# Harvey — Why we Built our own Cloud Agent Infrastructure

- Company: Harvey (harvey.ai)
- Announced: 2026-06-01T14:00:00+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://www.harvey.ai/blog/why-we-built-our-own-cloud-agent-infrastructure
- Record: https://forck.live/items/17559-why-we-built-our-own-cloud-agent-infrastructure
- Subject: Harvey

Harvey built its own cloud agent infrastructure because existing managed runtimes from frontier labs and cloud providers do not meet law firms' requirements for multi-model support, zero data retention, and cost control. The company argues that single-model lock-in is untenable for firms with conflicted clients, and that zero data retention must be an architectural property rather than a post-hoc deletion feature.

## Evidence

Verbatim from https://www.harvey.ai/blog/why-we-built-our-own-cloud-agent-infrastructure:

> Managed agent runtimes are now emerging from the frontier labs — Anthropic's Claude Managed Agents and OpenAI's — and from the cloud providers building on AWS, Microsoft's Foundry, and Google. They're impressive, and we work closely with all of them to shape where this goes. So it's worth being precise about why we still run our own: serving law firms and regulated enterprises imposes a handful of requirements that none of them meet yet, and won't for a while.

---

Record: https://forck.live/items/17559-why-we-built-our-own-cloud-agent-infrastructure
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md