Orders by status
Priya Sharma, a commercial analyst at Northwind, asked for last month's order count by status. Memtro looked up the member names in the Cube model, ran the query against the semantic layer, and gave her the count for each status.
Cube Cloud + Memtro
What was our order count by status last month, straight from the Cube model?
Cube Cloud is the semantic layer over your warehouse. Memtro reads deployments, the data model's measures and dimensions, and answers questions by querying it. It also reads workbooks, reports and their deliveries, AI scheduled tasks, dashboard notification schedules and build status. When asked and granted, it can create, change, run and delete scheduled tasks, schedule dashboard notifications and manage recipients, create, copy, publish and delete workbooks, refresh and delete reports, and run deliveries. Each query runs SQL on your warehouse and may cost compute, and notification schedules need an admin's key.
In Memtro
What you can do with Cube Cloud in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Cube Cloud tool, reads what it needs, and answers with the source cited.
What it does
- 01Query the semantic layer for measures by dimension, over a time range at a granularity, with filters.
- 02Read the data model's cubes and views with their measures, dimensions and segments, and the latest build's status.
- 03See workbooks, reports and their spreadsheet deliveries, AI scheduled tasks and dashboard notification schedules.
- 04When asked and granted, create, change, pause, run or delete an AI scheduled task, which can send results to the people it names.
- 05When asked and granted, schedule a dashboard notification and add or remove recipients, who are then emailed each render.
- 06When asked and granted, create, copy, publish or delete workbooks, refresh or delete reports, or run a report delivery into its spreadsheet.
Acts when asked
When you ask it to
These tools change something in Cube Cloud. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
- 01Create an AI scheduled task
- 02Change, pause or resume a scheduled task
- 03Delete a scheduled task
- 04Run a scheduled task now
- 05Schedule a dashboard notification
- 06Add recipients to a dashboard notification
- 07Remove recipients from a dashboard notification
- 08Delete a dashboard notification
- 09Create a workbook
- 10Copy a workbook
- 11Delete a workbook
- 12Publish a workbook's dashboard draft
- 13Refresh a report
- 14Delete a report
- 15Run a report delivery to its spreadsheet now
In practice
Ask it like you would a colleague
Once Cube Cloud is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Cube Cloud + Memtro
What was our order count by status last month in Cube?
Which measures does the orders cube have?
Did the latest build of the production model succeed?
Which AI scheduled tasks run every morning, and who do they notify?
Refresh the weekly revenue report.
A dashboard for the board
Dan Fletcher, a finance lead at BigCo, asked Memtro to send the revenue dashboard as a PDF every Monday to Maya Okafor. Memtro scheduled the notification and added Maya, so each Monday's render is emailed to her.
Teams
Where it fits
The teams that lean on Cube Cloud most, a question each of them asks, and what they connect beside it.
- Data and analyticsQuestions answered from the warehouse, with the SQL shownAnalyst, Data engineer, Anybody with a question, Head of data“Revenue by segment for Q3 from the warehouse, with the SQL you used”Used alongside Postgres, Stripe, Slack, Google Drive, Snowflake and 3 more.
- EngineeringKeep decisions from evaporatingEngineer, Tech lead, On call, New joiner“Who owns the billing migration, and what did we decide about retries?”Used alongside GitHub, Linear, Jira, Confluence, Slack and 5 more.
- FinanceAsk the ledger questions in plain EnglishFinance lead, Credit control, Management accountant, Founder or CFO“Which invoices over £5k are more than 30 days overdue?”Used alongside Xero, Stripe, Postgres, HubSpot, QuickBooks Online and 10 more.
Better together
Works with
A record in Cube Cloud is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
- AnalyticsCube Cloud with Google Analytics 4Ask your traffic questions in plain English and get the numbers back.
- AnalyticsCube Cloud with Plausible AnalyticsAsk about your website traffic in plain English.
- AnalyticsCube Cloud with UmamiAsk about your website traffic in plain English, without sending anybody to a dashboard.
- Finance and commerceCube Cloud with XeroInvoices, bills, contacts and reports, answered in plain English with figures cited to Xero.
- Finance and commerceCube Cloud with StripeCustomers, charges, invoices and subscriptions through a restricted key.
- Finance and commerceCube Cloud with FellohBookings, payments, refunds, chargebacks, supplier payments and payouts from the travel payments platform.
- Work managementCube Cloud with JiraJQL search, issue details and projects from Jira Cloud.
- Work managementCube Cloud with Clio ManageAsk the matter: its client, its fee earner, the time on it and what is still unbilled.
- Work managementCube Cloud with LinearIssues, projects and teams, synced hourly into memory.
Also in Databases and warehouses
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
- Postgres
- MySQL and MariaDB
- SQL Server
- BigQuery
- Snowflake
- AWS Athena
- MongoDB
- ClickHouse
- Amazon Redshift
- Databricks
- Elasticsearch
- dbt Cloud
- Fivetran
- Neon
- Appwrite
Grist- Hasura
- Meilisearch
NocoDB- Qdrant
Typesense
Weaviate
Tinybird
Hightouch
Census- Airbyte
- Budibase
- CockroachDB Cloud
- DataHub
kintone
Monte Carlo
OpenMetadata- Pinecone
- PlanetScale
- Quickbase
Secoda
Softr
Teable- Turso
- Upstash
Vectara- Xata
- Zilliz Cloud
Setup
How to connect
Connect withAPI key and Cube Cloud host
- 1
In Cube Cloud, open Admin → API Keys and create a key scoped to the deployments Memtro should see. Only admins hold keys unless all users may create them.
- 2
In Memtro, open Connections → Cube Cloud and paste the API key and the Cube Cloud host you sign in at, without https://.
- 3
If you limit the key to specific endpoints, include the deployment token endpoint. An administrator grants the task, notification and workbook actions by name to the teams that may use them.
- 4
Ask what your order count by status was last month in Cube.
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Cube Cloud tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in Cube Cloud?+
Only when you ask, and only what it has been granted: create an AI scheduled task; change, pause or resume a scheduled task; delete a scheduled task; run a scheduled task now; schedule a dashboard notification; add recipients to a dashboard notification; remove recipients from a dashboard notification; delete a dashboard notification; create a workbook; copy a workbook; delete a workbook; publish a workbook's dashboard draft; refresh a report; delete a report; run a report delivery to its spreadsheet now. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
Who can use a Cube Cloud connection?+
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Does Memtro store my Cube Cloud data?+
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
How do I connect Cube Cloud?+
API key and Cube Cloud host. In Cube Cloud, open Admin → API Keys and create a key scoped to the deployments Memtro should see. Only admins hold keys unless all users may create them.
Connect Cube Cloud in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.