Arca runs its financial services business on long-horizon agents, not with them
AI Engineer · youtube · 2026-10-24
The AI Engineer channel interviews Aman Singh, who leads AI at Arca, an AI-native financial services firm where agents don't just assist — they run the business. Long-horizon agents own a client goal end to end across days of stop-start work via:
- A signal system keeping agents aware of emails, calls, custodian events, and in-app actions
- Operational context and a harness to execute the work
- Persistent memory across sessions
- Shared spaces where agents pull in the right person at the right time
The result: agents prompt people more than people prompt agents, and the firm steers the business by steering its agents. The talk also covers primitives of long-horizon work, handling a messy real world, six months of emergent complexity, and the difference between using AI tools and being AI-native.
More from coding & agent
- Nat Eliason builds SlopEraser, a Chrome extension that turns highlighted text rewrites into batch agent prompts — nateliason · 2026-10-24
- Claude Code helped uncover 14 speaker-muted AirTags hidden across his family's cars and bags — luisdans · 2026-10-24
- Should an AI call agent keep running when one tool goes down? A degraded-mode proposal — SubtleInterval_4449 · 2026-10-24
- Claude Desktop blocks local models; users bypass it with a loopback proxy trick — pneuny · 2026-10-24
- OpenAI ships Automations in Agents API for scheduled agent tasks — OpenAIDevs · 2026-10-24
- AGENTS.md explained: one root Markdown file to rule every AI coding tool — adnan_hashmi · 2026-10-24