# What we’ve learned building cloud agents

Source: [Cursor](https://cursor.com/blog/cloud-agent-lessons)  
Feed7 permalink: https://feed7.dev/p/cloud-agent-lessons-06dh9iq  
Published: Unknown  
Trust: Official Source (official_source)

## Why Included

Cursor's writeup on a year of cloud agents: complete dev environments matter most, a Temporal rewrite pushed reliability past 99%, and over 40% of Cursor's internal PRs now come from cloud agents.

## Source Summary

**The gist** Cursor published lessons from roughly a year of running cloud agents (June 2, 2026). Rebuilding from a work-stealing architecture onto **Temporal**, a durable-execution framework, took reliability from about 90% to past **99%**; the system now handles **50M+ actions daily** across 7M+ workflows, and **40%+ of Cursor's internal PRs** originate from cloud agents.

## Practical Implication

**Why it matters** The biggest quality lever was not the model but a **complete dev environment** — incomplete setups degrade agent output subtly instead of failing loudly. Cursor also decoupled the agent loop, VM state, and conversation state, and moved from harness-enforced double-checking toward **exposing tools** like the GitHub CLI as models improved. If you run agents remotely, prompt for **autonomy**: a blocked cloud agent can idle for hours unnoticed.

## Agent-Ready Context

**The gist** Cursor published lessons from roughly a year of running cloud agents (June 2, 2026). Rebuilding from a work-stealing architecture onto **Temporal**, a durable-execution framework, took reliability from about 90% to past **99%**; the system now handles **50M+ actions daily** across 7M+ workflows, and **40%+ of Cursor's internal PRs** originate from cloud agents.

**Why it matters** The biggest quality lever was not the model but a **complete dev environment** — incomplete setups degrade agent output subtly instead of failing loudly. Cursor also decoupled the agent loop, VM state, and conversation state, and moved from harness-enforced double-checking toward **exposing tools** like the GitHub CLI as models improved. If you run agents remotely, prompt for **autonomy**: a blocked cloud agent can idle for hours unnoticed.

**Watch out** These lessons reflect Cursor's scale and infrastructure. The **self-healing environments** direction — agents reporting missing secrets or blocked network access and fixing them, via the **autoinstall** project — is still research, not a shipped feature.

## Context Map

- Layer: agent
- Domains: coding
- Topics: cloud-agents, harness-engineering, agent-reliability

## Uncertainty

- These lessons reflect Cursor's scale and infrastructure. The **self-healing environments** direction — agents reporting missing secrets or blocked network access and fixing them, via the **autoinstall** project — is still research, not a shipped feature.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.