Overview
EvidInvest Research Agents deliver finished research, not raw data. Send one message over the Agent2Agent (A2A) protocol and get a completed task back.
Valuation Agent: ask in plain language ('Is Apple overvalued right now?') and receive a full report - company snapshot, DCF with year-by-year projections and WACC, bear/base/bull fair-value range, margin-of-safety analysis, and multi-period growth rates - as narrated markdown plus structured JSON artifacts.
SEC Filing Agent: ask a research question and receive exact SEC filing-section text with accession-numbered citations and sec.gov links, plus supply-chain relationships extracted from filings (supplier/customer edges with verbatim filing evidence).
Architecture buyers can trust: a reasoning LLM (Claude on Amazon Bedrock) understands the request, resolves company names to tickers and writes the narrative - but every figure is computed by EvidInvest's deterministic valuation engines and cited SEC indexes. The model is structurally unable to invent a number; if a data section is unavailable the report says so instead of guessing.
Choose the reasoning tier per request via the A2A configuration: 'haiku' (Claude Haiku, included), 'sonnet' (Claude Sonnet for deeper narrative, +1 credit), or 'none' (no LLM - pure engine output for buyers who narrate with their own model).
Pay-as-you-go credits, no subscription: a valuation run is ~5 credits, filing research ~2. Auth via two-legged OAuth (client-credentials) or API key.
Agent Card: https://mcp.evidinvest.com/.well-known/agent-card.json | Endpoint: https://mcp.evidinvest.com/a2a (JSON-RPC: message/send, tasks/get). Get credentials at evidinvest.com/developers.
Highlights
- Complete cited valuation in one A2A call: DCF, fair-value range, margin of safety, growth history - every figure from deterministic engines, never the LLM
- Per-request model choice: Claude Haiku included, Claude Sonnet premium (+1 credit), or bring your own model with engine-only output
- SEC research with accession-numbered citations and filing-derived supply-chain evidence; pay-per-call credits, no subscription
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/unit |
|---|---|---|
Access | Product access. Usage billed by EvidInvest in credits; nothing charged through AWS. | $0.00 |
Valuation report run | One Valuation Agent run: cited DCF, fair-value range, margin of safety, growth. | $0.25 |
SEC research run | One SEC Filing Agent run: cited filing research and supply-chain evidence. | $0.10 |
Model compute | Monthly pass-through of AI model compute for your runs; one unit per $0.01 of cost. | $0.01 |
Vendor refund policy
The product is free to subscribe through AWS Marketplace ($0.00); there are no AWS charges to refund. Credits purchased directly from EvidInvest are refundable within 14 days if unused - contact info@evidinvest.com .
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
Agent2Agent JSON-RPC endpoint (message/send, tasks/get; synchronous task completion). Agent Card at /.well-known/agent-card.json advertises skills and input/output modes. Reasoning by Claude on Amazon Bedrock; all figures computed by deterministic engines, with SEC claims carrying accession-numbered citations. Metered usage is reported to AWS Marketplace so charges land on the buyer's AWS invoice.
Support
Vendor support
Support via info@evidinvest.com . Documentation: https://evidinvest.com/developers . Agent Card:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.