Deepline

• ▸One API and one bill across 108+ GTM data providers (Apollo, Crustdata, PDL, Hunter, LeadMagic, Apify, Exa, Firecrawl, and others)
• ▸Waterfall routing for enrichment tasks that falls back across providers. Managed waterfalls may pass through attempted-lookup costs; a successful match is not required for every charge.
• ▸Native Claude Code / Codex / Cursor agent skills and a `deepline` CLI, positioned as the primary interface (docs explicitly say to prefer the CLI over MCP)
• ▸Managed PostgreSQL database, owned by the customer, that every enrichment run writes to and that can be queried directly
• ▸"Plays": multi-step GTM workflow templates (job-change alerts, lead scoring, outbound personalization, ad intelligence) composed from smaller waterfall tasks
• ▸Bring-your-own-key mode (pay providers directly, no Deepline markup) alongside a managed billing mode with pre-run cost estimates

Authentication

API key (Bearer token) via `Authorization: Bearer <DEEPLINE_API_KEY>` header; workspace SAML SSO available (Okta, Google Workspace, Microsoft Entra) for account-level access

Base URL

https://code.deepline.com/api/v2/

Notable endpoints

• POST /integrations/{toolId}/execute - execute a specific provider tool
• POST /integrations/execute - legacy/deprecated execute endpoint
• POST /plays/run - start a multi-step workflow run
• GET /plays/run/{workflowId} - poll workflow run status

MCP tools exposed

search_deeplinequery_docs_filesystem_deeplinesubmit_feedback

Machine-readable spec

No OpenAPI link

Published by the vendor themselves — not community forks.

• gtm-eng-skills47 stars

  10 AI agent skills for Claude Code covering waterfall email enrichment, TAM building, signal discovery, job-change detection, and outbound automation, powered by the Deepline CLI. Hosted under Deepline's own GitHub org (getaero-io) but reads as a community-toned reference implementation rather than a first-party product release.

• deepline-gtm-agent23 stars

  Open-source GTM chat agent built on Deepline's v2 API, with web chat, REST, and Slack interfaces. Hosted under Deepline's GitHub org; the README frames it as a thin broker on top of Deepline's own backend for provider routing and billing.

• deepline-plugins1 stars

  Deepline GTM skills and CLI packaged as a Claude Code / Claude Cowork plugin.

Getting Started with Deepline: Go-to-Market Data in Claude Code — Deepline

Checked 2026-07-30 against their pricing page. Vendors change pricing without notice.

Deepline (legal entity Aero AI Labs, Inc., New York, founded 2024) is infrastructure for GTM engineers who build prospecting and enrichment pipelines from inside an AI coding agent rather than a no-code canvas. Instead of wiring up individual provider SDKs, a workflow calls a Deepline waterfall tool and Deepline handles provider selection, retries, deduplication, and cost tracking, logging results to a customer-owned Postgres database. The vendor positions it as a programmatic, agent-native alternative to visual table workflows. This research did not independently verify competing products' API availability.

GTM engineers, RevOps teams, and B2B operators running outbound, ABM, or CRM-hygiene workflows through Claude Code, Codex, or Cursor who need verified contact data at scale (100+ contacts) across 3+ providers and want one CLI/API instead of stitching together multiple provider SDKs.

Deepline's own agent-facing docs (llms.txt) list explicit non-use-cases: transactional email sending, using it as a system-of-record CRM, real-time email validation inside a checkout flow, single-provider lookups when a team has already standardized on one provider, audience builds over 1M rows, and consumer/B2C email finding. It is also a CLI/API-first product with no visible no-code canvas, so teams without an engineer or an AI coding agent in the loop, or teams wanting a point-and-click UI like Clay's, are a poor fit.

Tools that let a revenue team compose several data providers into one workflow, run it conditionally across a list of accounts or people, and push the result into a CRM or sequencer. The unit of work is a table or a pipeline, not a single lookup.

Category: GTM data orchestration. Membership is decided by 4 stated tests, not by category tags — see them and the full comparison.

CargoPipeline-shaped rather than table-shaped, and aimed at the engineer who would otherwise build the orchestration in-house.ClayTable-first workflow for orchestrating enrichment providers, AI research and activation steps.FloqerAPIMCPLeads with CRM enrichment and buying-signal monitoring rather than with list building.FreckleRuns GTM workflows from a CLI instead of a grid, aimed at teams that prefer scripted workflows.OctaveFocused on turning enriched context into positioning and messaging rather than on the enrichment itself.PersanaTable-first enrichment workflow with AI agents layered on a waterfall data model.Acquired — standalone future uncertain. Joining forces with Rox, per Persana's own site. Rox is also in this set, so these two can no longer be weighed as fully independent options.RoxAgent-driven revenue automation covering qualification and deal work, not just data assembly.UnifyBundles intent signals and outbound sending with the enrichment, so it competes as a whole motion rather than as a data layer.ZoomInfo GTM AIThe incumbent data vendor's own orchestration layer, with ZoomInfo's database as the default source rather than a bring-your-own waterfall.

• Pricing and developer comparison checked 2026-09-19. Billing terms and the Clay developer comparison were corrected from current official sources. The original full-profile research date still applies to other fields.
• An official X/Twitter account
• Published rate limits for the REST API
• A genuine product-specific OpenAPI/Swagger document (the linked openapi.json is Mintlify's generic sample spec)
• SOC 2 report itself (available to customers under NDA only, not publicly retrievable)
• A machine-readable OpenAPI specification was not included in the reviewed source set.