GTM infrastructurefor coding agents
Make your GTM self-driving. Declare it as a repo. Cargo runs it.
Install Cargo by following https://api.getcargo.io/INSTALL.md$npx @cargo-ai/cli@latest project init my-gtm
A go-to-market that waits for people.Or one that drives itself.
Self-driving means nobody is holding it up: it runs on a trigger, retries itself, and says what it did. Most GTM stacks fail all three.
Your GTM today
- ✕Each API with its own auth and rate limits
- ✕Glue code you wrote and now maintain
- ✕Failures you find a week later
- ✕One person's laptop keeps it running
On Cargo
Notify in SlackYour coding agent can write a GTM engine.Cargo is where it runs.
Cargo is the runtime they build on. The skills say how, the CDK and the MCP server are what they write into, and the runtime is what keeps the result running after the session ends.
Your go-to-market, as a repository you own.One command starts it.
Not a workspace you log into and configure. A git repository, on your GitHub, that your coding agents read and write and Cargo deploys.
What it leaves you
- ├─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/cookbookyour account universe
- │ └─account-scoring/cookbooktiered 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
Markdown above infra/, TypeScript inside it. Reviewed in a pull request like the rest of your code.
What you run
- 1
$npx @cargo-ai/cli@latest project init my-gtmScaffolds the repo, runs git init, writes the first commit, installs the Cargo skills, and offers to create the GitHub remote. - 2
$cargo-ai project add cookbook/tam-buildingA worked example you adapt: real CDK source, plus the procedure for fitting it to your systems. - 3
$cargo-ai project deployLive. Plan the diff before it runs, and roll back to any previous state whenever you want.
Seven primitives. One system.
Everything a GTM is made of, as TypeScript in the repo above. Defined once, deployed by Cargo, used by your team and your agents alike.
Agents
Bring your own or use ours. Each has a prompt, tools, memory, and a check on its own work.
One play. Ask for it, or write it.
The same play in your repo either way: asked for in a coding agent session, or written as CDK TypeScript and deployed from the CLI. The app is there for the people who read the results, not a second place to build.
The TypeScript you write is the Cargo CDK: plan the diff, deploy, roll backCreate a play that qualifies demo requests against our ICP and assigns them to a rep.
Done. Here is the play, deployed to your workspace:
- TriggerDemo request
- QualifyAgent, against your ICP
- AssignTo a rep
Notify the team in Slack when it is a strong fit.
Added a Slack step after Assign.
Account scoring
Keep every account scored and tiered against your written ICP by a deployed agent that re-scores as accounts arrive and as the ICP changes, writing the rationale back to the CRM.
Agentic engagement
Deploy an agent that holds email conversations with leads: a sending domain, a mailbox, native sendEmail and listEmailEvents on the agent, a native email trigger on reply and unsubscribe, and a heartbeat that checks thread status when nothing inbound happened.
Call capture
Every call the team records is collected into the cadence layer each morning, scribed into a log entry, and — once a claim repeats — promoted into the context knowledge layer, as one reviewable pull request against your GTM repo.
CRM enrichment
Keep CRM accounts filled and refresh them when they go stale: a deployed play that fills approved blank firmographics from LinkedIn and re-enrolls a record after six months.
TAM building
Stand up your account universe as a deployed pipeline: an AI Ark company search shaped by your ICP, sized for free before it bills, then tiered A / B / C / disqualified by an agent that reads your rubric from the workspace context and web-searches the evidence the sourced row does not carry.
100+ connectors, maintained for you.
Teams build their go-to-market on Cargo
More Leads Generated
Cargo automated Descript's lead enrichment pipeline, surfacing 5x more qualified prospects from inbound signups.
CRM Enrichment Levels Achieved
Oneflow achieved 80% CRM data coverage by combining 30+ enrichment providers through a single Cargo play.
Frequently asked questions
What Cargo is, how you build on it, and how to start.
Built with Claude Code. Running on Cargo.
“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 Girard
Pivot
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.
Give your agents a runtime
Bring the agents you have.Start free, deploy in one command.