Weekly CSM book-of-business digest

Create a weekly account digest for each CSM with risks, expansion signals, product adoption, and customers needing outreach.

Updated · published

markdown for agents →

difficulty intermediate · time to value 10 minutes · execution human review required

Start from this

Create a weekly CSM book-of-business digest: at-risk accounts, expansion signals, product adoption changes, and suggested outreach for each CSM.

Why this matters

CSMs operate from notes, Slack, and stale dashboards. A book-of-business digest gives them a prioritized list every week without a BI analyst.

What you get

  • Accounts needing outreach
  • Expansion and champion signals
  • Usage drops and support friction
  • Suggested next action per account

Walk through it

You

Build this week’s digest for each CSM.

Agent

I’ll group account signals by CSM owner and write short action briefs.

Endpoint: POST /v1/projects/:project_id/analytics/query
Exact shape: /v1/openapi.json?path=%2Fv1%2Fprojects%2F%7Bproject_id%7D%2Fanalytics%2Fquery&method=post
Custom HogQL goes in the OpenAPI-defined `query` field.
Concept fields:
  query: "SELECT properties.csm_owner AS csm, properties.account_id AS account, count() AS events_7d, max(timestamp) AS last_seen FROM events WHERE timestamp > now() - INTERVAL 7 DAY AND properties.account_id IS NOT NULL GROUP BY csm, account ORDER BY csm, events_7d DESC"

The output

The agent returns one digest per CSM with high-signal bullets. It should avoid flooding the CSM with healthy accounts unless there is an expansion opportunity.

Setting it up

Emit account snapshot or usage events with account_id and csm_owner. Provide each CSM’s preferred brief format in the interactive prompt or keep it in your team’s existing reviewed configuration; do not rely on undocumented agent-local state.

This query exposes account-level activity and uses owner-authenticated custom analytics, so run it in a human-controlled session. A runner cannot receive raw accounts or generic HogQL, and this page does not grant authority to contact customers. The reviewer chooses what to share and with whom.

Variations

  • “Only show accounts with a health score drop.”
  • “Create a version for the VP CS.”
  • “Prepare this for the latest seven-day window and let the CSM review it before choosing any recipients.”

Adapt this workflow in your own agent.

Ask your agent to map the starter prompt to your saved signal map, live events, and the current HTTP API before answering.

Agentry gives coding agents production context from errors, product analytics, and deploys through one HTTP API. Fetch and read https://agentry.sh/install.md completely, then install Agentry's full first-time telemetry baseline in this repository. I authorize device-code login, saving the owner key only to ~/.agentry/credentials.json, creating one Agentry project for this repository, and read-only inspection of shipped source plus hidden CI/provider configuration. Deeply analyze the product's business logic and complete value flow before choosing telemetry. Save the complete source-backed plan and show me its exact contents and hash. Until I explicitly approve that plan or request a replacement, do not edit app/CI source, place runtime/CI credentials, commit, exercise product traffic, start proof, push, or deploy. After approval, I authorize only the reviewed targets: place the required scoped browser/server/CI credentials through the established environment or secret mechanism, preserve existing telemetry, implement and test the baseline, commit it, push that reviewed commit when the shipped CI/provider path requires it, exercise safe proof paths with test/non-customer data, and perform one deployment through the reviewed shipped CI/provider path. Ask first if proof would charge money, contact a third party, change real customer data, or require new external access. After the plan is saved, immediately before every onboarding state-changing POST, GET current onboarding state, perform only its single returned next_action, then read state again; do not batch or infer later stages. Continue until status is verified, installation_complete is true, and next_action is null. Keep all secrets, source snapshots, proof markers, and scratch files outside the repository.

+ Full access
5.5 Extra High
  1. 1. Open your repo in Codex, Claude Code, Cursor etc.
  2. 2. Paste the install prompt.
  3. 3. Your agent reads the install doc and shows you an implementation plan for approval.