Office hours: Build your self-driving GTM engine·Oct 29, 9:00am PT, onlineRegister→
Cargo
  • PrimitivesData ModelsYour companies, contacts and deals, merged from every sourceContextWhat your team knows, as files every agent readsTerritoriesWho sells where, defined onceMailboxesMailboxes in your reps' names, warmed up and kept under limitsToolsThe actions your agents, plays and reps callAgentsAI that researches, decides and writes, reading your contextPlaysWorkflows that run on a trigger or a schedule, with retriesAppsInternal apps for your reps, hosted on Cargo
    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 workGitHubPlan on every pull request, deploy on merge
    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
Cookbooks
WLContext

Win loss review

Run a monthly win-loss review of your CRM's closed deals, landed in context/ as one pull request: the ICP verified against won versus lost with a disqualifier, dated insights with counts and denominators, objections from recorded lost reasons, and a client file per closed-won account; a five-line Slack digest says what changed. Never edits a persona, nor the ICP after the first pass.

Installation
Set up the win-loss-review cookbook in this project. 1. If the Cargo CLI is not installed yet, follow every step in https://api.getcargo.io/INSTALL.md 2. From the Cargo project, run: cargo-ai project add cookbook/win-loss-review 3. Then follow .claude/skills/win-loss-review/SKILL.md. Stop for my approval before any paid call, and stop at "cargo-ai project plan" before deploying anything.
Paste it into Claude Code, Cursor, Codex, Gemini CLI, Devin or Replicas.
$cargo-ai project add cookbook/win-loss-review
Run it in your Cargo project. Copies the example in, and deploys nothing.

Say this to your agent

Every month, read what our HubSpot won and lost deals say, verify the ICP, and post the digest to #gtm-context.

Illustrative output #

Fictional records, to show the shape of what comes back.

text
:bar_chart: *Win-loss review Oct 2026*: 23 deals closed
Won 9, lost 14 · lost reason on 11 of 14 · contacts on 19 of 23
Learned: a RevOps title at 6 of 9 won accounts · 8 of 14 losses were under 50 employees · "no budget this quarter" on 5 of 11 reasons
Proposed: add "under 50 employees" as an ICP disqualifier (8 of 14 losses, 0 of 9 wins), in the PR body
PR: https://github.com/northwind/gtm/pull/331

The pull request adds four dated insight/ files, two objection/ files and nine client/ files, and modifies nothing under icp/ or persona/; the disqualifier waits for a human.

What you will be asked #

InputWhy
icp/, insight/, objection/, client/Looked upThe disqualifier is the half of an ICP that protects the team’s time, and won versus lost is the only place it comes from with evidence

Done when #

  • the models synced, and the pipelines query returned non-zero won and lost counts
  • cargo-ai project check prints the agent bound to the repository root, and cargo-ai project plan reports one agent, the models, the bound connectors and two folders
  • the first pass opened one pull request whose body opens with the two hygiene findings with denominators, then the mode and the won count that set it
  • outputs/<date>-win-loss-review/README.md holds every query’s result, with no amount and no email
  • icp/ carries a disqualifier derived from won versus lost, as a new file or as one dated section appended to the seeded one
  • insight/ holds dated files in the three buckets with counts and denominators, and every title at a won account is mapped to a persona or listed as undetected
  • with the fill rate under half, no objection/ file exists and the body says why; at or above it, every objection cites two or more deals by id
  • every client/ file carries reference_permission: unknown and no amount
  • nothing under persona/ changed, and any proposed change is in the pull request body with deal ids
  • the Slack digest is five lines, its numbers match the run record, and the last line is the pull request link
  • a monthly run with new deals opened a pull request that adds files and modifies none under icp/ or persona/; with none it opened no pull request and the digest said so
  • after merging and cargo-ai project deploy, the verified ICP section is readable from the workspace context repository and an agent with the context capability quotes it back with its tag

What it costs #

CRM extraction bills no credits, and neither do the SQL queries. The recurring cost is one harness run a month, scaling with how many deals closed since the previous one, plus the first pass over the whole window. Confirm the extraction price for the workspace’s CRM with cargo-ai connection integration get hubspot before the first deploy.

To learn who you should and should not sell to, audit your CRM’s closed deals against each other: won versus lost by industry, size and country, and the lost reasons recorded on them. Once a month this cookbook has a Claude Code harness agent run fixed SQL over the CRM extracted into Cargo models, and lands the ICP check, dated insights and objections in context/ as one pull request, with a five-line Slack digest.

shellscript
cargo-ai project add cookbook/win-loss-review

What it does #

  • Extracts the CRM into models, whole. crm_deals, crm_accounts and crm_contacts: every record, every column, no filter in the config. Extraction bills no credits, and the last two are the same models crm-enrichment and crm-deduplication declare.
  • Audits with fixed SQL. The prompt carries the queries: counts by pipeline, lost reasons, contacts on deals, won versus lost by industry, size and country, titles at won accounts, and the deals since the last run. The agent runs those and no other.
  • States the hygiene findings. The lost-reason fill rate and the deal-to-contact rate open every pull request, with their denominators, and decide what can be written.
  • Writes, then appends. The first pass verifies icp/ (one dated section if it is seeded) and writes insight/, objection/ and client/. Every month after adds files and edits none. Personas are never edited; changes are proposals in the pull request body.
  • Records the run. outputs/<date>-win-loss-review/README.md holds each query’s result, which every [R: <query>] tag points to.

