> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/consume/v1/recipes/find-a-data-product.md). # Discovering the Right Data Product in Natural Language You have a business need ("report on quarterly sales revenue") but you do not yet know which product to trust. This recipe takes you from the question to a vetted, healthy product, using only natural language. The journey is Discover → evaluate trust (quality and runs) → confirm ownership. **What this enables:** * [ ] Discover data products by business need, not by table or product name * [ ] Narrow candidates to the ones that actually expose the metric you need * [ ] Check quality and freshness before trusting a product's numbers * [ ] Confirm ownership before depending on a product {% hint style="info" %} **Prerequisites:** a [connected client](/consume/v1/consume-with-ai/connect-a-client.md). Confirm the connection by asking what is available. {% endhint %} ## Steps Example responses below are illustrative: exact wording, fields, and figures depend on your catalog, your data, and your permissions. ### 1. Discover candidates from the need Start from the need, not a product name. Ask for products related to your question, then narrow to those that expose the exact metric. {% code overflow="wrap" %} ``` I need to report on quarterly sales revenue. What data products exist for orders and revenue? ``` {% endcode %}
Sample response Found 6 data products relevant to orders and revenue: #### executive (1) | # | Name | Description | Business Metrics | | - | ------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- | | 1 | Revenue & Growth Command Center | Aggregate executive data product publishing revenue KPIs, net revenue retention, cohort retention, and CAC:LTV payback analysis from governed Cartwell product outputs. | cac\_ltv\_ratio, cohort\_retention\_rate, net\_revenue\_retention, total\_revenue | #### marketing (1) | # | Name | Description | Business Metrics | | - | --------- | ----------------------------------------------------------------------------------------------------------------------------- | ----------------------------- | | 2 | Orders360 | Governed customer, order, and product analytics data product with curated gold models, semantic models, and business metrics. | order\_volume, revenue\_trend | #### retail (2) | # | Name | Description | Business Metrics | | - | ---------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | | 3 | \[PG] Retail Intelligence Platform (dev) | Governed retail analytics covering revenue performance, customer lifecycle, product merchandising, fulfillment ops, and RFM segmentation. | customer\_lifetime\_value, daily\_sales\_performance, fulfillment\_conversion, rfm\_value\_by\_segment, weekly\_revenue\_trends | | 4 | \[PG] Retail Intelligence Platform (stg) | Same coverage as above, staging tenant. | customer\_lifetime\_value, daily\_sales\_performance, fulfillment\_conversion, rfm\_value\_by\_segment, weekly\_revenue\_trends | #### sales (2) | # | Name | Description | Business Metrics | | - | --------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | | 5 | Orders & Transactions | Source-aligned data product unifying online commerce orders and in-store POS transactions, exposing trusted revenue and return metrics. | channel\_mix, net\_revenue, return\_rate, total\_revenue | | 6 | Sales & Channel Performance | Consumer-aligned data product publishing daily/monthly channel, region, and category performance with MoM growth. | aov, channel\_mix, growth\_pct\_mom, revenue, units | For a quarterly sales revenue report, "Orders & Transactions" (source-level revenue/returns) and "Sales & Channel Performance" (channel/region/category trends with MoM growth) are the most direct fits, with "Revenue & Growth Command Center" for executive-level KPIs. Explore all data products: [dev](https://productsandbox.instance.dataos.cloud/platform/data-product/dev) | [stg](https://productsandbox.instance.dataos.cloud/platform/data-product/stg) Want me to pull the actual revenue numbers from one of these and build the quarterly report?
Narrow further: ``` Which of those has a monthly or quarterly revenue trend metric? ```
Sample response Two data products have explicit monthly revenue metrics, and none have a native quarterly grain: | Data Product | Metric | Granularity | | ------------------------------- | ----------------------- | ---------------------------------------------------------- | | Sales & Channel Performance | channel\_mix | Monthly revenue mix by channel | | Sales & Channel Performance | growth\_pct\_mom | Month-over-month revenue growth by channel/region/category | | Revenue & Growth Command Center | total\_revenue | Monthly valid order revenue | | Revenue & Growth Command Center | net\_revenue\_retention | Monthly retained-revenue NRR proxy | Everything else is daily or weekly (Orders360's revenue\_trend is daily, Retail Intelligence's weekly\_revenue\_trends is weekly, Orders & Transactions' total\_revenue has no stated time grain). For a quarterly report, you'd roll up "Sales & Channel Performance" (best channel/region/category breakdown) or "Revenue & Growth Command Center" (best for executive-level total revenue) monthly metrics into quarters; there's no metric that's quarterly out of the box. Want me to pull the monthly revenue data from one of these and aggregate it into Q2/Q3 figures for your report?
You now have a shortlist of products that actually expose the measure you need, each with a link to open it. This is [Discover in natural language](/consume/v1/consume-with-ai/discover-in-natural-language.md). ### 2. Check that a candidate is trustworthy A product that has the right metric is not the same as a product you can trust. Before committing, check quality and freshness: ``` Are the quality checks on Sales & Channel Performance passing? ```
Sample response Yes: all 6 checks are passing (100% pass rate across completeness and validity), last evaluated 2026-07-17. Nothing failing or warning. View quality details
A clean quality summary and a recent successful run mean the numbers are safe to act on. Failing checks or stale runs are your signal to pick another candidate or contact the owner. This is [Understand in natural language](/consume/v1/consume-with-ai/understand-in-natural-language.md). ### 3. Confirm ownership Before you depend on a product, know who maintains it: ``` Who owns Sales & Channel Performance, and how do I reach them? ```
Sample response Sales & Channel Performance has three owners listed: * Mukul Gupta (mukulguptatmdcio): primary owner, also owns Orders & Transactions and Revenue & Growth Command Center * Shreya Sikarwar (shreyasikarwartmdcio) * Hanumanth M (hanumanthmmdcio) Use cases: None configured. Limitations: None configured. I don't have direct contact info (email/Slack) in this catalog, just their usernames. [View Data Product](https://productsandbox.instance.dataos.cloud/platform/data-product/stg/sales-channel?tab=overview)
Note the owner so you can ask about schema stability and report issues. For a production dependency, reach out before committing. ## Troubleshooting
IssueResolution
The assistant returns no matches for your needRephrase around the business term rather than a table or product name; the search matches on domain, metric, and description, not exact identifiers.
Too many candidates to compareNarrow by the specific metric or dimension you need, as in step 1's follow-up, rather than by name.
Quality or run status looks stale or missingAsk for the last run's timestamp and status directly; a missing snapshot usually means the product has not run recently rather than a broken check.
No owner is listedCheck the product's catalog page directly, or ask in your team's data channel; not every product has owner metadata populated yet.
## Outcome You have moved from a vague business need to one vetted, healthy, owned product, without leaving the chat or guessing at a table name. ## References * [Discover in natural language](/consume/v1/consume-with-ai/discover-in-natural-language.md): the full range of discovery questions you can ask * [Understand in natural language](/consume/v1/consume-with-ai/understand-in-natural-language.md): quality, lineage, and run questions to evaluate trust --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://v2.dataos.info/consume/v1/recipes/find-a-data-product.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.