- 39890 Views
- 23 replies
- 50 kudos
Databricks Announces the Industry’s First Generative AI Engineer Learning Pathway and Certification
Today, we are announcing the industry's first Generative AI Engineer learning pathway and certification to help ensure that data and AI practitioners have the resources to be successful with generative AI. At Databricks, we recognize that generative ...
- 39890 Views
- 23 replies
- 50 kudos
- 639 Views
- 2 replies
- 2 kudos
Azure Databricks Genie + Copilot Studio: MCP tools discovered and enabled, but Copilot never invokes
Hi everyone,I'm trying to integrate an Azure Databricks Genie Agent with Microsoft Copilot Studio through the MCP integration, and I'm stuck in a situation where everything appears correctly configured, but Copilot never actually invokes the Genie to...
- 639 Views
- 2 replies
- 2 kudos
- 2 kudos
Same issue here. Just occurs with new Copilot Studio UI. Legacy UI works perfectly.Is there any workaround to this?
- 2 kudos
- 74 Views
- 2 replies
- 0 kudos
Genie Agent response Export to PDF via API
Hello,Got a need to invoke the Genie Agent chat (in agent mode) via API, and on the request completion, export the agent response in PDF and share the exported PDF in email. Am already using 'Agent Mode Create Response' endpoint to invoke the chat p...
- 74 Views
- 2 replies
- 0 kudos
- 0 kudos
@GunaR Adding to the above mentioned from @Ashwin_DSA, I tested this from Databricks and can confirm the client side PDF approach works.A couple of useful observations from the test:The completed Agent response can be extracted from the assistant mes...
- 0 kudos
- 346 Views
- 3 replies
- 0 kudos
Genie Agent content search on a managed volume fails with "The request was invalid"
Hi all, I am trying to enable content search on a Unity Catalog managed volume so a Genie Agent can answer questions over PDFs. The Enable action fails every time with: "Failed to update content search - The request was invalid." Environment: AWS, eu...
- 346 Views
- 3 replies
- 0 kudos
- 0 kudos
Thanks both, very helpful. Two updates. First, a correction on my side: the workspace is in us-east-2, not London, so cross-Geo processing should not have been required for this region. Second, I checked the workspace Security and compliance tab anyw...
- 0 kudos
- 174 Views
- 3 replies
- 0 kudos
Databricks-Native AI Agent for Job Incident Detection, RCA & Safe Remediation
I’m exploring an architecture for a Databricks-native AI Agent for intelligent Spark job incident detection, root cause analysis (RCA), and safe remediation, and I would love your technical feedback.The ProblemA common operational challenge is the "S...
- 174 Views
- 3 replies
- 0 kudos
- 0 kudos
@VibinRoy_C the key limitation is telemetry latency: system.lakeflow.job_run_timeline and job_task_run_timeline are useful for baselines, but records typically arrive within an hour. system.compute.node_timeline adds minute-level metrics for classic...
- 0 kudos
- 189 Views
- 3 replies
- 3 kudos
Genie - Cost monitoring and usage
Hi Team,Genie is widely used within our department, and we would like to establish appropriate governance around its usage. Do we have any existing guidelines or recommended practices for this? In particular, we are looking for guidance on:Cost monit...
- 189 Views
- 3 replies
- 3 kudos
- 3 kudos
Hey @Sanjeeb2024, Good to note Genie usage in your org. Databricks does have solid governance tooling for Genie, and it's matured quite a bit since billing went live on July 8, 2026. Here is what you need to know. The source of truth for Genie spend ...
- 3 kudos
- 6147 Views
- 14 replies
- 10 kudos
Resolved! AgentBricks - Multi Agent Supervisor Issue
Hi, I am doing POC using AgentBricks and using Multi Agent Supervisor. I have configured 2 subagents.1. Genie Space2. UC Function to call LLM3. UC Function to plot chartsHowever, the agent is able to access and use only Genie space agent and not usin...
- 6147 Views
- 14 replies
- 10 kudos
- 10 kudos
We have a Unity Catalog SQL function that is scalar, takes one STRING parameter, returns STRING, and reads a single Delta table. It works when called directly in the SQL editor. Registered as the only tool on an Agent Bricks Supervisor agent, every c...
- 10 kudos
- 206 Views
- 3 replies
- 2 kudos
Can Unity AI Gateway Model Service guardrails protect an existing LangGraph agent deployed as a Data
I have a LangGraph agent deployed as a Unity Catalog model on aDatabricks Serving Endpoint.Architecture:User↓Databricks Serving Endpoint↓UC Model: ai_workspace.agent.agent↓LangGraph agent↓LLM + toolsThe serving endpoint shows "AI Gateway enabled", bu...
