cargo-quickstart

Cargo Quickstart — first value in two minutes

One guided demo: pull ~25 fresh leads matching a buyer persona the user picks, show the cost receipt, then save the pull as a recurring play. The point is not the list — it's that in minute 3 the user owns a running system, not a one-off result.

A new account starts with 100 free credits — no card. This demo spends about 5 of them. Say that out loud before the first paid call ("this costs about 5 of your 100 free credits"): it converts the moment from a purchase decision into a look around, which is the whole job of a quickstart. Never let a new user think the demo is why they'd run out.

Bootstrap

Already signed in (cargo-ai whoami returns a workspace)? Skip to the next section.

npm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`
cargo-ai login --email [email protected]  # emailed code, no browser; creates the account on first use
                                        # alternatives: --oauth (browser) · --agentid (an agent as itself) · --token <api-token> (CI)
cargo-ai whoami                         # confirm the active workspace before any write

Not ready to sign up? Two things work with no account, free: browse the catalog (cargo-ai orchestration action list enrich company) and dry-run an action (cargo-ai orchestration action execute --action '<from action list>' --data '{"domain":"example.com"}' --dry-run — validates the inputs, shows sample output in the real shape and the credit price, calls nothing). Offer it once if the user hesitates at the email step; don't detour a user who is ready — the demo is the real thing.

A first sign-in lands in a new workspace named Personal; pass --workspace-name "<Company> GTM" to the login that creates the account and it renames that one (within 10 minutes, while you're its only member) instead of making a second. Starter connectors and agents seed in the background, so an empty-looking workspace a minute after sign-up may still be filling in — that is not a reason to stop.

Every command prints JSON to stdout; failures exit non-zero and print {"error": "...", "status": ..., "body": {...}} to stderr. Anything that creates a run or a batch is async — pass --wait-until-finished or poll the matching get. When the full skill bundle is installed, ../cargo/references/prerequisites.md adds the CLI version pin, token scopes, and the admin-only surface.

The one question

Ask exactly one question before doing anything:

"Who do you sell to?" (a persona in a few words — e.g. "Heads of RevOps at mid-market SaaS")

Everything else — provider, filters, limits — you decide. Don't ask about output format, volume, or providers; defaults below.

Speed budget — HARD RULES

The demo has a two-minute budget from answer to deliverable. On the fast path:

• No discovery detours. Do not run cargo-ai --version, cargo-ai whoami, connection connector list, or any exploratory command first. Auth problems will surface as errors on the first real call — handle them then.
• One command block per step, no narration between commands.
• Paid work is capped at ~5 credits total. The demo uses LinkedIn-native people search (salesNavigator.searchLeads, 0.2/record → 25 records ≈ 5 credits). Nothing else paid runs without asking.
• Never dead-end. Every step has a fallback (ladder below). If a rung fails, drop one rung silently and keep moving.

Fast path

Translate the persona into a searchLeads filter (quote the exact title phrase in keywords; a bare keyword matches loosely and pollutes the page) and run:

# 1. Execute — returns a run object; note run.uuid and run.workflowUuid.
#    searchLeads bills 0.2 per returned lead, so limit 25 costs at most 5 credits.
cargo-ai orchestration action execute \
  --action '{"kind":"connector","integrationSlug":"salesNavigator","actionSlug":"searchLeads"}' \
  --data '{"keywords": "\"<persona title phrase>\"", "limit": 25}' \
  --wait-until-finished > /tmp/quickstart-run.json

# 2. Fetch the output data (NOT in the execute stdout) — signed URL, then filter to THIS run
RUN_UUID=$(jq -r '.run.uuid' /tmp/quickstart-run.json)
WF_UUID=$(jq -r '.run.workflowUuid' /tmp/quickstart-run.json)
curl -s "$(cargo-ai orchestration run download-outputs \
  --workflow-uuid "$WF_UUID" --output-node-slug action --format json | jq -r '.url')" \
  > /tmp/quickstart-outputs.json

# 3. Show the table (the file holds ALL of the workflow's runs — filter by _uuid;
#    each row's .output is the leads array directly, fields are snake_case)
jq -r --arg u "$RUN_UUID" \
  '[.[] | select(._uuid==$u)][0].output[] | [.full_name, .job_title, .company_name, (.recently_hired // false)] | @tsv' \
  /tmp/quickstart-outputs.json | head -25

Show the table (name · title · company · recently-hired), not the raw JSON. recently_hired: true rows are the demo's headline — lead with them ("6 of these 25 just started the job — the exact moment to reach out").

Fallback ladder (on auth/error, drop a rung — don't stop)

1. salesNavigator.searchLeads (0.2/record) — primary.
2. theirStack.searchJobs (0.5/record) — reframe as "companies hiring your persona right now" (job postings for the persona's title). Same wow, different angle.
3. waterfall.searchProspects (3/record) — exceeds the ~5-credit demo cap, so this rung asks first: "The two cheap sources aren't connected; I can pull 5 matches via waterfall for ~15 credits instead — run it, or connect Sales Navigator first (free)?" Run only on an explicit yes, with limit capped at 5.
4. Nothing connected at all → run the free path: cargo-ai connection integration list | head, show what could be wired, and offer to connect one (browser auth) — the demo resumes after.

The receipt (mandatory, verbatim discipline)

The demo is itself the pilot from ../cargo-gtm/references/cost-discipline.md. Close it with a receipt:

• Credits spent + balance remaining (cargo-ai billing subscription get — remaining = subscriptionAvailableCreditsCount + additionalAvailableCreditsCount − subscriptionCreditsUsedCount on .subscription). For a brand-new account, frame it against the 100 free starting credits rather than as a bare number — "5 spent, 95 of your 100 free credits left" lands very differently from "95 credits remaining".
• Hit-rate: "25 of 25 returned" (or what actually came back, and which rows look off).

Minute 3 — save it as a play

Immediately offer to make the pull recurring — this is the step that shows what Cargo is:

"Want this to run by itself? I can save this exact search as a play that runs weekly and writes new matches into a model — new <persona> leads land without you asking."

On yes, follow ../cargo-gtm/recipes/save-as-play.md with the demo's action + filter as the workflow body and a weekly cron.

After the demo — route onward

Propose 2–3 next steps grounded in the rows just pulled, per the next-step spec in ../cargo-gtm/SKILL.md (§4): e.g. "enrich these 25 with firmographics (~0.5 cr each)", "find + verify emails for the best 10 (~1.4 cr each)", or something else entirely. From here, real GTM work belongs to cargo-gtm — read it before anything beyond the demo.