Most companies are starting to use more AI agents.One team may use a coding agent. Another team may use a search agent. Some teams may build their own agents for specific business workflows. Each agent may work well on its own.The real problem starts...
I want to add a set of Common Questions to my genie room as a guideline for users of what functions (i.e., question types) they are encouraged to choose from. I want it to be like a pseudo-menu, with functions F1, F2, and F3. The actual questions w...
Unfortunately, not at the moment. I've explored this as well, including the possibility of removing or customizing the menu/action buttons, but there currently isn't any control available for that.The only option is to include a list of suggested que...
Hi everyone,I'm trying to use the new Unity AI Gateway v2 (beta) endpoint from an agent deployed with the Mosaic AI Agent Framework and I'm running into what looks like a scope mismatch.Library versionsdatabricks-agents==1.11.0mlflow==3.12.0python~3....
This isn't a config problem on your end, it's a support gap. On-behalf-of auth for the standalone Unity AI Gateway beta endpoint isn't supported yet when you're deploying through databricks.agents.deploy(). Specifically, "ai-gateway" isn't a valid va...
I'm trying to use the Foundation Models API (databricks-claude-opus-4-8) in my workspace but every call returns this error:PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0.This happens both from notebook...
Hi, this one isn't fixable from the endpoint or AI Gateway settings, even though it looks like a rate limit you should be able to just raise. That "Databricks-set rate limit of 0" is a workspace trust tier restriction, not the rate limit you configur...
Is the "move fast and break things" startup mindset actually fatal for custom AI agent development?I read that rushing MVPs creates massive tech debt and unstable guardrails that cause projects to crash by year two.Have any of you hit this "year 2 wa...
Well, you can only break things which exist, so if you're delivering an MVP, nothing yet exists to be broken. This is kind of the wrong mindset, I think you should look at the agile process of "ship fast, ship small, iterate". Sometimes the iterati...
Hi everyone,Don't know where to put this specific question. I'm working on a reference data mesh implementation to connect and combine datasets to find matching trials for patients with a specific genetic profile. - Do you know anyone that might be i...
Hi @steff_horemans, Yes, this is absolutely fine to ask here. You're touching a few quite different areas, though... Trial matching/reference data design, GenAI extraction of eligibility criteria, and governance/serving of bespoke models. You’ll like...
On my first try with letting the Genie Code agent run multiple cells in my existing notebook, it fails at a certain cell that has previously been given the %skip magic. If I un-skip it, agent can then run the cell.Bug?
Hi, this definitely sounds like a bug, the fact that when you remove the %skip it runs fine. I did also find another report of this issue. The best bet is to file a support ticket for this. They will make sure it gets to the correct engineering team....
I have been thinking a lot about something Ali Ghodsi (CEO - Databricks) said recently. In a Bloomberg interview, he stated: "We already have artificial general intelligence. We don't need AI to get smarter. It is just lacking context."After years of...
I built an interactive experience to go along with this discussion. It lets you toggle context signals on and off and see how AI decisions change in real time.Try it here: aineedscontext.comIt covers four scenarios: grocery reorder decisions, paymen...
As a data engineer, I've been watching Genie Code closely since it went GA last month, and I wanted to share some honest thoughts here today not a feature dump, but how it's starting to change the way I think about my own role.Databricks recently sha...
Hi, Can genie code be accessed via databricks app or external app; or is it confined to Workspace UI only?
The question raised by @Gautam2809 was about Genie Code - specifically can you use it outside UI. And as of now there's no such an option.
Hi everyone,we're building a voice chatbot for a customer using a mix of technologies — Databricks, Azure AI Foundry, and a few external containerized services.Currently, we're tracking requests and logs via Lakebase with custom traces, but I'm now e...
Similar response to the one from WorksBuddy. Short answer: yes, it's supported, and there's a specific Databricks guide for your case. The tutorial you found is for local/IDE; the production-container equivalent is here: Trace agents deployed out...
Hey all — looking for confirmation on a behavior I'm hitting on the Foundation Model API (pay-per-token) Anthropic-compatible endpoint, in case anyone else has worked around it.What I'm doing: serving Claude models through /serving-endpoints/anthropi...
Hi @cormierjohn , Your understanding is correct. The validation rejecting a trailing assistant turn is happening at the FMAPI proxy layer before the request reaches Claude, so any client that uses Anthropic's prefill primitive will 400 against this e...
SpoilerHi,I am experimenting with ai-dev-kit and would like to ask whether there are any best practices, demos, or safety guardrails that were followed when using it. Specifically recommended settings for a limited-access PAT for dev-ai-toolkit.Thank...
@skarangi_349 As this is not a official DB product hence there's no such guide or docs. Best would be to follow the creators - https://www.youtube.com/@DustinVannoyYou may check other videos over youtube as well.
But for all I can know are these limits intentional?Empathy for the Genie (image(1))---This feels a little short sighted. Almost the like, in some ways, a terminal is still more elevated. AI prompt certainly won't be a challenge to HAL9000 anytime so...
I was looking forward to using there openAI responses API when the new gpt-oss models were added to Databricks.The openAI website states these model are compatible with the responses API.However, it does not seem to support it on Databricks. See erro...
Great discussion here—this highlights a real gap between the Chat Completions API and the newer Responses API. It’s clear the Responses API is the direction forward, especially with better multi-modal and tool-calling capabilities, but the lack of su...