- 206 Views
- 3 replies
- 2 kudos
- 2 kudos
AI Gateway Model Service guardrails are scoped to Databricks-hosted foundation models and external LLM endpoints, not to custom UC-registered models or agent-serving endpoints. The "AI Gateway enabled" flag on your endpoint provides usage tracking an...
- 2 kudos
- 39890 Views
- 23 replies
- 50 kudos
Databricks Announces the Industry’s First Generative AI Engineer Learning Pathway and Certification
Today, we are announcing the industry's first Generative AI Engineer learning pathway and certification to help ensure that data and AI practitioners have the resources to be successful with generative AI. At Databricks, we recognize that generative ...
- 39890 Views
- 23 replies
- 50 kudos
- 178 Views
- 1 replies
- 0 kudos
Best Practices for Deploying Custom LLM Pipelines on Databricks?
Hi community,We are currently designing an enterprise-grade LLM pipeline on Databricks to handle end-to-end data processing, model fine-tuning, and inference serving.While Spark handles our data orchestration effectively, we are looking at optimizing...
- 178 Views
- 1 replies
- 0 kudos
- 0 kudos
@exrwebflowai Model Serving and Routing Architecture Hybrid setup anchored by Databricks Model Serving / Unity AI Gateway gives the best balance between deterministic latency and governance for production workloads. Use Provisioned Throughput endpoin...
- 0 kudos
- 113 Views
- 0 replies
- 0 kudos
Premium pay-as-you-go account still blocked by Databricks-set rate limit of 0
Hello,I’m having an issue using the Databricks Foundation Model API.My account is on the Premium plan, I have a valid payment method attached, and I currently have trial credits available. However, when I try to use the GLM Foundation Model endpoint,...
- 113 Views
- 0 replies
- 0 kudos
- 296 Views
- 1 replies
- 1 kudos
How Can a Databricks App Render the Same Detailed Response as the Genie UI?
I’m building a Databricks App with a Genie Space at the core and have run into a difference between the Genie UI and the Genie Conversation API.For the same business question, the Genie web UI can produce a detailed response containing an executive s...
- 296 Views
- 1 replies
- 1 kudos
- 1 kudos
Checked the current Genie REST API reference for this rather than guessing, a few concrete answers. Query attachment result data: GET /api/2.0/genie/spaces/{space_id}/conversations/{conversation_id}/messages/{message_id}/attachments/{attachment_id}/q...
- 1 kudos
- 231 Views
- 1 replies
- 0 kudos
Agent mode: will per-turn context reporting be added, or is there another way to read it?
Genie spaces are steered by a semantic layer: text instructions (e.g. "when the user says 'sales', always filter to region = 'EMEA'") and example question→SQL pairs.We read turn payloads programmatically — via the message endpoint behind the Genie UI...
- 231 Views
- 1 replies
- 0 kudos
- 0 kudos
Checked the current Agent mode Responses API docs on this (docs.databricks.com/aws/en/genie-agents/api) and your read looks right, not a gap in your search. The response stream only documents four output item types: reasoning, function_call, function...
- 0 kudos
- 381 Views
- 2 replies
- 1 kudos
Resolved! Custom Agent traces only showing basic input and output
I've been working with MLflow Agent Server deployments using the OpenAI Agents SDK hosted both locally and in Databricks Apps. Currently, tracing is instrumented with:set_trace_processors([]) mlflow.openai.autolog()Locally, everything works great and...
- 381 Views
- 2 replies
- 1 kudos
- 1 kudos
@taniumalloy Unity Catalog trace storage provides additional benefits beyond trace detail - unlimited storage, queryability for analysis and debugging, Unity Catalog governance and permissions and compatibility with the latest features. Trace richnes...
- 1 kudos
- 5674 Views
- 13 replies
- 3 kudos
Resolved! RLS in Genie Space
I am developing a Conversational BI Solution using Genie. There are users from different roles and we need to restrict the rows returned based on the user's role. Typically RLS. I understand from documentation Genie leverage the RLS setup on the Unit...
- 5674 Views
- 13 replies
- 3 kudos
- 3 kudos
This post explains the solution to your problem.Multi-Tenant Genie Spaces: Working Demo | by Rohit Bhagwat | Medium
- 3 kudos
- 470 Views
- 1 replies
- 0 kudos
Databricks-hosted Foundation Model APIs blocked by workspace rate limit of 0
Hello,My Databricks-hosted Foundation Model endpoints appear READY, but every runtime invocation is blocked by a workspace-level quota.Workspace details:- Workspace ID: 7474647458172567- Workspace URL: https://dbc-731cb41b-741e.cloud.databricks.com- ...
- 470 Views
- 1 replies
- 0 kudos
- 0 kudos
@APIUser4827 What you are encountering is the expected behavior in free edition. Databricks imposes a hard limit of 0 on premium, high demand Foundation Models especially - Claude and GPT groups when a workspace is operating under a free edition.You ...
- 0 kudos
