Account Health
Use these checks for named customer, organization, account-health, QBR,
renewal, risk, expansion, contract-utilization, or adoption questions. This is
not an ordinary metric lookup: a wrong identity or metric definition can put
another customer's data into a customer-facing decision.
Identity lock
Treat an organization ID supplied in a prompt as a lookup key, not as proof that
the rows returned by a warehouse query belong to that customer.
- Resolve the ID through the canonical CRM or contract source first.
- Record the resolved customer name, organization ID, root organization ID,
and any canonical account key.
- Carry the same resolved identity through every usage query and check the
returned rows against it.
- Stop and report an identity mismatch if a result contains another customer,
mixed organization IDs, or an unresolved ID. Do not summarize the rows or
silently choose the most plausible customer.
Source order and completeness
- Use the catalog and organization data dictionary before writing warehouse
SQL. For contract and usage metrics, the dbt Semantic Layer
(
query-dbt-semantic-metric) is the approved definition. Approved definitions
and saved query shapes outrank a table name that merely sounds right.
- Gather available CRM, contract, support, and conversation evidence. Treat
that context as complementary, not as a complete usage result.
- For account health, product usage is mandatory: query approved definitions
for each requested product or feature dimension separately, using an explicit
window (default 90 days for adoption unless the user asks for another one).
- Report source, window, filters, row counts, identity join, freshness, and
gaps. A missing source is a gap, not a reason to fill in a plausible value.
Metric contracts
- Contract metric - distinguish the contracted measure from similarly named
platform, web, content, or event metrics. Do not use a familiar synonym when
comparing against a contract.
- Completed-month usage - “last month” excludes the current partial month.
Verify the month/as-of field and freshness before using a reporting table;
a single current-month snapshot is not last month's completed value.
- Seats - use the total distinct contracted/eligible users for the stated
period when comparing with a seat contract. Do not substitute DAU, WAU, or a
point-in-time daily active count, and label active users separately.
- Capacity usage - report actual usage, contracted capacity, and utilization.
Explicitly flag utilization at or above 100% as an overage risk and potential
renewal/expansion signal.
- Adoption - keep separate products or feature dimensions separate. Include
feature adoption, active-user/session counts, and last activity only when the
source query returns them; absence claims require complete coverage for the
stated window.
Known source traps
- If a saved query or dictionary entry is marked deprecated or retired, do not
run it; use the current approved replacement and note the stale reference.
- A source that returns only one current partial-period snapshot is not proof of
a completed-period value. Verify the period/as-of field and freshness first.
- If the dictionary does not define the requested contract metric or the
replacement source cannot be verified, ask or report the gap instead of
guessing from a similarly named table.
Answer shape
Lead with the identity check, then provide a compact table of contract versus
actual usage, followed by product/feature adoption signals, account context,
risks, and next steps. Make every number traceable to one source and explicitly
say when the readout is partial.
1---2name: account-health3description: >-4 How to produce a trustworthy named-customer account health, QBR, renewal, or5 contract-usage readout. Use when a prompt names an organization or account.6metadata:7 source: https://skillmd.com/skills/builderio/account-health8---910# Account Health1112Use these checks for named customer, organization, account-health, QBR,13renewal, risk, expansion, contract-utilization, or adoption questions. This is14not an ordinary metric lookup: a wrong identity or metric definition can put15another customer's data into a customer-facing decision.1617## Identity lock1819Treat an organization ID supplied in a prompt as a lookup key, not as proof that20the rows returned by a warehouse query belong to that customer.21221. Resolve the ID through the canonical CRM or contract source first.232. Record the resolved customer name, organization ID, root organization ID,24 and any canonical account key.253. Carry the same resolved identity through every usage query and check the26 returned rows against it.274. Stop and report an identity mismatch if a result contains another customer,28 mixed organization IDs, or an unresolved ID. Do not summarize the rows or29 silently choose the most plausible customer.3031## Source order and completeness32331. Use the catalog and organization data dictionary before writing warehouse34 SQL. For contract and usage metrics, the dbt Semantic Layer35 (`query-dbt-semantic-metric`) is the approved definition. Approved definitions36 and saved query shapes outrank a table name that merely sounds right.372. Gather available CRM, contract, support, and conversation evidence. Treat38 that context as complementary, not as a complete usage result.393. For account health, product usage is mandatory: query approved definitions40 for each requested product or feature dimension separately, using an explicit41 window (default 90 days for adoption unless the user asks for another one).424. Report source, window, filters, row counts, identity join, freshness, and43 gaps. A missing source is a gap, not a reason to fill in a plausible value.4445## Metric contracts4647- **Contract metric** - distinguish the contracted measure from similarly named48 platform, web, content, or event metrics. Do not use a familiar synonym when49 comparing against a contract.50- **Completed-month usage** - “last month” excludes the current partial month.51 Verify the month/as-of field and freshness before using a reporting table;52 a single current-month snapshot is not last month's completed value.53- **Seats** - use the total distinct contracted/eligible users for the stated54 period when comparing with a seat contract. Do not substitute DAU, WAU, or a55 point-in-time daily active count, and label active users separately.56- **Capacity usage** - report actual usage, contracted capacity, and utilization.57 Explicitly flag utilization at or above 100% as an overage risk and potential58 renewal/expansion signal.59- **Adoption** - keep separate products or feature dimensions separate. Include60 feature adoption, active-user/session counts, and last activity only when the61 source query returns them; absence claims require complete coverage for the62 stated window.6364## Known source traps6566- If a saved query or dictionary entry is marked deprecated or retired, do not67 run it; use the current approved replacement and note the stale reference.68- A source that returns only one current partial-period snapshot is not proof of69 a completed-period value. Verify the period/as-of field and freshness first.70- If the dictionary does not define the requested contract metric or the71 replacement source cannot be verified, ask or report the gap instead of72 guessing from a similarly named table.7374## Answer shape7576Lead with the identity check, then provide a compact table of contract versus77actual usage, followed by product/feature adoption signals, account context,78risks, and next steps. Make every number traceable to one source and explicitly79say when the readout is partial.