10 stories
Better code retrieval does not automatically mean better task completion. Here is how to measure retrieval, agent performance, and cost without confusing one for another.
Regulated engineering teams must prove which files an AI agent read before it shipped a change. How scoped retrieval turns agent context into an audit trail.
Code Finder runs its own search loop and hands your coding agent the exact files and line ranges, faster and cheaper than the agent searching on its own.
The bottleneck in most large-scale migrations is not the engineers or the plan. It is that the tools cannot see the whole codebase.
On nine CodeScaleBench tasks designed to evaluate agent effectiveness in large codebases, Claude Sonnet 4.6 with the Sourcegraph MCP server outscored Fable 5, winning six of nine at roughly half the cost for each point of quality.
Data from 1,281 agent runs across 40+ large open source repos reveals five repeatable failure patterns in coding agents, and the infrastructure fixes for each.
AI added new ways to search code, but not all of them apply to every problem. Here’s how to choose between Code Search, Deep Search, and MCP.
While direct API calls seem cheaper and easier, they lack the safety layer large organizations rely on. Tool connection protocols aren't dead; they remain vital for security, governance, and centralized control in big teams.
The initial findings from CodeScaleBench, a new benchmark designed to evaluate coding agents against the true complexity of enterprise software development, including large codebases and multi-repository tasks.
Today, we're announcing Sourcegraph 7.0, a release that marks the beginning of a new chapter for our company and product.
Showing 10 of 10 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from Sourcegraph Cody Blog
Join 15,000+ AI enthusiasts
