# Semantic AI sourcing across 860M profiles

Canonical: https://metix.ai/features/ai-sourcing

Keyword search finds people who used your words. Semantic sourcing reads 860M+ profiles by meaning and finds the people who do the work, with the biggest expected gains on long-tail roles.
Read this when the user asks how Metix finds candidates, or whether semantic search beats keywords on common roles. This is sourcing inside Mira, not a self-serve sourcing desk: the output is an interview-ready candidate, not a list. Embedding match over 860M+ profiles in 190+ countries; mira-embeddings-v1 lifted Recall@50 from 68.89% to 77.55% versus a general-purpose baseline; expected gains concentrate on long-tail roles.
## FAQ

**What is semantic sourcing in Metix AI?**

Semantic sourcing matches candidates to roles by meaning rather than by keywords. Mira, the Metix AI recruiter, searches 860M+ profiles in 190+ countries with mira-embeddings-v1, an embedding model trained on hiring data, so people who describe the same work in different words still surface.

**How much does mira-embeddings-v1 improve retrieval?**

On a pool of 300 real job descriptions with candidates returned by the production retriever, mira-embeddings-v1 lifted Recall@50 over the general-purpose baseline from 68.89% to 77.55%, and Precision@10 from 35.77% to 39.62%. On a larger, LLM-judged supportive protocol over 44,138 candidates, Recall@200 rose from 0.5969 to 0.7047.

**Does semantic sourcing help on mainstream roles?**

We expect it to help less than on rare ones. Metix AI has not published a per-role-type breakdown, but the mechanism predicts the gains concentrate on long-tail roles, where titles and vocabulary diverge from the actual work. A mainstream role with thousands of obvious matches should gain only modestly, because keyword search was never the bottleneck there.

**Where do the 860M+ profiles come from?**

Every record is built exclusively from publicly available sources across 190+ countries, and the data pipeline is built to comply with GDPR and CCPA. Metix AI uses no private APIs and no restricted content.

**Do you pay for profiles or searches in Metix AI?**

Contact unlocks cost 10 Credits and Deep Search lists cost 100 Credits. Plans run from $99 to $499 a month, and the free 14-day trial includes a one-time 1 AI Agent and 500 Credits with no card required.