Revenue before the meeting
Sarah Chen, finance director at BigCo, asked what the weekly revenue Look showed. Memtro found the Look, checked its fields and filters, and ran it for its rows, using Looker's cached result first.
What does the weekly revenue Look show, and which dashboards are in the Finance folder?
Memtro reads your Looker instance over API 4.0. It searches Looks and dashboards, reads a dashboard's tiles and the query behind each, browses folders and models, and runs a Look or saved query for up to 500 rows, asking for a cached result first. When asked and once an administrator has granted the action by name, it can save queries as Looks, create, copy, move or rename Looks, dashboards and folders, and delete them to Trash or permanently. It can send a scheduled delivery now, which may email people outside the company and cannot be recalled.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Looker tool, reads what it needs, and answers with the source cited.
These tools change something in Looker. 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.
Once Looker 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.
Which dashboards are in the Finance folder?
What does the weekly revenue Look show?
What fields and filters sit behind the pipeline Look?
What tiles are on the board KPIs dashboard?
Send the weekly revenue schedule now.
Sarah Chen, finance director at BigCo, asked what the weekly revenue Look showed. Memtro found the Look, checked its fields and filters, and ran it for its rows, using Looker's cached result first.
Dan Fletcher, a data analyst at Acme Ltd, asked Memtro to save pipeline by region for this quarter as a Look in the Sales folder. Memtro defined the query on the sales explore and saved it there as a new Look, which everyone with access to the Sales folder could see and run.
The teams that lean on Looker most, a question each of them asks, and what they connect beside it.
A record in Looker 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.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
In Looker, open Admin → Users, pick a dedicated API user whose role covers only the models and folders Memtro should see, read-only unless it should also save Looks, edit dashboards or send schedules. On Looker (Google Cloud core) an admin must first enable API management for that user.
Under that user's API keys choose New API key, and copy the Client ID and the Client secret, which is shown once.
In Memtro, open Connections → Looker and paste API host (host name only, such as <instance>.cloud.looker.com), Client ID and Client secret. Set API port to 19999 only for an older AWS-hosted instance.
Ask: "Which dashboards are in the Finance folder?"
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Looker tools are the same everywhere.
Only when you ask, and only what it has been granted: define a query (model, explore, fields, filters, sorts) so it can be saved as a Look; save a query as a new Look in a named folder; rename a Look, change its description or the query behind it; move a Look to another folder, which changes who can see it; delete a Look, to Trash by default or permanently when asked; create an empty dashboard in a named folder; rename a dashboard or change its description, refresh interval or display options; copy a dashboard into a named folder; move a dashboard to another folder, which changes who can see it; delete a dashboard, to Trash by default or permanently when asked; create a folder under a parent folder; send a scheduled delivery now to all of its recipients, as saved; check an alert now, which notifies its recipients if the condition is met; delete a scheduled delivery, permanently. 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.
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.
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.
API host, Client ID and Client secret. In Looker, open Admin → Users, pick a dedicated API user whose role covers only the models and folders Memtro should see, read-only unless it should also save Looks, edit dashboards or send schedules. On Looker (Google Cloud core) an admin must first enable API management for that user.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time