LangChain's GTM Agent: deals with agent-built sales docs advance 47% vs 16%
LangChain · x · 2026-11-18
LangChain published a detailed blog on its internal GTM Agent for sales artifacts. In 12 weeks it generated 1,540 artifacts (account plans, proof-of-value docs, proposal decks, onboarding plans); deals where reps sent one advanced to a later stage 47% of the time vs 16% for matched deals without one, 46% of sends led to a customer call within 14 days, and reps saved 337 hours.
Key lessons:
- Quality came mostly from context around the model, not prompt tuning: sales leadership's taste, real customer call content, business logic like sales stages, and concrete stage-advancement criteria
- Because the agent knows each deal's stage, it suggests the right document before customer calls
- The workflow can be replicated on the Deep Agents harness; Managed Deep Agents ships the required sandbox, skills, and memory
Related event: LangChain's GTM Agent Lifts Deal Progression to 47%(2 posts)→
More from coding & agent
- Sarvam AI launches Token Factory with voice agents MCP integration — itsOmSarraf_ · 2026-11-18
- Cognition launches Devin Bots; Bryan Johnson uses them to ingest billions of health data points — marvinvonhagen · 2026-11-18
- AI supercharges formal verification: Anthropic proves 239 entry points never crash with 180M-line proofs — kfountou · 2026-11-18
- aivoicebus 0.16.0 adds Grok Bot to its AI agent fleet via webhook — baditaflorin · 2026-11-18
- Microsoft Ignite: Windows endpoint security GA, Agent 365, Hybrid Intelligence — pavandavuluri · 2026-11-18
- deadweight: a Rust CLI that measures wasted tokens in your Claude Code setup — JeremyCMorgan · 2026-11-18