Office hours: Build your self-driving GTM engine·Oct 29, 9:00am PT, onlineRegister→
Cargo
  • ProductAgentsReduce manual effort and close more deals with AIPlaysAutomate every stage of lead management so you can move fasterToolsAutomate repetitive tasks so your team can focus on what drives impactData ModelsUnify, organize, and activate your revenue dataAppsCustom interfaces for your team, wired to your live GTMTerritoriesModel your team, territories, and capacity in one placeContextOne shared knowledge base for your team and agents
    Add-onsChrome ExtensionSell faster, right in your browserButtonTrigger AI agents inside your CRMFormTurn any tool into an embeddable formSlackTag Cargo in Slack. It does the GTM work
    MoreProjectsDefine your entire GTM in codeCLIUse Cargo from your terminalMCPUse Cargo from Claude and ChatGPTDeveloper resourcesCargo API docs, OpenAPI spec, auth docs, webhooks, MCP serverAPI ReferenceExplore the Cargo APIDocumentationLearn how to use CargoIntegrationsConnected to your entire GTM stack
  • VeriffHow Veriff replaced MuleSoft with Cargo under NetSuite, Stripe and SalesforceAugmentHow Augment Code routes developer sign-ups to reps in under an hourWeights & BiasesHow Weights & Biases ships a new purchase signal in 2 days on CargoSee all
  • Pricing
  • Cookbooks
  • Blog
Sign in

GTM infrastructurefor coding agents

AI made it easy to build GTM workflows. Cargo keeps them working: your GTM as code in your repo, a production runtime, every run traced.

Watch the five-minute walkthrough

Trusted by GTM teams at

  • <1 h to a repAugment Code
  • Signal in 2 daysWeights & Biases
  • Dust
  • WorkOS
  • Braintrust
  • 2x pipelineDescript
  • Alaan
  • Engine
  • Scaleway
  • Preply
  • DataDome
  • 80% CRM enrichedOneflow
  • 60% less eng. workGorgias
  • 1,000+ h savedAshby
  • 5x fewer API callsVeriff
  • Mooncard
  • Qobra
  • 80% less upkeepUpfluence
backed by y combinator
~/why/

Easy to build.Hard to keep working.

AI agents build a GTM workflow in an afternoon. Keeping it working is the hard part: make your GTM code, reviewed like code, and let Cargo run it.

Your GTM today

  • It depends on the one person who built it
  • It breaks when a quota, a schedule or an API changes
  • A lead goes to the wrong rep and nobody can say why
  • Glue code you wrote and now maintain
Clay
Apollo
Salesforce
Snowflake
scripts.py
HubSpot
Outreach
OpenAI
Slack
Gong
Instantly
ZoomInfo
LinkedIn
leads.csv
Intercom
vs

As code, on Cargo

  • In a repository. Every person and every agent reads the same code.
  • Cargo runs it on triggers and schedules, with retries and maintained connectors.
  • Every change is a pull request, and every run is traced.
  • Declared, not glued. Cargo deploys it and keeps it working.
my-gtm
  • ├─plan/the goal, and how it gets won
  • ├─context/ICPs, personas, objections
  • ├─initiatives/the bets, with owners and dates
  • ├─cadence/the weekly plan, the daily log
  • ├─infra/what Cargo runs
  • │ ├─context.tspublishes context/
  • │ ├─tam-building/your account universe
  • │ └─account-scoring/tiered as they arrive
  • ├─evals/what gates a prompt change
  • ├─outputs/what ran, and what came back
  • ├─AGENTS.mdhow an agent works this repo
  • └─cargo.state.jsonwhat is deployed
~/how-it-works/

Your agent writes it. You review it. Cargo runs it.

The loop every change goes through, the same one your engineers already use for code.

  1. 01

    Write

    Your coding agent writes your plays, agents and context into a repository you own.

    $cargo-ai project init my-gtm
    my-gtm/ context/ ICP, personas infra/ plays, agentsCargo skills installed
  3. 02

    Review

    Every change is a pull request with its plan, before anything runs.

    $cargo-ai project plan
    + play route-demo-requests+ agent qualify-lead~ model contacts2 to create, 1 to update
  5. 03

    Run

    Merging deploys it. Cargo runs it, retries what fails and traces every run.

    $cargo-ai project deploy
    deployed, 3 resourcesrun #1 tracedretries onrollback ready
How projects workCookbooksIntegrations
~/what-cargo-is/

Five pillars. One system.

The infrastructure coding agents need to build your revenue engine and keep it working in production. Used by your team and your agents alike.

Unified data and semantic layer

One data foundation across your GTM stack. CRM, warehouse, product and enrichment unified into companies, contacts and deals that every agent reads and writes.

About data models

Company brain

Shared business context your agents reason over: goals, ICP, personas, playbooks and policies, written down once and versioned like code.

About context

Execution and orchestration

A production runtime for enrichment, scoring and routing. Plays on triggers and schedules, tools on maintained connectors, agents, territories, with retries and rate limits handled.

About plays

Observability and governance

Every run traced through logs and spans. Roles, permissions and human review where judgment matters, so when something changes, you can say what and why.

About security

GTM as code

Your GTM logic defined, versioned and reviewed in git, so coding agents can keep building and improving it. The repo defines it. Cargo runs it.

About Cargo projects
~/built-on-cargo/

Teams build their go-to-market on Cargo

descript2x

Pipeline From Free Sign-ups

Descript runs one Cargo play over every product-led sign-up in its warehouse, and pipeline from sign-ups doubled in 6 months.

augment
gorgias
oneflow80%

CRM Enrichment Levels Achieved

Oneflow runs four sales motions on one Cargo engine and keeps its CRM 80% enriched, where large sections used to be empty or out of date.

ashby
veriff
~/from-the-field/

Built by their agents. Kept working by Cargo.

