A Gleap custom agent can run SQL in Google BigQuery through Composio, list datasets and tables and read schemas. It gives support and product teams direct answers from the warehouse, such as an account’s usage, without waiting for an analyst.
What a Gleap agent can do in Google BigQuery
- Answer usage questions: Query runs SQL, such as the number of exports an account ran last month, and Get BigQuery Query Results reads longer results.
- Write valid SQL: List BigQuery Tables and Get BigQuery Table Schema show the columns before the agent writes a query.
- Explore datasets: List BigQuery Datasets shows which datasets the connected account can reach.
- Log support facts: Insert Data into BigQuery Table streams a row per resolved bug or feature request, so analysts can join support data with product data.
Example: A disputed usage charge
An enterprise customer disputes an overage charge in Gleap and says they ran only 200 exports. The account manager asks the agent to check. The agent reads the schema of the usage table, queries the account’s exports by day and posts the totals in the ticket. The account manager reviews the numbers with finance before replying.
How to connect Google BigQuery
- In Gleap, open AI & Automation > Agents and select a custom agent, or create one.
- In its Tools section, click Add tool and search for “Google BigQuery”.
- Pick Google BigQuery under More integrations and click Connect Google BigQuery.
- Enter the credentials Gleap asks for: a Google service account key, or the client ID and client secret of your own Google OAuth app.
- Open the new Google BigQuery tool and switch off every action the agent does not need, such as Delete BigQuery Table or Delete BigQuery Dataset.
- Tell the agent in its instructions when to use Google BigQuery, then test it in chat.
Custom agents are included in the Team, Pro and Enterprise plans. Kai Support can use connected apps as tools on Team, Pro and Enterprise. Kai Code, also on those plans, can use Google BigQuery in coding sessions once you add it under Settings > MCP in Kai Code.
FAQ
Does Gleap integrate with Google BigQuery?
Yes, through Composio. A Gleap custom agent can run queries, read schemas and results, list datasets and tables and insert rows. Queries run when the agent runs; Gleap does not export its data to BigQuery on its own.
What can a Gleap AI agent do in Google BigQuery?
It answers account and usage questions from support tickets with SQL against your warehouse and can log support events for later analysis. Kai Code can use the same toolkit to check data while it works on a change.
Which Gleap plan includes the Google BigQuery integration?
Kai Support and Kai Code can use the Google BigQuery toolkit on Team, Pro and Enterprise; custom agents that use it are on Team, Pro and Enterprise. Kai Support answers customers, so switch on only actions that are safe in a customer conversation. BigQuery query costs are billed by Google as usual. Gleap bills the agent’s AI usage billed separately; see pricing.
How do we keep the agent from changing data?
Connect a service account with read-only BigQuery roles, and switch off write actions such as Insert Data into BigQuery Table and Delete BigQuery Table. Query can run any SQL that the account’s permissions allow.
