Connect your stack
27 native integrations. 3,200+ tools via managed connectors. Most are one-click OAuth, some use API keys - Viktor handles auth and starts working. No webhooks, no Zapier zaps.
Loading
Viktor is an AI employee that connects to Snowflake with a scoped API key and helps you query and maintain application databases, running 9 Snowflake actions for you like Start SQL Session, Insert Single Row, and Execute SQL Query. Ask in plain English in Slack or Microsoft Teams; Viktor does the work in Snowflake and reports back. Setup takes about two minutes.
Free to start · No credit card · SOC 2 Type 1 · Works in Slack & Microsoft Teams
Messages you'd actually send. Paste one into Slack or Microsoft Teams, swap in your specifics, and Viktor takes it from there.
“Query Snowflake for last month's signups and summarize the trend.”
— you, in Slack or Teams
“Check Snowflake for slow queries this week and flag the worst offenders.”
— you, in Slack or Teams
“Sync new records from Snowflake into a sheet every morning.”
— you, in Slack or Teams
“Watch Snowflake for a spike in errors and alert me with the likely cause.”
— you, in Slack or Teams
Ask in plain English in Slack or Microsoft Teams. Viktor picks the right Snowflake actions, runs the work, and reports back. No workflows to build.
Start a Snowflake session and return it in serialized form, so subsequent Snowflake actions can run in the same session (preserving temporary tables, USE context, and session parameters) by passing it to their Session prop. The returned value contains session auth tokens — treat it as sensitive. Sessions expire server-side after ~4 hours or your account's idle timeout.
Retrieves available options for the Warehouse Name field.
Retrieves available options for the User Name field.
Retrieves available options for the Database field.
Insert a row into a table.
Insert multiple rows into a table.
Execute a custom Snowflake query. See our docs to learn more about working with SQL in Pipedream.
Execute a Snowflake query inside a session started by the Start SQL Session action, so it shares that session's state — temporary tables, USE context, and session parameters — with the other queries in the same session. Pass the serialized session from Start SQL Session to the Session prop. Note: to preserve the session this query runs on a direct connection and therefore does NOT egress from the shared static IP (usepdsqlproxy); if your Snowflake network policy allowlists only the static IP, use Execute SQL Query instead. See our docs to learn more about working with SQL in Pipedream.
Execute a SQL Query. See our docs to learn more about working with SQL in Pipedream.
27 native integrations. 3,200+ tools via managed connectors. Most are one-click OAuth, some use API keys - Viktor handles auth and starts working. No webhooks, no Zapier zaps.
Message Viktor in Slack like you'd message a teammate. "Query Snowflake for last month's signups and summarize the trend." "Check Snowflake for slow queries this week and flag the worst offenders." Plain English, any tool.
Viktor opens Snowflake, runs the work, and posts back what changed. Sensitive actions wait for your approval. Everything is logged. You stop doing the work and start reviewing it.
A Snowflake AI agent is an AI that connects to your Snowflake account and completes work in it - it doesn't just answer questions about Snowflake, it takes the actions. Viktor is that agent: an AI employee that works in Snowflake on your behalf and delivers the finished result in Slack or Microsoft Teams.
Unlike workflow builders such as Zapier or Make, there is nothing to configure - no triggers to map, no workflows to maintain. You describe the outcome in plain English, and Viktor picks the right Snowflake actions, chains them with the other 3,200+ tools it connects to, and asks for approval before anything sensitive runs.
A data warehouse built for the cloud
Scoped API keys - Viktor stores your key securely, uses only the scopes you grant, and you can revoke it at any time.
Review-first approvals: sensitive Snowflake actions wait for your sign-off before they run.
Isolated compute per team, encrypted in transit and at rest - and your data is never used to train models.
SOC 2 Type 1 compliant, with Type 2 and ISO 27001 in progress.
Yes. Snowflake is one of the 3,200+ tools Viktor connects to, via a managed connector. Once connected, anyone on your team can put Viktor to work in Snowflake from Slack or Microsoft Teams - no workflow builder, no code.
Ask for outcomes that span tools — Viktor pulls from Snowflake, cross-references the rest of your stack, and delivers one finished result.
Viktor connects to 3,200+ tools and works across them in a single run.
