A Gleap custom agent can run SQL in Snowflake through Composio and list databases, schemas and tables. It suits data teams that keep account, usage and billing data in Snowflake while support answers customers in Gleap.
What a Gleap agent can do in Snowflake
- Answer account questions: Execute SQL runs a query, such as an account’s active users or last sync time, and returns the rows to the agent.
- Find the right table: Show Databases, Show Schemas and Show Tables help the agent locate data before it queries.
- Handle long queries: Check Statement Status polls a statement that takes longer, and Cancel Statement Execution stops it.
- Check Snowflake itself: Get Status Summary and Get Unresolved Incidents read Snowflake’s public status page when customers report delayed data.
Example: A dashboard that stopped updating
A customer writes in Gleap that their dashboard has not updated since yesterday. The teammate asks the agent to look. The agent checks Snowflake’s status page for open incidents, finds none, then queries the sync log table for the customer’s account and sees that the last run failed. The teammate passes the failure to engineering and keeps the customer informed.
How to connect Snowflake
- In Gleap, open AI & Automation > Agents and select a custom agent, or create one.
- In its Tools section, click Add tool and search for “Snowflake”.
- Pick Snowflake under More integrations and click Connect Snowflake.
- Set up an OAuth client for Snowflake as described in Composio’s setup guide, paste its client ID, client secret and any account details Gleap asks for, and add the redirect URI Gleap shows. Then sign in to Snowflake in the popup.
- Open the new Snowflake tool and switch off every action the agent does not need, and keep Execute SQL on only with a read-only role.
- Tell the agent in its instructions when to use Snowflake, 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 Snowflake in coding sessions once you add it under Settings > MCP in Kai Code.
FAQ
Does Gleap integrate with Snowflake?
Yes, through Composio. A Gleap custom agent can execute SQL, check and cancel statements, list databases, schemas and tables and read Snowflake’s public status page. It queries Snowflake only when it runs.
What can a Gleap AI agent do in Snowflake?
It answers data questions from support tickets, such as an account’s usage or the result of a sync, straight from your warehouse. Your team reviews the answer before it reaches the customer.
Which Gleap plan includes the Snowflake integration?
Kai Support and Kai Code can use the Snowflake 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. Snowflake bills warehouse compute for the agent’s queries as usual. Gleap bills the agent’s AI usage billed separately; see pricing.
Can the agent change data in Snowflake?
Execute SQL accepts any statement the connected role allows, including INSERT, UPDATE and DROP. Connect a role with read-only grants on the schemas the agent needs.
