# Inside the Team That Killed Mandatory Code Review — Quinn Slack, AMP

## Executive summary

The discussion outlines a paradigm shift in software development driven by AI agents, moving away from traditional local development environments and mandatory code reviews. The core argument is that cloud-based agent execution (via platforms like AMP/Orbs) enables unprecedented parallelism and efficiency, making older methods obsolete. This transition requires rethinking infrastructure, security models (e.g., using limited OIDC access instead of unfettered laptop access), and even version control systems.

## Key takeaways

- The Obsolescence of Local Development: Local development is becoming outdated because cloud-based agents (like those running in Orbs) allow for massive parallelization, enabling developers to run many tasks simultaneously without the friction or limitations of a local machine. The speaker notes that this shift benefits both developer experience and security.
- The Decline of Mandatory Code Review: Speakers claim that mandatory code review is 'dead' for modern, agent-driven workflows. This change is attributed to the high trust and accountability built into small, highly skilled teams using agents, allowing fixes to be deployed rapidly (e.g., 15 minutes after detection) rather than waiting days.
- The Rise of 'Jellyware' and Mini-Apps: Software is moving toward highly customizable, forkable mini-apps (or 'jellyware') rather than monolithic packages with fixed settings screens. Agents are positioned as the ultimate configuration layer for any software.
- Cloud Infrastructure is Key to Agent Security: Running agents in a controlled cloud environment (like Orbs) is argued to be significantly more secure than running them on an unmanaged developer laptop, which can grant unfettered access and pose security risks.

## Technical details

- AMP/Orbs Architecture: AMP (Agent Model Platform) utilizes 'Orbs'—a remote, cloud-based environment for running agents. This setup allows users to run multiple tasks in parallel and provides a stable dev server view within a portal, eliminating the need for local development.
- Security Model (OIDC): To mitigate security risks associated with cloud agents, the recommended approach is granting intentionally limited access to resources (e.g., using OIDC for 30 minutes of read-only access to G-Cloud logs or a production database).
- Sandboxing Technologies: The discussion highlights the importance of robust sandboxes (like E2B) for running agents. These technologies are crucial because they provide reproducible, isolated environments necessary for complex agent workflows.
- Software Development Lifecycle: The trend suggests that traditional CI/CD processes may be evolving; while deterministic testing remains important, the reliance on exhaustive, manual CI runs is diminishing as agents become more reliable.

## Practical implications

- Build teams should prioritize cloud-native agent workflows over traditional local development setups to maximize parallelism and efficiency.
- Security architects must adopt granular access controls (like OIDC) for agents running in the cloud, recognizing that this model is inherently more secure than unfettered developer laptop access.
- Future software architecture should embrace 'jellyware' or mini-app patterns—highly customizable components with stable contracts—rather than relying on monolithic, fixed-setting applications.

## Topics

AI Agents, Software Architecture, DevOps/CI/CD, Cloud Computing, Remote Workflows, AMP, Orbs, E2B, SourceGraph

Source: https://www.youtube.com/watch?v=hvwtHZ5E27c