BigQuery + Memtro

What you can do with BigQuery in Memtro

Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right BigQuery tool, reads what it needs, and answers with the source cited.

• List datasets, tables and columns, including nested RECORD fields
• Run one SELECT or WITH query at a time, rows capped, 20 second timeout
• Dry-run any query to see the bytes it would scan
• Tokens use the bigquery.readonly scope, so nothing can be written

Ask it like this

Questions people ask once BigQuery is connected. In agent mode each one also checks the other systems that know about the same people, companies or identifiers.

• ›How many orders did Acme place last quarter, from the warehouse?
• ›Which tables in the analytics dataset hold customer emails?
• ›How much would it cost to scan events for the last 30 days?

Where it fits

Teams that get the most from BigQuery in Memtro, with the rest of their stack attached.

• Data and analyticsQuestions answered from the warehouse, with the SQL shownPoint Memtro at a read-only replica and anyone can ask the warehouse a question in plain English. The agent reads the schema, writes the query, runs it inside a read-only transaction, and shows its work.
• EngineeringKeep decisions from evaporatingDecisions, owners and deadlines are extracted from conversations and tool results into a typed, time-aware memory. Corrections supersede old facts instead of piling up next to them.
• FinanceAsk the ledger questions in plain EnglishXero, Stripe and the warehouse answer through read-only tools. Duplicate charges, aged receivables, revenue by segment: one question, with the figures cited to their source.

Questions

Can Memtro change anything in BigQuery?

No. The BigQuery connector is read-only: every tool reads, searches or lists. Nothing is created, sent, updated or deleted, and the credentials you give it should be read-only too.

Who can use a BigQuery 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 BigQuery 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extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.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 BigQuery?

Service account key. Create a service account in Google Cloud and grant it BigQuery Data Viewer and BigQuery Job User.