--- title: "How We Built DEmate: Taming LLMs for Data Engineering at Meta" url: https://daily.dev/posts/how-we-built-demate-taming-llms-for-data-engineering-at-meta-0vkrtgy3x source_url: https://medium.com/@AnalyticsAtMeta/how-we-built-demate-taming-llms-for-data-engineering-at-meta-d134e69637c5 type: article source: "Medium" published: 2026-07-02T13:10:42.363Z updated: 2026-07-02T14:21:29.778Z tags: ["llm", "ai-agents", "data-engineering", "prompt-engineering", "ai-assisted-development"] reading_time: 8 upvotes: 3 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How We Built DEmate: Taming LLMs for Data Engineering at Meta **[Medium](https://daily.dev/sources/medium_js)** · 8 min read · 3 upvotes · 0 comments ## Summary Meta's Analytics team built DEmate, an AI assistant tailored to their proprietary data engineering stack. General LLMs failed because they lacked knowledge of Meta's internal tools, custom SQL macros, and UDFs. The solution was a 'Recipe Architecture' — a four-phase execution loop (auto-selection, context injection, code generation, validation) backed by ~70 DE-specific recipes. Recipe Chaining with Progressive Disclosure keeps LLM context focused and reduces hallucinations. An AI-powered code review system enforces 20 quality rules for community-contributed recipes. Asynchronous validation was solved by integrating an Analytics Agent that monitors long-running test jobs and auto-updates diffs. DEmate is deployed across Meta's IDE extension, SQL interface, and task tracking tools, and an Omni Plugin architecture allows model-agnostic future-proofing. In five months, DEmate reached 3,500 weekly active users with an 80% code acceptance rate. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [LLM-native EL workshop on Data Talks Club](https://daily.dev/posts/llm-native-el-workshop-on-data-talks-club-y3f6g6knp) · dltHub · 1 upvotes · 0 comments - [Build LLM Agents Faster with Datapizza AI](https://daily.dev/posts/build-llm-agents-faster-with-datapizza-ai-mhn3pva1m) · Towards Data Science · 1 upvotes · 0 comments - [Case for AI powered Data Pipelines at OmbuLabs Blog](https://daily.dev/posts/case-for-ai-powered-data-pipelines-at-ombulabs-blog-wunyvktaw) · RUBYLAND · 1 upvotes · 0 comments - [Speeding up analytics with Databao](https://daily.dev/posts/speeding-up-analytics-with-databao-4pnaqkpng) · JetBrains · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#data-engineering](https://daily.dev/tags/data-engineering), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#ai-assisted-development](https://daily.dev/tags/ai-assisted-development) [View this post on daily.dev](https://daily.dev/posts/how-we-built-demate-taming-llms-for-data-engineering-at-meta-0vkrtgy3x)