---
type: "post"
id: "factory-is-partnering-with-databricks-to-bring-autonomous-400e46"
slug: "factory-is-partnering-with-databricks-to-bring-autonomous-400e46"
title: "Factory is partnering with @databricks to bring autonomous software engineering to enterprise data and AI."
description: "Factory and Databricks are presenting enterprise modernization as one engineering workflow across data and dependent applications."
retrieval_nugget: "Factory and Databricks are presenting enterprise modernization as one engineering workflow across data and dependent applications."
published_at: "2026-10-19"
updated_at: "2026-10-19"
record_date: "2026-10-19"
date_kind: "published_at"
topics: ["coding-agents","enterprise-agents","workflows"]
source_urls: ["https://factory.com/news/databricks-partnership"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:factory-is-partnering-with-databricks-to-bring-autonomous-400e46"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:3e26eb1457fb350ac0cd61299bee03c01cc5879c9a8f74cb2a01695abbcfeaf9","reviewed_at":"2026-10-19T17:05:21.911Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":2,"watch_condition_count":2,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"The durable integration surface for agentic software is becoming a small family of protocols that separate models and harnesses from tools, services, interfaces, and other agents.","observed_facts":[{"text":"The source says Factory Droids work across application code, data pipelines, SQL, tests, and available documentation to trace application dependencies.","source_urls":["https://factory.com/news/databricks-partnership"]},{"text":"The source says Factory can use Databricks API access to create and run jobs, execute queries to validate results, and deploy applications.","source_urls":["https://factory.com/news/databricks-partnership"]},{"text":"The source describes an enterprise migration involving petabytes of data and hundreds of thousands of tables.","source_urls":["https://factory.com/news/databricks-partnership"]},{"text":"The source says qualifying customers may purchase Factory through Databricks Marketplace using up to 10% of their existing Databricks commitment.","source_urls":["https://factory.com/news/databricks-partnership"]}],"mechanism":"Shared workflow lets agents connect dependency analysis and migration planning to execution and validation against the data platform.","why_now":"The source frames data modernization and software modernization as linked work, with application dependencies becoming the next challenge after data movement.","implications":["Enterprise agent value may come from coordinating changes across data and application boundaries, not merely generating code.","The integration makes governance and API-mediated action part of the agent workflow, while leaving engineers to review plans and resolve ambiguous business rules."],"evidence_boundary":"These are vendor claims and an illustrative customer migration; the source does not establish completion, measured productivity gains, or independent validation.","watch_conditions":["Watch for independently verifiable migration outcomes, including whether dependent applications pass compatibility checks and reach production.","Watch whether the workflow demonstrates repeatable validation across application and data changes."],"related_records":[],"new_branch_reason":"No prior New Runtime analytical record was supplied, so this announcement starts a distinct record without asserting an invented relationship."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/factory-is-partnering-with-databricks-to-bring-autonomous-400e46/","markdown":"https://newruntime.com/posts/factory-is-partnering-with-databricks-to-bring-autonomous-400e46.md","json":"https://newruntime.com/posts/factory-is-partnering-with-databricks-to-bring-autonomous-400e46.json"}
related_shifts: ["coding-agent-general-workbench"]
---

# Factory is partnering with @databricks to bring autonomous software engineering to enterprise data and AI.

## Retrieval answer

Factory and Databricks are presenting enterprise modernization as one engineering workflow across data and dependent applications.

Factory and Databricks are presenting enterprise modernization as one engineering workflow across data and dependent applications. The thesis is: The durable integration surface for agentic software is becoming a small family of protocols that separate models and harnesses from tools, services, interfaces, and other agents. This announcement is a partnership, not evidence that a new protocol has emerged; the relevant mechanism is the joining of Factory’s engineering agents to Databricks-governed data and execution capabilities.

The source says Factory Droids can inspect application code, data pipelines, SQL, tests, and documentation to trace dependencies, then use Databricks API access to run jobs, queries, and deployments. It gives an enterprise example involving petabytes of data and hundreds of thousands of tables, while explicitly framing the work as rebuilding applications after much of the data had moved. The mechanism is: Shared workflow lets agents connect dependency analysis and migration planning to execution and validation against the data platform. Why now: The source frames data modernization and software modernization as linked work, with application dependencies becoming the next challenge after data movement.

The first implication is: Enterprise agent value may come from coordinating changes across data and application boundaries, not merely generating code. The evidence boundary is: These are vendor claims and an illustrative customer migration; the source does not establish completion, measured productivity gains, or independent validation. The source also says qualifying customers can buy Factory through Databricks Marketplace using up to 10% of existing Databricks commitment. The first watch condition is: Watch for independently verifiable migration outcomes, including whether dependent applications pass compatibility checks and reach production. Treat this as a distinct record because no prior New Runtime analytical record was supplied; no earlier record is assumed.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Coding Agents](https://newruntime.com/topics/coding-agents.md): Explore the coding-agents topic hub.
- topic hub: [Enterprise Agents](https://newruntime.com/topics/enterprise-agents.md): Explore the enterprise-agents topic hub.
- topic hub: [Workflows](https://newruntime.com/topics/workflows.md): Explore the workflows topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)