Code Generation
Developing AI systems that automatically generate code from specifications, design documents, and natural language descriptions, advancing program synthesis and software development automation.
EVEREST
Data Systems Group · MIT CSAIL
Our mission is to establish the engineering principles for AI-driven data systems. We move beyond ad-hoc experimentation to build a foundation of new abstractions, reusable software components, and rigorous development tools.
Research Directions
Data Analytics
Building AI-powered systems for data analysis, transformation, and insight extraction, applying optimization techniques to make data processing more efficient and accessible.
Large Scale Retrieval
Developing efficient systems for retrieving relevant information from massive datasets, optimizing both accuracy and performance for real-world applications.
Agent Operations
Investigating operational frameworks for deploying and managing AI agents in production environments, addressing challenges in monitoring, debugging, and maintaining autonomous systems.
Agent Planning
Developing methods for AI agents to autonomously plan and execute complex multi-step tasks, combining reasoning, decision-making, and adaptive execution strategies.
Projects
D4: Design Doc Driven Development
D4 achieves a 54.8% average pass rate on the commit-0 benchmark, outperforming the next-best system by 14 percentage points. The system is an LLM-based compiler that generates code from design documents, treating design specifications as input and automatically producing implementation code.
Palimpzest
Palimpzest achieves a 90.3x speedup and 9.1x cost reduction on document processing benchmarks. The system applies cost-based query optimization techniques to AI-powered data processing, automatically selecting optimal combinations of models, prompts, and execution strategies for data transformation tasks.
A2rchi
A2rchi is an open-source RAG framework for AI support systems. The system enables retrieval-augmented generation for technical assistance and has been deployed at MIT (SubMIT system and multiple courses) and CERN for particle physics data processing support.
BRAD
BRAD (Blueprint for Relational Adaptive Databases) virtualizes cloud data infrastructures, automatically optimizing cloud database deployments across different storage engines and compute resources to balance performance and cost.
KramaBench
KramaBench is a comprehensive benchmark for evaluating AI agents on knowledge-intensive tasks. The benchmark provides a systematic framework for assessing agent performance across diverse scenarios requiring deep domain knowledge and reasoning capabilities.
Team
Affiliate Faculty
Postdocs
Tianyu Li
Postdoctoral Researcher
Jason Mohoney
Postdoctoral Researcher
Gerardo Vitagliano
Postdoctoral Researcher
Research Engineers
James Moore
Research Engineer
Students
Sushrut Borkar
PhD Student
Peter Baile Chen
PhD Student
Zhuohan (Joshua) Gu
PhD Student
Darryl Ho
PhD Student
Ferdinand Kossmann
PhD Student
Eugenie Lai
PhD Student
Markos Markakis
PhD Student
Amadou Latyr Ngom
PhD Student
Matthew Russo
PhD Student
Ziniu Wu
PhD Student
Geoffrey Yu
PhD Student
Alex Zhang
PhD Student
Anna Zeng
PhD Student
Sylvia Zhang
PhD Student
Xinjing Zhou
PhD Student
Publications
For a complete list of publications from Everest Lab members, please visit the DSG Publications page.
Sponsors
Our research is made possible through the generous support of industry partners and funding agencies who share our vision for advancing AI-driven data systems.
For sponsorship opportunities, please contact us at everest-info@csail.mit.edu
Contact
Lab Contact
Location
MIT Computer Science & Artificial Intelligence Laboratory
32 Vassar Street
Cambridge, MA 02139
Prospective Students
We welcome inquiries from prospective PhD students interested in AI-powered data systems. Please reach out to faculty members directly regarding research opportunities.