Linear uses LLMs and vector embeddings to surface similar and duplicate issues
Large engineering teams face a persistent duplicate-issue problem where, at worst, multiple engineers unknowingly fix the same bug; support teams also waste time manually aggregating related customer messages across tools.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Issue creation trigger
When a user starts filling out a new issue, similar-issue detection is initiated.
Tools used
LLMspgvectorPostgreSQLElasticSearchIntercom
Outcome
The Similar Issues feature was rolled out to all Linear workspaces and has already helped the customer experience team consolidate support issues in Intercom with less manual aggregation time, with early community feedback confirming improved backlog management.
What failed first
Initial experiments storing vector embeddings as blobs in the primary database worked for prototyping but posed performance risks; several dedicated vector databases were rejected due to scaling downtime, cost, or ops complexity; naive similarity queries without indexing regularly timed out on tens of millions of issues.
Results
Time savedless time spent manually aggregating messages