Arca uses Claude for financial services
The story so far
Arca uses Claude to support long-term financial tasks, where the AI analyzes and proposes solutions, but humans retain final decision and execution rights. The agent can handle tasks up to ten days long, using internal memory systems for tracking. Arca employs models from Anthropic and OpenAI, selecting them based on internal benchmarks. The AI's operations are strictly limited to avoid client risk, using sandbox computing and additional measures for sensitive data. Arca presented this approach at a New York AI conference, emphasizing human oversight and AI's role in background work.
AI-written from the reports · Updated 18 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Latent SpaceAgents Prompt People: Using Agents for Long-Horizon Financial Work
Arca stated at the AI Engineers' New York Summit that its agents primarily handle background work, but human advisors retain final decision-making authority. Agents only analyze and propose solutions, with transactions executed by humans. Agent tasks can last up to ten days, and the company has developed an internal memory system to track task progress and responsibility allocation. They use models from Anthropic and OpenAI, automatically selecting models based on internal benchmarks via a custom harness. In terms of security, agent operations are strictly limited, involving no client risk, and they use sandbox computing and additional measures to handle sensitive data.