Databricks Community

DoTA

I'm trying to work out what a sensible guardrail looks like for each agent when several of them share a few serving endpoints.A plain token budget feels too blunt. An agent that retries a failing tool four times looks like a heavy user, while a cheap...

DoTA

I hope this is useful for anyone running Genie spaces or agents past the demo stage. This is a question more than a recommendation, because I have not found a pattern I fully trust yet. The situation: a Genie space or an agent sits on top of a handfu...

DoTA

Hi everyone, I hope this helps start a useful comparison of notes for those running agents on Databricks in production.Token cost per endpoint is easy to get. Tag the serving endpoints, and the custom tags propagate to system.billing.usage, where usa...

DoTA

I hope this helps for those who are trying to keep LLM costs under control on batch workloads. I have been looking at ai_decide (Beta) as a router rather than as a classifier, and it fits that job well. Sharing the pattern and the open questions, sin...

DoTA · 08-22-2026

A pattern that shows up repeatedly when people move a working Structured Streaming pipeline from "runs fine in a workspace notebook" to "runs in CI via Databricks Connect against serverless" is a ModuleNotFoundError that only appears in the second co...

DoTA

Thanks for sharing the demo. I haven't benchmarked it myself, so I'll add what I'd want to check before dropping a broker, rather than numbers.Zerobus removes the broker when Databricks is the only consumer of those events. If another system also nee...

DoTA

Yes, this is doable, and the pieces are already documented. Two parts.1. Get the Genie conversations into an MLflow experiment as traces, which you already know how to do. The MLflow cookbook page on Genie evaluation judges walks through tracing conv...

DoTA

On your closing question, the rule I'd use for the line: anything with a checkable ground truth, either inside the document or in a system of record, goes to deterministic logic, and the model only proposes. Amount in figures vs words, date validity,...

DoTA

Your worry is fair, but I'd push on where the dividing line sits. I don't think it should be team role (DE vs analyst). I think it should be how many other people depend on the output.A table that only one analyst reads can be as fragile as they like...

DoTA

Nice explainer. To answer your closing question: the first thing I'd ask is what changed week over week by SKU. A cost jump is nearly always one product or one SKU, rarely the whole total moving evenly, so that view finds the culprit fastest.One gotc...

Databricks Community

User Stats

User Activity

Per-agent guardrails: what do you alert on, tokens, retries, or cost per task?

How do you regression-test a Genie space or agent when a table or metric view changes underneath it?

How are you attributing agent cost per successful task, not just per token?

Routing between GLM 5.3 Flash and GLM 5.3 with ai_decide: a cheap router in front of ai_query

Databricks Connect + Serverless: Why "Module Not Found" Shows Up Only in CI, Not Interactively

Re: Bypassing the Message Broker with Databricks Zerobus Ingest

Re: Jev as Judge for Genie Agents

Re: Document AI is a pipeline, not a model

Re: Enable non-DE teams to build their own pipelines

Re: What Is – a system table? (Your Databricks bank statement)