workspace's own data.
Yes. Every agent carries a default $250 / month spend cap with its current spend tracked against it. When an agent hits its cap it stops, so budgets are enforced by the system rather than by trust. You can raise, lower or watch the cap per agent at any time.
Yes. A Director agent orchestrates member agents into a multi-agent campaign — running them in parallel or handing off in sequence so a full motion (research → content → outreach → analysis) executes as one deliverable with shared context.
From $79 a month after the free 14 days, agents included. Every plan includes every feature.
We use one analytics cookie (Google Analytics) to understand aggregate usage. Details.