AgentsSeptember 9, 2026via AWS Machine Learning Blog
How Heurist Finance built an AI-native investment workbench on Amazon Bedrock AgentCore
Why it matters
AgentCore's agent infrastructure (payments, memory, code execution, observability) is shipping real features that let small teams deploy autonomous financial workflows. This is an inflection point: agents are moving from lab demos to production tools that integrate with existing enterprise systems.
Key signals
- Heurist Finance built on Amazon Bedrock AgentCore
- AgentCore features used: payments, Identity, Memory, Code Interpreter, Observability
- Use case: conversational AI investment workbench handling premium market data per query
- Sandbox isolation for analysis; full audit trail of agent actions
- Small team deployment (implication: low operational overhead)
- Live production system, not pilot
- AgentCore features deployed: payments, Identity, Memory, Code Interpreter, Observability
- Use case: conversational AI investment workbench
- Architecture includes sandbox isolation for analysis
- Per-query billing for premium market data
- Full audit trail of actions maintained
- Small team able to ship complex agentic system
The hook
Small fintech team built a production agent system on Bedrock AgentCore—not a pilot, but a live investment workbench handling real market data and auditable trades.
Learn how Heurist built Heurist Finance, a conversational AI investment workbench, on Amazon Bedrock AgentCore. This customer story shows how AgentCore payments, Identity, Memory, Code Interpreter, and Observability let a small team buy premium market data per query, isolate analysis in a sandbox, a…