Explain recent job failures
Review job [job ID] during [time range]. Inspect failed runs and summarize affected tasks, errors, and follow-up checks.
Leina connects to Databricks to help you investigate failed jobs and start selected workloads. Ask in your team chat. Leina does the work and brings back the result.
Connect Databricks, choose what to share, and hand off your first task.
You
Review last night’s runs for job [job ID]. Tell me which task failed and what to check next.
Leina
The ingestion task failed with an access error. I found no completed downstream transform in that run.
Databricks · Failure review
Nightly pipeline
The ingestion error is the first issue to investigate.
A Databricks AI agent can review job runs, explain available error details, and start an existing job with your chosen parameters.
You specify the source and the destination. Leina uses the content available to your connection and returns the result for you to review.
Databricks runs data processing and analytics workloads in a shared workspace.
Provide the job and time range to review.
Read task states and available error output.
Summarize the evidence without assuming a root cause.
Copy a prompt, add your details, and send it to Leina in your connected team chat.
Review job [job ID] during [time range]. Inspect failed runs and summarize affected tasks, errors, and follow-up checks.
Start existing job [job ID] with [parameters] for [purpose]. Check its current progress and tell me whether it has finished.
Your next Databricks task can start with a message.
Tell Leina what you need in your team chat. Include the source, destination, and expected result.
Connect the tools involved and give Leina access to the content it needs.
Share the source material, say where the result belongs, and describe what you need.
Review the result and any changes in the connected app.
Hand off these everyday tasks to your AI employee.
Get the current Databricks workspace principal profile for the connected personal access token.
List Databricks jobs in the connected workspace with optional pagination, name filtering, and task expansion.
Get one Databricks job, including its current settings and optional continuation page token.
Create a Databricks job from a raw official Jobs API settings object and return the new job ID.
Update an existing Databricks job by ID using the official partial-update payload fields.
Delete a Databricks job by ID.
Trigger an immediate run for a Databricks job with optional parameter maps and idempotency token.
List Databricks job runs with optional job, state, time-range, and pagination filters.
Get one Databricks job run by run ID.
Get the output payload for one Databricks run, including notebook output or error details when available.
Cancel a Databricks job run by run ID.
Submit a one-time Databricks run from a raw official Jobs API submit payload and return the run ID.
List Databricks clusters with optional paging, filtering, and sorting controls from the official clusters API.
Get one Databricks cluster by cluster ID.
Create a Databricks cluster from a raw official clusters create payload and return the new cluster ID.
Edit an existing Databricks cluster by cluster ID using a raw official clusters edit payload.
Start a terminated Databricks cluster by cluster ID.
Permanently delete a Databricks cluster by cluster ID.
List Databricks cluster node types that are available in the connected workspace region.
List Databricks cluster availability zones for the connected workspace when the API is supported.
List Databricks Runtime and Spark versions that can be used when creating or editing clusters.
List the direct Databricks workspace objects under a workspace path.
Get metadata for one Databricks workspace object by absolute path.
Export one Databricks workspace object as base64 content or direct text content, depending on the export mode.
Import base64 content into the Databricks workspace at an absolute path.
Create a Databricks workspace directory, including any missing parent directories.
Delete a Databricks workspace object or directory by absolute path.
Create a Databricks workspace repo that links a Git remote into the connected workspace.
Update a Databricks workspace repo by switching branch or tag, or by changing sparse-checkout settings.
Delete a Databricks workspace repo by repo ID.
List Databricks secret scopes in the connected workspace.
List Databricks secret metadata rows in one secret scope.
Create a Databricks secret scope with an optional backend configuration and initial manager principal.
Delete a Databricks secret scope by scope name.
Create or overwrite a Databricks secret value inside one Databricks secret scope.
Delete one Databricks secret value from a Databricks secret scope.
Connect the Apps your work depends on, and give Leina the context to carry the task forward.
Hand off a task while your team is discussing it. Leina uses your connected tools and brings the result back to the conversation.
See How Leina Works in SlackThe ingestion task failed with an access error. I found no completed downstream transform in that run.
Yes. It executes the selected workload and may incur compute costs.
The available operations cover jobs, runs, and workspace resources. They do not include direct SQL warehouse queries.
Start with one task you already need to do. Tell Leina what a finished result should look like.
Connect Databricks, choose what to share, and hand off your first task.