Superpower Daily

Superpower Daily

Your reading space

Sign in
Baseten’s Base Labs Partners With Hugging Face and Goodfire on...OpenAI Says an Astra Training Model Inserted Its Own Jailbreak...Meta’s Oversight Board Orders Facebook to Remove Two AI Deepfak...European Commission Proposes Barring Chatbots From Simulating R...Databricks Introduces Omnigent Beta for Agents That Run Across...Lambda Publishes an AI Evaluator for Multi-Turn Image EditsBaseten’s Base Labs Partners With Hugging Face and Goodfire on...OpenAI Says an Astra Training Model Inserted Its Own Jailbreak...Meta’s Oversight Board Orders Facebook to Remove Two AI Deepfak...European Commission Proposes Barring Chatbots From Simulating R...Databricks Introduces Omnigent Beta for Agents That Run Across...Lambda Publishes an AI Evaluator for Multi-Turn Image Edits
Swipe

Databricks Introduces Omnigent Beta for Agents That Run Across Coding Tools

The managed layer promises one agent definition and a single control surface, but its featured search provider’s performance figures are vendor-reported.

By 2 min read
Databricks Introduces Omnigent Beta for Agents That Run Across Coding Tools
Databricks Introduces Omnigent Beta for Agents That Run Across Coding Tools

Listen to this story

The audio brief

About 1:27
0:001:27
Read transcript
Databricks has introduced Omnigent, a managed beta that lets engineers define an agent once, then run it through Claude Code, Codex, Cursor, Pi, custom agents, or direct APIs. The core promise is portability: the model, tools, policies, and limits stay attached to the agent definition while the underlying agent harness changes. That gives teams a single setup and control layer instead of rebuilding the same agent for every coding environment or API. Omnigent also makes the web-search provider part of that setup. Databricks is featuring Nimble, which offers a lighter mode for broad discovery and a deeper mode that extracts content from pages, with controls for how many results come back. Databricks says Nimble can support multi-source search, extraction, cross-checking, and citations. For agents using Databricks-hosted models, calls run through Foundation Model APIs. The company says that centralizes cost tracking, audit records, and governance. The managed beta does come with deployment conditions: a workspace must be enabled, and the region must support Unity AI Gateway. The main claim still needs testing. Databricks cites Nimble’s own results, where web search lifted benchmark accuracy from 46 percent to 71 percent and cut search costs by half. Those figures are vendor-reported, with no methodology or task-level breakdown in the post. The thing to watch is whether that portability and search advantage holds up on customers’ real workloads.

Story brief

3 key points

Omnigent gives Databricks customers a portability layer for agent definitions: model, tools, policies, and limits can persist while execution moves among Claude Code, Codex, Cursor, Pi, custom agents, or APIs. The managed beta also lets teams standardize web search through Nimble and centralize Foundation Model API costs, audits, and governance. Access requires workspace enablement and a Unity AI Gateway-supported...

  1. 01

    Agent definitions can run through Claude Code, Codex, Cursor, Pi, custom agents, or direct APIs.

  2. 02

    Nimble offers light discovery and deep page-extraction modes, with configurable result counts.

  3. 03

    Databricks-hosted model calls use Foundation Model APIs for centralized cost tracking, audits, and governance.

Databricks has introduced Omnigent, a managed beta that lets engineers define an agent once and run it through Claude Code, Codex, or direct APIs. Nimble is positioned as the web-search provider, turning external retrieval into a choice made in the agent setup rather than one inherited from each runtime.

One agent spec, several ways to run it

The product is a layer above the agent harness, the environment that supplies the model and tools. Databricks says an Omnigent definition can retain its model, tools, policies, and limits while the underlying harness changes. Its documentation also lists Cursor, Pi, and custom agents among the supported paths.

For agents running on Databricks-hosted models, calls go through the company’s Foundation Model APIs. Databricks says that places cost tracking, audit records, and governance in one place. The managed version requires Omnigent beta enablement for a workspace and a region that supports Unity AI Gateway.

Nimble’s demonstration shows its web-search provider configured for an Omnigent agent. Video via nimbleway.com.

Web search becomes part of the spec

Nimble can be selected through Omnigent’s built-in web-search tool. Nimble says its integration offers a light mode for broad discovery and a deep mode that extracts page content; it also supports settings for the number of results returned. Databricks describes Nimble Web Search Agents as handling multi-source searching, extraction, cross-checking, and citation generation for research and enrichment work.

Selecting the provider
tools:
  builtins:
    - name: web_search
      search_provider: nimble

A performance case that still needs validation

Databricks cites Nimble’s testing, which reported that adding Nimble web search increased LLM benchmark accuracy from 46% to 71% and cut web-search costs in half. Those are vendor-reported results, not an independent comparison, and Databricks does not provide a methodology or task breakdown in its post.

The immediate appeal is operational: teams can keep the same agent definition while changing its harness or model, and can set one search provider across those runs. But the claimed quality and cost advantage remains a result for prospective users to test against their own workloads.

Sources

  1. docs.databricks.comdocs.databricks.com
  2. nimbleway.comNimble Is Now a Built-In Web Search Provider for Omnigent
  3. databricks.comThe Web Search Your Agent Inherited Isn't Good Enough

Loading discussion...