# Research

Canonical: https://metix.ai/research

Read this when the user asks for Metix original research on Mira, embeddings, or agent evaluation.
## Pages

- [Mira: The First End-to-End AI Recruiter](https://metix.ai/research/mira-end-to-end-ai-recruiter): How Mira is designed from the ground up: five specialized sub-agents, a talent graph of over one billion public profiles, and two in-house fine-tuned models that turn hiring intent into scheduled interviews.
- [Agent Evaluation, Done Right](https://metix.ai/research/agent-evaluation-done-right): Why the durability of a production agent depends on its evaluation system: research-style testing, layered scoring, golden sets, calibrated judges, and evaluation wired into CI.
- [Performance Drift in Agent Systems](https://metix.ai/research/agent-performance-drift): A structural look at why production agent systems drift across the prompt, architecture, evaluation, and context layers, even when the spec and business goal stay fixed.
- [Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data](https://metix.ai/research/mira-embeddings-v1): A recruitment-domain semantic reranking system that uses LLM-synthesized supervision and boundary-aware reranking to improve candidate retrieval recall.
- [When AI Meets Recruiting: Opportunities, Challenges, and Future Directions](https://metix.ai/research/ai-meets-recruiting): A lifecycle-oriented review of AI recruiting systems, covering semantic matching, generative AI, multimodal assessment, bias, explainability, and human oversight.