QCon London 2026: Shipping Constantly with Humans and Beyond at Monzo

2026-03-17 · Source: InfoQ · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Advanced, short

Summary

At QCon London 2026, Monzo's principal engineer Suhail Patel detailed how the bank's developer platform enables shipping hundreds of daily changes across over 3,000 microservices, leveraging LLM-based tooling like Claude and Cursor to generate code conforming to "Backend 101" standards and allowing non-engineers to address technical queries. The "tenancies" system provides lightweight, isolated staging environments for parallel testing of individual service changes, significantly accelerating the development lifecycle. Monzo enforces mandatory, high-signal quality checks, including LLM-written Go AST-based syntax checkers and Semgrep, to maintain trust and compliance, while robust production observability and a multi-party authorized internal CLI support reliable operations and efficient LLM interaction. Patel emphasized investing in composable tools, rapid iteration, and standardized technology choices to focus on business problems.

Key takeaway

Monzo's developer platform, augmented by LLM-based tooling, enables shipping hundreds of daily changes across 3,000+ microservices in a regulated environment. LLMs like Claude generate 10-20 code implementations in hours, learn from 3,000+ repos, and write Go AST-based syntax checkers, while a "tenancies" system provides rapid, isolated testing. This accelerates development, improves code quality via mandatory checks, and empowers non-engineers, offering a scalable model for AI-augmented software delivery in compliant systems.

Topics

• Developer Platforms
• Microservices Architecture
• LLM-based Development Tools
• Isolated Staging Environments
• CI/CD Quality Assurance

Best for: CTO, VP of Engineering/Data, Director of AI/ML, Software Engineer, DevOps Engineer, MLOps Engineer

Related on AIssential

• Giving Developers Claude Code with Azure API Management and Claude Models in Microsoft Foundry — Centralize "Claude Code" access via Azure APIM to manage authentication, usage, and cost for developers.
• A new era for software testing — LLMs can significantly enhance software QA and testing by automating complex, traditionally manual processes without compromising quality.
• 🎙️ This week on How I AI: How Intercom 2x’d their engineering velocity with Claude Code — Intercom doubled engineering velocity in nine months by deeply integrating Claude Code, emphasizing telemetry and cultural permission.
• LLM Eval Workflow: How to Build Reliable AI Quality Gates Without Vibes — Reliable LLM evaluation requires a structured workflow integrating diverse checks and continuous feedback, not just tools.
• QCon London 2026: Tools That Enable the Next 1B Developers — AI tooling is rapidly expanding the developer base, necessitating new approaches to tool design and platform architecture.
• Podcast: From Java EE to Quarkus and LLMs: Adam Bien’s Playbook for Boring, Future‑Proof Systems — Standardized, low-dependency Java systems, especially with BCE, are future-proof and optimize LLM code generation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by InfoQ.