Founding Team

Founding partners Michael, Dean, and Dustin have built and deployed critical AI infrastructure adopted by 2M+ developers and some of the world's largest enterprises. They have built agent harnesses, large-scale retrieval systems, APIs, search and agent evals, and agent integrations. They are active contributors to the open source AI ecosystem. The following body of work grounds that claim:

Tavily Search API: a web search engine for agents that has served over a billion all-time queries and tens of millions of queries per day, used by more than 2 million developers. The MoE team designed and built a multi-billion document index of the web, with systems spanning scraping, search algorithms, embeddings, rerankers, caching, and LLM inference.
Tavily Platform: designed and built the Tavily platform used by millions of developers and enterprises, including billing, usage monitoring, and dashboards.
Tavily Research API: a deep-research harness that ranked state-of-the-art on HuggingFace's DeepResearch Bench at launch, outperforming the deep-research offerings from OpenAI, Perplexity, Claude, and Gemini. (benchmark writeup)
Evaluations: designed and ran large-scale search and agent evaluations on public benchmarks, including SimpleQA and DeepResearch Bench. (Tavily search evals, DeepResearch Bench, SimpleQA)
Developer tooling: the Tavily CLI, agent skills, MCP server (2.1 million downloads), and SDKs.
Framework and cloud integrations: production integrations with Claude, OpenAI, Azure, Bedrock, Databricks, Snowflake, IBM, LangChain, OpenClaw, Weights and Biases, and others.

Start a Conversation Back to Home