Docs / Use cases

GTM

The GTM stack turns one sentence about what you sell into a running outbound pipeline: your AI teammates map your market's language, watch LinkedIn for live buying signals, verify emails, write in your voice, and send through your own inboxes — with every outbound step waiting on your approval. This page explains each tool in the chain and how they hand work to each other.

The pipeline at a glance

Map · learn your market's words Find · signal leads + engagers Enrich · verified emails + context Draft · judged, personal emails
↓
Send · your Smartlead, gated launches Reply · approval-gated responses Learn · outcomes tune everything upstream

Cloud superpowers do the finding, enriching, and writing (flat credits per run); free local skills do the sending and replying on your own keys. Replies and booked meetings flow back and sharpen the targeting and the copy.

Set up from the Marketplace

Everything below comes from the Marketplace in the desktop app. Two kinds of capability, two verbs:

  • Cloud tools — Activate. Hosted superpowers (ICP Mapper, Intent Leads, Lead Enricher, Email Drafter, …). Activating adds them to your agent; each run costs its flat, published credit price.
  • Local skills — Install. Free packages that run on your own machine with your own keys (Campaign Runner, Campaign Responder, Campaign Stats — your Smartlead key stays with you).
Your agent restarts after each activate or install — that's normal. It picks up the new capability on the way back up; give it a moment and it resumes where it left off.

Find buyers

Two sourcing engines, one shared map of your market.

ICP MapperStart here, once per offer. Give it 1–3 sentences on what you sell and who it's for; it probes 40–80 buyer phrasings against live LinkedIn, measures which ones your real buyers actually use, and hands back a refined ICP, a measured weekly supply estimate, and a map the other tools pull from. Re-running the same offer refreshes the map — it appreciates with use.
Intent LeadsPull up to 500 qualified leads from your map per run. It harvests fresh posts from the map's proven phrasings, scores every author 1–10 against your ICP with the reasoning written out, and delivers a ranked CSV. Nothing older than a month is ever included — and each run only returns people never delivered to you before, so running again tomorrow harvests the new day's signals.
Engagement MinerThe second population: the people commenting and reacting on high-signal posts — 10–50x more people than the posters themselves, mostly untouched by outbound. Seed it with pain-topic posts, your map, or a topic; it scores every engager and returns their own verbatim comment as the personalization hook.

Enrich

Lead EnricherTurns a lead list into outreach-ready records: a verified work email (two-provider waterfall + live SMTP verification into an email confidence grade), the person's recent posts verbatim, an AI summary of their company, and ready-to-use personalization hooks. Only high/medium-confidence emails ever reach a send — low-confidence addresses would bounce and burn your domain, so the pipeline drops them automatically. A bulk tier handles bigger batches at a better per-lead price.

Write

Email DrafterWrites a personalized, reply-optimized sequence per lead — every draft is scored by an editor-judge on eight reply-driving dimensions and revised until it clears the bar. By default it drafts with your proven offer (the one with real reply history); unproven offers on big batches are blocked unless you explicitly opt into the test. Supports A/B variants and 1–4 step sequences, and its output is ready to hand straight to Campaign Runner.
Viral ScoutFinds who's going viral on LinkedIn about your topic right now, keeps only posts whose structure earned the performance, and returns a ready style handoff for Ghostwriter.
GhostwriterDrafts your next LinkedIn post in your exact voice, learned from your last ~15 real posts — optionally in the proven structure of a creator Viral Scout surfaced. Your content, their mechanics, never impersonation.
Post HistoryPulls anyone's last N LinkedIn posts verbatim with computed stats — the grounding for content strategy or pre-call prep.
Brief RoomDeep AI research briefs on a founder — background, company, signals — delivered as a PDF. The pre-meeting superpower.

Send, reply, learn — the free local skills

These run on your machine with your own keys (Smartlead), so your sending identity never leaves your hands. They're free — no credits.

Campaign RunnerFull campaign ops through your own Smartlead account: create campaigns, upload deduped leads (with the email-confidence gate), set the drafted sequence, schedule, and launch behind preflight checks — plus health monitoring with auto-pause on bounce spikes, A/B stats and promote-winner, and sync-contacted, which pushes everyone you've contacted into the cloud suppression list so no tool ever re-targets them.
Campaign ResponderThe reply desk: detects new replies (filters auto-replies/OOO), classifies intent, drafts in-thread responses behind a mandatory approval gate, records booked meetings, nudges stalled threads, and handles unsubscribes as permanent do-not-contact across every layer.
Campaign StatsOne clean funnel table across all campaigns — sent, opens, replies, booked meetings, bounces, every rate — with the ICP and offer that produced each.
✦ The learning loop: Campaign Runner's learn harvests every reply, sentiment, and booked meeting, and feeds them back upstream — the Drafter's style profile learns what your audience answers, and the map learns which phrasings produce repliers vs. dead ends. The system gets sharper with every campaign you run.

Guardrails

  • Nothing sends without you. Drafts wait for approval; replies wait for approval; launches pass preflight checks first.
  • Suppression is permanent and server-side. Anyone who opted out or was already contacted is excluded from every future pull, enrichment, and draft — enforced in the cloud, not by agent memory.
  • Deliverability is protected by default. Low-confidence emails never send, bounce history is remembered forever, and campaign health auto-pauses at bounce spikes.

Credits & billing

Each cloud superpower has a flat, published per-run price in the Superpower catalog — one run, one price, regardless of how much work it did. A failed run is refunded automatically. Watch every debit and refund as a line item in your dashboard's wallet activity. The local skills (Runner, Responder, Stats) are free.

Say it to your agent

You don't call these tools directly — you ask your Stand, in the room, in plain language:

# gtm
# day one → "Map my ICP: we sell bookkeeping automation to e-commerce founders." → "Pull 250 qualified leads from my map." # same afternoon → "Enrich the top 100 and draft a 3-step sequence in my voice." → "Set it up in my Smartlead and show me the preflight before launch." # every morning after → "Any new replies? Draft responses for my approval." → "How are the campaigns doing — and what did we learn?"