February 2026 Summaries

Sourcegraph 7.0 introduces a fundamental shift in the company's approach by positioning its platform as a shared intelligence layer for both developers and AI agents, aimed at improving the understanding and management of large, complex codebases. This release addresses the challenges faced by AI coding agents, such as navigating cross-repository dependencies and understanding historical context, by providing a deep, reliable context similar to what seasoned developers rely on. Key enhancements include Deep Search via the MCP server, which allows agents to ask semantic, cross-repository questions and gain insights into architectural patterns, as well as improved workflow integration and a modernized UI. While some features are being deprecated, the focus remains on providing a reliable infrastructure that supports both AI-assisted and human development efforts. Sourcegraph 7.0 is designed to offer teams the dependable context needed to work effectively with production code, marking the start of a new era in AI-assisted development.

Sourcegraph developed DataBot, an AI-powered Slack bot designed to minimize context-switching for data analysts by addressing routine data inquiries, allowing the data team to focus on auditing rather than performing analyses. DataBot operates by leveraging various tools and custom data warehouse contexts to answer questions about user behavior, telemetry, and product metrics without human intervention, thus streamlining the process for quick questions that would otherwise disrupt analysts' deep work. The bot is equipped with a suite of tools, including BigQuery, PostHog, and Looker, and is guided by SCHEMA_CONTEXT, which helps it understand the business logic and data warehouse structure, ensuring accurate responses. By maintaining thread context, DataBot can handle follow-up questions seamlessly, building on previous answers for a cohesive dialogue. This shift allows data analysts to audit responses quickly, akin to reviewing pull requests, and drastically reduces the time spent on each query, as DataBot's capabilities improve with each interaction.

Deep Search is a tool designed to enhance the efficiency of Support Engineers by enabling them to investigate the root causes of issues in codebases without initial escalations. It allows engineers to ask questions in natural language and receive structured, evidence-backed answers including file paths, call flows, and recent code changes, thus bypassing outdated documentation and ineffective searches. This tool reduces the time spent on problem-solving from potentially hours to just a few minutes by simulating the insights of a senior engineer analyzing the codebase, providing a clear understanding of system behavior and potential causes of failures. Deep Search offers seamless integration with workflows, such as Slack, and can generate visualizations for better comprehension of system architecture. By minimizing the need for escalation, it improves response times, reduces interruptions for engineering teams, and enhances the overall efficiency of support operations. Michael Bali, a Senior Support Engineer at Sourcegraph, highlights its impact on both support and development teams, emphasizing its role as a productivity boost and investment in organizational code understanding.