Success Stories
/
From Financial Information to Market State: Exa Tests Pyth for Agentic Search
From Financial Information to Market State: Exa Tests Pyth for Agentic Search
The collaboration explores how Exa’s agentic search can use Pyth’s real-time and historical market data to answer financial questions in one workflow.
AI
Challenge
Financial research tasks need two kinds of information: what the world is saying and what markets are doing.
Exa has built search and agent infrastructure for researching information across the web and premium data partners. Pyth provides structured financial market data, including current prices, historical observations, and candlestick data.
An agent can search the web to understand why an asset moved, identify the companies involved in an event, and compare commentary from different sources. But a useful financial answer may also depend on the current price, the price at a specific timestamp, performance over a defined period, or the relationship between several assets.
Those observations need to be retrieved from structured market data rather than inferred from articles, search results, or secondary commentary.
For Exa, the challenge was connecting specialist financial data to the same agentic search workflow as web research, allowing agents to combine market information with market state in a single response.
Solution
Exa is testing Pyth as a market-data layer for its agentic search.
Through MCP, Exa’s agents can research an event or financial question while Pyth provides the relevant market data. The agent can then combine both inputs into one structured answer.
Example Workflow
For example, a user could ask:
“What happened to this company after its latest earnings announcement, and how did its stock perform over the following five sessions?”
Exa can identify the announcement, summarise the relevant details, and surface the information needed to understand the event. Pyth can retrieve the corresponding market data for the requested period. The agent can connect the two and present the result in a single response.
The value is not simply in adding another data source. It is in giving the agent the right source for each part of the question.
Impact
The collaboration is in an early testing phase, with the immediate goal of understanding where market data adds the most value inside agent workflows and how agents request it in practice.
By connecting web research with structured market data, Exa’s agents can connect news, filings, and company research to current and historical market observations. This can enrich analysis with a direct view of how the market responded.
The workflow creates a foundation for more sophisticated financial applications, including event-driven research, cross-asset analysis, portfolio monitoring, automated market reports, prediction-market applications, and chart and time-series generation.
