Skip to content
ClickRuntime

Automate BigQuery

Put your BigQuery tables to work on a schedule. Saved queries run and land in your inbox, metrics that cross a limit trigger an alert, stale tables get flagged, and API data is appended to a table so you build a history. Describe what you want to your AI assistant, check what it will do, and it keeps running with your laptop closed.

Add to ChatGPTAdd to Claude
Works inChatGPTClaudeClaude CodeCursorCodexVS CodeGemini CLIZedopencodeAny MCP client

Try asking

Create a ClickRuntime automation: every hour, fetch account balances from https://api.example.com/v1/balances and insert them as rows into analytics.balance_history in BigQuery with a fetched_at timestamp.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Ideas

What you can automate in BigQuery

Query results that arrive without anyone running them, alerts when a number crosses a line or a table goes stale, and plain-English answers from your datasets. These are ready-made starting points. Anything else you can describe works too.
Every minute to daily

Save API snapshots to a BigQuery table

Data from an API is appended to your table with a timestamp on each run, building a history you can query.

See how it works
The moment it happensAI

Ask your data questions in plain English

You send a question and get the answer from your tables by email, without writing SQL.

See how it works
Daily

Get your KPI query results every morning

Your saved SQL runs each morning and the results arrive as a table in your inbox.

See how it works
Hourly

Get alerted when a metric crosses a limit

A query runs every hour and you hear in Slack as soon as the value passes your threshold.

See how it works
Daily

Hear when a table stops updating

Each morning you're told if a table hasn't changed in the last day, so broken pipelines get noticed.

See how it works Your own logic

Any other automation you can describe in words

Your own rules, schedule and AI steps with BigQuery, plus any other app. Describe it and your assistant builds it.

See how to build your own

Build your own

Build any BigQuery automation you can describe

The ideas above are ready-made starting points, not a fixed list. Describe what BigQuery should do in your own words, with your conditions, other apps or an AI step, and your assistant writes it, tests it and runs it on ClickRuntime.

  • Your own rules

    Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.

  • Any number of apps

    One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.

  • AI where it helps

    Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.

  • On a schedule or on each event

    Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

For example, ask your assistant

Every morning at 6, run my BigQuery query for yesterday's signups and alert me if the count is less than half of the 7-day average.

Every Monday, run my BigQuery revenue query and write the results to my Revenue sheet in Google Sheets.

Every day, run my BigQuery query for accounts with no logins in 14 days, add them to my At Risk sheet in Google Sheets and post the top 10 by revenue in #success on Slack.

Beyond chat

Have BigQuery work when you're not in the chat

Connecting BigQuery to ChatGPT or Claude lets you ask about it while you chat. ClickRuntime handles the part that should happen on its own: checks on a schedule and actions on each new event, set up from the same chat and running after you close it.

Setup

Connect BigQuery

You connect BigQuery with a service account in your own Google Cloud project. Its IAM roles decide whether it can only read datasets or also write rows.

BigQuery

Data warehouse

  1. In Google Cloud Console, go to IAM & Admin, Service Accounts, and create a service account.
  2. Grant it BigQuery Job User on the project, plus BigQuery Data Viewer to read or BigQuery Data Editor to insert rows.
  3. Under Keys, choose Add key, then JSON, and download the key file.
  4. In the ClickRuntime dashboard, open Connections & secrets, upload the JSON key and enter your project ID.

Good to know

BigQuery limits that affect automations

  • On-demand queries are billed by the data they scan. Automations can cap the bytes a query may bill, and selecting only the columns you need keeps the cost down.
  • BigQuery Job User can only be granted for a whole project, while Data Viewer and Data Editor can be limited to single datasets.
  • Reading table metadata, as the freshness check does, doesn't run a query.
  • Google advises against the broad Owner, Editor and Viewer roles in production, so give the service account only the BigQuery roles above.
  • The shortest schedule is every 5 minutes.

FAQ

Questions about automating BigQuery

What can ClickRuntime see in BigQuery?
The datasets your service account has roles on. With Data Viewer it can run queries and read tables, and with Data Editor it can also insert rows.
Will the automations cost me money in BigQuery?
Google bills your project for the data each query scans. Metadata checks don't scan data, and query automations can set a maximum bytes billed so a bad query can't run up a large bill.
Can I ask questions without writing SQL?
Yes. The plain-English automation reads your table schemas, has AI write the SQL, runs it as a read-only query and emails you the answer.
Can I limit access to one dataset?
Yes. Grant Data Viewer or Data Editor on that dataset only. Job User still has to be granted on the project so the account can run queries.
Do I need AI for BigQuery automations?
No. Scheduled queries, threshold alerts, freshness checks and row inserts run without it. Turning questions into SQL uses the AI that comes with every ClickRuntime plan, so you don't need your own AI key.
Is this a BigQuery connector for ChatGPT or Claude?
Not for chatting with BigQuery data. A chat connector lets your assistant read and change BigQuery while you're in the conversation. ClickRuntime is for the work that should happen without you: you set up an automation from the chat once, and it keeps running on a schedule or on each BigQuery event.

Related pages

Keep exploring

Tell your assistant what BigQuery should do

Free plan. No credit card.

Add to ChatGPTAdd to Claude