Pivot
“Most ICP models are built once and forgotten. Ours runs perpetually — every closed-won, every churn, every pattern. Cargo enriches the gaps, does the analysis, and deploys it as a skill we can call from anywhere. This is what infrastructure actually means.”
Alexis GirardAlexis Girard · Pivot
Qobra
“I've built a full BDR execution analysis in 5 minutes — Claude Code plugged straight into Cargo datasets. This is a gold mine.”
Vincent BonjeanVincent Bonjean · Qobra
“I built a meeting prep agent in one Claude Code session. It pulls Gong calls, Salesforce history, deal-won patterns, and sales activity — and generates a full brief before every meeting. My reps went from 30 minutes of prep to zero. The data was always there. It just needed infrastructure to act on it.”
Guillaume AubertGuillaume Aubert · Head of GTM Engineering
~/systems-that-improve/

Automation scales execution. Improvement compounds.

Every run teaches the next one. Three steps run on their own; the fourth is yours.

  1. Sense

    Signals and outcomes from your CRM, warehouse and product, and from every run.

    Northwind2 h ago
    new Head of RevOps

  3. Decide

    Agents reason over your company brain: who to act on, and how.

    ICP fit82 / 100
    route toDana, EMEA

  5. Act

    Plays enrich, score, route and reach out across your tools, with every run traced.

    enrich
    score
    assign
    slackretried once

  7. Improve

    Yours

    Agents propose the change as a reviewable diff. You approve, and Cargo deploys the next version.

    raise the fit threshold
    - threshold: 70
    + threshold: 75

The approved change is the next version, and the loop starts again.

~/security-compliance/

Enterprise-grade infrastructure

SOC 2 Type II certified

Audited annually by independent third parties. Controls verified across security, availability, and confidentiality.

Audit log & evals

Every run, write, and approval is recorded and exportable. Eval suites gate a prompt change before it reaches production.

Data residency

Choose where your data lives. Multi-region deployments keep you compliant with local regulations.

SSO & role-based access

SAML-based single sign-on and granular permissions so every team member sees only what they need.

Version history

Every agent, play, and workflow is versioned. Compare diffs, roll back in one click, and audit who changed what.

GDPR & trust center

DPA templates, sub-processor lists, and security documentation ready for your procurement team.

Frequently asked questions

What Cargo is, how you build on it, and how to start.

Cargo is go-to-market infrastructure for coding agents. Your coding agents build your go-to-market as code in a git repository, and Cargo keeps it working in production: one data layer, a company brain your agents read, execution that retries, and a trace of every run.
Start building if you have GTM engineers or coding agents to do the building: your agents write your go-to-market as code in a repository, and Cargo keeps it working in production. Build with us if nobody on your team will build it: our team builds, operates and continuously improves it with you, delivered as a repository you own. Both run on the same Cargo workspace, so a team that starts with us can take it over later.
One that keeps working without somebody holding it up. AI made GTM workflows easy to build; keeping them working is the hard part. They depend on the one person who built them, they break when a quota, a schedule or an API changes, and when a lead goes to the wrong rep nobody can say why. On Cargo they start on a trigger, retry when a step fails, and leave a trace of every run, declared in your repo and deployed with one command.
Run npx @cargo-ai/cli@latest project init my-gtm. It scaffolds a go-to-market repo, runs git init, writes the first commit, installs the Cargo skills, and can create the GitHub remote. Then point a coding agent at it: the same play can be asked for in Claude Code, declared in a TypeScript project, or run from the CLI.
Claude Code, Cursor, Codex, Gemini CLI, Devin and Replicas. All six read the same skills, call the same MCP server, and declare the same workspace in a TypeScript project. Cargo can also start Devin and Replicas itself, from a play or from a failed batch.
Cargo is SOC 2 Type II certified, with SSO and role-based access, data residency, audit logs, and GDPR documentation for procurement.
~/two-ways-in/

Build it yourself. Or build it with us.

Same engine, same workspace. Start with us and your team can take it over later; nobody migrates.

  • For GTM engineers and their coding agents

    Start building

    Your coding agents build it. Cargo keeps it working in production.

    • Your GTM as code, in a repository you own
    • Data, company brain and runtime, ready for your agents
    • Free credits to start, no card
    Start building
  • For teams that want it built and run

    Build with us

    Our team builds, operates and continuously improves it with you.

    • A working GTM engine, delivered as a repository you own
    • A dedicated Slack channel, onboarding and on-demand calls
    • Your engineers can take it over at any time
Cargo
Backed byY CombinatorSOC 2 Type IICertified
LinkedinX

Product

AI AgentsPlaysToolsData ModelsAppsTerritoriesContextEnrichmentRoutingIntegrationsPricing

Add-ons

Chrome extensionButtonFormSlack

Build

DocsDeveloper resourcesCargo API docsCargo OpenAPI specCargo auth docsCargo webhooksCargo MCP serverProjectsClaude Code

Resources

ReportsBlogCustomer storiesCookbooksGTM skillsGTM EngineeringGlossaryCompareCargo x ClayCargo x WorkatoCargo x n8nCargo x DeeplineCargo x DefaultCargo x LeanDataCargo x UnifyCargo x ValleyCargo x Gojiberry

Company

ManifestoCommunityEventsJobsPartners DirectoryPartner Program

Legal

SecurityTerms of servicePrivacy PolicyRefundsDPASupport
© 2026 Cargo
Cargo