Stalled deal nudge

Illustrative output #

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

:hourglass: *Stalled deals · Dana Ruiz · 2026-W41*
_2 open deals with no logged activity in 14+ days._

*Fabrikam — Platform* — Proposal, $64,000, closes Oct 31 · quiet 19 days, flagged 1 Monday running
Last: Sep 17 "Send the security questionnaire and we'll take it to procurement."
Why now: The close date is three weeks out and the questionnaire that unblocks procurement never went.
Draft: > Hi Lee, attaching the completed security questionnaire you asked for on the 17th.
       > If procurement needs anything else to keep the Oct 31 date, send it my way today.

*Northwind — Expansion* — Discovery, $22,000, closes Nov 20 · quiet 16 days
Last: Sep 20 "Let's regroup once the Q4 budget is set."
Why now: Q4 budgets were due Oct 1, so the regroup they asked for is now.
Draft: > Hi Priya, you mentioned regrouping once Q4 budget was set. Is this week good?

Five owners had stalled deals, so five digests landed and eleven rows were added to deal_nudges; a second run that Monday posted nothing.

What you will be asked #

Done when #

• node --import tsx evals/contract.mjs passes
• cargo-ai cdk plan reports the agent, the gtm_opportunities, gtm_accounts, gtm_activities and deal_nudges models, the two connectors and the two folders
• the hand-run selection returned only open deals whose latest activity is older than QUIET_DAYS
• the first run posted exactly one digest per owner with stalled deals, in the references/digest.md shape, and wrote one deal_nudges row per deal with the digest’s Slack ts
• a second run the same Monday, once the first run’s ledger rows read back through SQL, posted nothing and added no row
• every Last: quote exists in the gtm_activities row it came from, with that date
• no draft was sent and no deal, account or activity row changed

What it costs #

There is no enrichment provider, no CRM connector and no per-record fan-out: the selection and the last-activity reads are SQL over the workspace’s own models. The one connector action is the Slack post. Immediately before the plan, read its live price:

• cargo-ai orchestration action list postMessage --kind connector --integration-slug slack

Say the number out loud; the run posts once per owner with stalled deals. The recurring cost is the agent run, once a week, billed as LLM tokens through the Anthropic connector. It scales with the number of stalled deals that week, and maxSteps caps it per run. A crm-backed adaptation adds the CRM extract: read its price with cargo-ai connection integration get <crm>.

One Slack digest per owner every Monday, listing their open deals with no logged activity in the last fourteen days: the line the last activity left off on, why the deal is worth a touch now, and a follow-up drafted for them to send. The example runs on Cargo native deal, account and activity models with no CRM connector; one agent selects the quiet deals in SQL, and a ledger keeps each deal to one nudge per week. With deals in HubSpot, Salesforce or Attio, the models become connector-backed and the agent stays the same.

What it does #

• Computes each open deal’s last activity in SQL, as the latest logged email, meeting, call or note.
• Each Monday, selects the open deals quiet for QUIET_DAYS or more, and drops any already nudged this ISO week.
• Reads the last note, meeting or call on each, and writes a reason and a draft grounded in it.
• Posts one digest per owner to a locked channel, then records each deal in the ledger.

What’s inside #

Adds 9 resources.

Why one agent and not a play #

The output is a digest grouped by owner, and grouping is a judgment over the whole list. A play enrolls deals one at a time and would need a second step to gather them back into one post per owner. The agent runs the selection itself, in SQL over a model that holds every deal, so the rule is one readable query in the prompt.

Placeholders (edit before deploy) #

1. channelId in infra/agents/nudger.ts: the Slack channel id the digests land in.
2. OWNERS in infra/agents/nudger.prompt.ts: owner_id to the name the digest prints.
3. QUIET_DAYS in the same file: fourteen by default.
4. The hour and timezone: the cron (UTC) and the timezone named in the trigger text.
5. languageModel: any Anthropic model the workspace’s connector can reach.

Deals in a CRM #

Swap gtm_opportunities and gtm_activities for connector-backed models that extract every record and every column, and adapt the column names in the prompt’s SQL. SKILL.md, crm-backed, maps the last activity property for HubSpot and Salesforce.

What it does not do #

It does not write to the deal models, send the drafts, message a prospect, post anywhere but the locked channel, or edit the workspace context.