Resources #

FileResourceRole
infra/agents/win-loss-analyst.tsdefineAgent (claudeCode)monthly cron, locked Slack channel, no env
infra/agents/win-loss-analyst.prompt.ts(not a resource)the audit’s SQL, the first pass, the monthly append, the digest
infra/models/crm-deals.tsdefineModel (crm_deals)every deal, all columns; the queries narrow to closed
infra/models/crm-accounts.tsdefineModel (crm_accounts)the accounts behind the deals, shared with the other CRM cookbooks
infra/models/crm-contacts.tsdefineModel (crm_contacts)the people at the accounts, shared with the other CRM cookbooks
infra/connectors/crm.tsdefineConnector (hubspot)the CRM the models extract, bound
infra/connectors/anthropic.tsdefineConnector (anthropic)the model the harness runs on, billed and metered
infra/connectors/git.tsdefineConnector (github)the clone, branch, push and PR path, resolved by binding
infra/connectors/slack.tsdefineConnector (slack)the digest, through a locked postMessage
infra/folders/index.tsdefineFolder ×2the agent and the models, filed under the cookbook

Why models, not a script #

The audit is counts and joins, which is what SQL is for. A collector that pages through CRM search results re-implements pagination, filters and aggregation per CRM, and every one of those is a place to return part of the window as if it were all of it. Models leave extraction to the platform, keep the raw deals in Cargo storage rather than in the repository, and are shared: a project that already runs crm-enrichment or crm-deduplication extracts its accounts and contacts once.

Why one source #

A cookbook is a prebuilt approach an agent follows. Give it two kinds of evidence, a page and a deal, and it has to hold two confidence levels in one run and the reader has to tell them apart afterwards. So this cookbook holds one: the CRM. The website has web-capture, which seeds what this one verifies; calls have call-capture.

Placeholders (edit before deploy) #

  1. languageModel on the agent, and the Slack channelId on its postMessage use.
  2. The lost-reason property, as LOST_REASON_COLUMN in the prompt, when the portal records it on a custom property.

What it does not do #

It does not read a call, an inbox or a website; run SQL beyond its own queries; write to the CRM; select or write a deal amount; write the workspace context directly; edit a persona, or the ICP after the first pass; or merge its own pull request.

Verify #

From this skill’s folder:

shellscript
node --import tsx evals/contract.mjs

From the project root:

shellscript
npm run check && cargo-ai project plan
Version0.2.0
LicenseMIT
Source
Deploys
  • agents
  • connectors
  • models
For
  • RevOps
  • Sales leadership
  • GTM engineering
Integrations
  • Anthropic
  • GitHub
  • HubSpot
  • Slack
Content
  • Say this to your agent
  • Illustrative output
  • What you will be asked
  • Done when
  • What it costs
  • What it does
  • Resources
  • Why models, not a script
  • Why one source
  • Placeholders (edit before deploy)
  • What it does not do
  • Verify
More in Context
  • Call capture
  • Web capture
Next: Fundamentals
  • TAM building
  • TAM building advanced
  • Account scoring
  • Contact sourcing
  • Website building
  • Website auditing

Build the self-driving GTM engine

Your coding agents build it on Cargo.Or our team builds, operates and improves it with you.

Start building
Cargo
Backed byY CombinatorSOC 2 Type IICertified
LinkedinX

Product

Data ModelsContextTerritoriesMailboxesToolsAI AgentsPlaysAppsIntegrationsPricing

Add-ons

Chrome extensionButtonFormSlackGitHub

Build

DocsDeveloper resourcesCargo API docsCargo OpenAPI specCargo auth docsCargo webhooksCargo MCP serverProjectsClaude CodeCodexCursorAll coding agents

Resources

ReportsBlogCustomer storiesCookbooksEnrichmentRoutingSignalsScoringCRM hygieneAd audiencesGTM skillsGTM EngineeringGlossaryCompareCargo x ClayCargo x WorkatoCargo x n8nCargo x DeeplineCargo x DefaultCargo x LeanDataCargo x UnifyCargo x ValleyCargo x GojiberryCargo x PhantomBusterCargo x ZapierCargo x ApolloCargo x Chili PiperCargo x Common RoomCargo x MakeCargo x Tray.io

Company

ManifestoCommunityEventsJobsPartners DirectoryPartner Program

Legal

SecurityTerms of servicePrivacy PolicyRefundsDPASupport
© 2026 Cargo
 ////////    ///////    ////////     ////////    ///////
///         ///   ///   ///   ///   ///         ///   ///
///         ///   ///   ///   ///   ///         ///   ///
///         /////////   ////////    ///  ////   ///   ///
///         ///   ///   /// ///     ///   ///   ///   ///
///         ///   ///   ///  ///    ///   ///   ///   ///
 ////////   ///   ///   ///   ///    ///////     ///////

$ npm install -g @cargo-ai/cli