ENCO: Deploying Production-Scale Engineering Copilots
Authors:
- Yiwen ZhuYZYiwen Zhu
- Mathieu DemarneMDMathieu Demarne
- Kai DengKDKai Deng
- Wenjing WangWWWenjing Wang
- Nutan SahooNSNutan Sahoo
- Hannah LernerHLHannah Lerner
- Anjali BhavanABAnjali Bhavan
- Divya VermareddyDVDivya Vermareddy
- Yunlei LuYLYunlei Lu
- Swati BarariaSBSwati Bararia
- William ZhangWZWilliam Zhang
- Xia LiXLXia Li
Open Access
- 20 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2606-2616
Abstract
Software engineers frequently grapple with the challenge of accessing fragmented documentation and telemetry data, such as Troubleshooting Guides (TSGs), incident reports, code repositories, and internal tools maintained by different teams. In this work, we introduced ENCO, a comprehensive framework for developing, deploying, and managing copilots tailored to improve productivity in large scale production scenarios. The framework combines an innovative NL2SearchQuery module with a lightweight hierarchical agentic planner to enable accurate and efficient retrieval-augmented generation (RAG) for code, semi-structured data and documents. These components allow the copilot to retrieve relevant information from diverse sources and invoke the right skills with low latency to answer highly complex technical questions. Since its launch in September 2023, ENCO has demonstrated its effectiveness through widespread adoption, enabling tens of thousands of interactions and engaging over 1,000 monthly active users (MAUs). The system has been continuously optimized based on usage patterns and user feedback, resulting in measurable improvements in response relevance, latency, and user satisfaction.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models2023
- AutoTSG: learning and synthesis for incident troubleshooting2022
- TILDE: Term Independent Likelihood moDEl for Passage Re-ranking2021
- Towards intelligent incident management: why we need it and how we make it2020
- ColBERT2020
- Reliability Analytics for Cloud Based Distributed Databases2020
- LADRA: Log-based abnormal task detection and root-cause analysis in big data processing with SparkFuture Generation Computer Systems, 2019
- Today Was a Good Day: The Daily Life of Software DevelopersIEEE Transactions on Software Engineering, 2019
- Log-based Abnormal Task Detection and Root Cause Analysis for Spark2017
- Reciprocal rank fusion outperforms condorcet and individual rank learning methods2009