Coding agents
A smarter way to run code migrations with less LLM context
Our short summary of Sourcegraph’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on sourcegraph.com (opens in a new tab)Problem
Scanning thousands of files for migrations flooded LLM context, driving up token costs.
Solution
Sourcegraph built Deep Search, a sandbox that runs scripts on search results, aggregates data, and returns concise CSV/JSON reports, feeding only the summary to the LLM.
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on sourcegraph.com (opens in a new tab)
JetBrains
Snowflake
Postman