State: to-be-approved. Deploy-verified against a live workspace: not yet. Treat Done when
below as the acceptance test and review cargo-ai cdk plan before deploying. Make no outcome claim
for this cookbook until cookbook.json says approved.
The outcome
Every account scored against your ICP, tiered, and written back to the CRM with the rationale, so a rep can always see why an account is tier A. The criteria are not point weights in code: they are the ICP markdown in your context repo, versioned in git and shared with every other agent. Edit the ICP and accounts re-score against it as they come due.
The procedure lives in deploy-cookbook
npx skills add getcargohq/cargo-cookbooks/deploy-cookbook # if it is not already in this session
cargo-ai cdk init my-scoring --from getcargohq/cargo-cookbooks/account-scoring
That pulls base-gtm, crm-sync and gtm-knowledge-graph with it. Read README.md in this
folder first, including the deterministic variant at the bottom if you want zero-LLM scoring.
What you will be asked
Four inputs, in cookbook.json. The first one is the whole cookbook.
| Input | Derived, or asked | Why it matters |
|---|---|---|
icp |
asked, or proposed from closed-won vs closed-lost data if the workspace has it | The criteria ARE the prompt. Name the disqualifiers, not only the fit signals: they are what caps a bad account at 20. |
languageModel |
derived from the authenticated LLM connector | Scoring quality and per-account cost both live here. |
crmScoreProperties |
checked, not written | cargo_score, cargo_tier, cargo_rationale, cargo_last_updated_at must exist on the CRM account object first. |
tierThresholds |
asked | The agent emits A, B and C. The shipped segments cover A and C only. |
Two failure modes worth knowing before you start. If the CRM properties do not exist, the run
looks successful and the scores land nowhere, which wastes the whole batch. And cargo_score plus
cargo_tier must be selected as columns on the accounts model, or the tier segments filter on a
column they cannot see.
Done when
- A test account run shows the agent's lookups in the trace, not a score guessed from the domain.
- The CRM record carries a score with a rationale citing real evidence and named ICP criteria.
- The evaluator scores at least 0.8.
- After the next model refresh the account appears in the matching tier segment.
What it costs
One LLM call plus up to two Cargo database calls (matchBusiness,
enrichBusinessFirmographics) per account, on arrival and again on the weekly sweep of accounts
last scored three or more months ago. It scales with accounts in the model times re-scores, so a
TAM built by tam-building scores at that size. Score a sample before the book.
Composes into
routing-engine (territories and capacity over the scored book), rep-cockpit, ai-sdr.