We’re building a new kind of data product for a new kind of investment process

LLM agents are increasingly being used to execute complex, market-wide investment strategies. These agents are expected to inspect, filter, join, rank, and verify across thousands of companies and years of filings in search of overlooked opportunities.

For these kinds of agentic tasks, the bottleneck is not the model or the agent harness, it's the data.

Traditional APIs and MCP servers are useful for known lookup tasks, but they are often a poor interface for exploratory market-wide research. They require the agent to make repeated network calls to gradually assemble enough context before the real analysis can begin.

Agents do their best work when the data contract is predictable. They can search it, reshape it, query it, write scripts against it, and iterate without guessing how each source file or endpoint behaves.

So we're building an agent-first data service that gives agents the data they need in a format they can depend on.

Here's how it works.

Chadwin exposes structured SEC-derived data through an authenticated API. The API is designed for workflows that need stable identifiers, source filing links, and normalized response shapes instead of raw EDGAR scraping.

For our beta launch, the API includes insider buying and selling for the US market. Over the next few months, we're expanding the data offered, including institutional holdings and normalized financial statement data.

The agent can work with this data using the tools it already knows how to use: HTTP clients, TypeScript, Python, DuckDB, pandas, Polars, shell scripts, queues, and customer-owned databases.

When deeper evidence is needed, the API can fetch the full source filing view for an accession. The goal is to make source evidence available without forcing each customer to build a private SEC ingestion system.

Behind the scenes, Chadwin runs a data pipeline that prioritizes agent ergonomics. We fetch, transform, normalize, and serve financial data with attention to source provenance, stable schemas, and practical downstream integration.

We think your agents will love it.