
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.
Viktor is an AI employee that connects to Databricks (OAuth - Service Principal) in one click via OAuth and helps you run and evaluate LLM and AI infrastructure workloads, running 42 Databricks (OAuth - Service Principal) actions for you like Get Run, Get Job, and Reset Job. Ask in plain English in Slack or Microsoft Teams; Viktor does the work in Databricks (OAuth - Service Principal) 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.
“Run this batch of documents through Databricks (OAuth - Service Principal) and summarize the results.”
— you, in Slack or Teams
“Compare Databricks (OAuth - Service Principal)'s output on this prompt with what we use today.”
— you, in Slack or Teams
“Set up a daily job that queries Databricks (OAuth - Service Principal) on new entries and reports back.”
— you, in Slack or Teams
“Watch Databricks (OAuth - Service Principal) for a cost or latency spike 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 Databricks (OAuth - Service Principal) actions, runs the work, and reports back. No workflows to build.
Fetch the next page of results from a previously executed Databricks Vector Search query, using the nextpagetoken returned by a prior call. Run Query Vector Search Index first to get an initial page and its nextpagetoken, then pass that token here (and again on each subsequent call) to walk through all pages. Results are returned in groups of up to 1000, with a maximum of 10,000 total; an empty nextpagetoken in the response means there are no more pages.
List all vector search endpoints.
Upserts (inserts/updates) data into an existing vector search index.
Update an existing job. Only the fields that are provided will be updated.
Synchronize a Delta Sync vector search index in Databricks.
Stops a SQL Warehouse by ID.
Starts a SQL Warehouse by ID.
Updates the permissions for a specific SQL Warehouse.
Updates the global configuration for SQL Warehouses.
Set permissions on a job.
Scans a vector search index and returns entries after the given primary key.
Run a job now and return the id of the triggered run.
Overwrite all settings for the given job.
Re-run one or more tasks.
Query a specific vector search index in Databricks.
Lists all vector search indexes for a given endpoint.
Lists all SQL Warehouses available in the Databricks workspace.
Lists all runs available to the user.
List all jobs using automatic pagination.
Retrieves details about a specific vector search index.
Retrieves details for a specific SQL Warehouse.
Retrieves the permissions for a specific SQL Warehouse.
Retrieves the global configuration for SQL Warehouses.
Retrieve the metadata of a run.
Retrieve the output and metadata of a single task run.
Retrieves the details for a single job.
Get permissions of a job.
Get details of a specific vector search endpoint.
Export and retrieve the job run task.
Edits the configuration of an existing SQL Warehouse.
Deletes a vector search index in Databricks.
Deletes rows from a Direct Access vector index by primary-key values.
Deletes a SQL Warehouse by ID.
Delete a non-active run. Returns an error if the run is active.
Delete a job. Deleted jobs cannot be recovered.
Delete a vector search endpoint.
Creates a new vector search index in Databricks.
Creates a new SQL Warehouse in Databricks.
Create a job.
Create a new vector search endpoint.
Cancel a job run. The run is canceled asynchronously, so it may still be running when this request completes.
Cancel all active runs for a job. The runs are canceled asynchronously, so it doesn't prevent new runs from being started.

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. "Run this batch of documents through Databricks (OAuth - Service Principal) and summarize the results." "Compare Databricks (OAuth - Service Principal)'s output on this prompt with what we use today." Plain English, any tool.
Viktor opens Databricks (OAuth - Service Principal), 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 Databricks (OAuth - Service Principal) AI agent is an AI that connects to your Databricks (OAuth - Service Principal) account and completes work in it - it doesn't just answer questions about Databricks (OAuth - Service Principal), it takes the actions. Viktor is that agent: an AI employee that works in Databricks (OAuth - Service Principal) 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 Databricks (OAuth - Service Principal) actions, chains them with the other 3,200+ tools it connects to, and asks for approval before anything sensitive runs.
Databricks is the lakehouse company, helping data teams solve the world’s toughest problems.
One-click OAuth - Viktor never sees your password, and you can revoke access at any time.
Review-first approvals: sensitive Databricks (OAuth - Service Principal) 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. Databricks (OAuth - Service Principal) 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 Databricks (OAuth - Service Principal) from Slack or Microsoft Teams - no workflow builder, no code.