Field notesOn engineering with AI agentsLast entry 27 Sept 2026
Agents do the work.
People make the calls.
I'm Daniel Broadhurst, a full-stack engineer. These are my notes on building real software with AI agents in the loop: how to structure the work, where a person should decide, and what to leave out.
Fig. 1 · How a feature moves
agentyou
- 01ResearchAn agent writes the brief and picks the lane: feature or fix.
- 02PrototypesThree genuinely different takes. You pick one.
- 03PlanA spec, or questions. You only answer if it asks.
- 04BuildAgents implement, run the checks and open a draft PR.
- 05IterateYou try it running. Five minutes beats a green test run.
- 06ReviewTwo reviewers on different models argue. You tick what’s worth fixing.
- 07LaunchDocs and the demo ship alongside it.
Contents
Every post →- 01Direct, SQS, EventBridge or Step Functions? What 160 Lambda Benchmarks SayI benchmarked four ways to chain AWS Lambda functions for my MSc. Managed orchestration adds a ~1.5 s routing tax, 512 MB is the memory sweet spot, and SQS catches up.27 Sept 2026 · 6 min read
- 02How AI Agents Scale Software Engineering: The Agentic WorkflowThe agentic workflow: how a pipeline of AI agents acting as product manager, architect, engineer and QA can scale software engineering without cutting quality.12 Jan 2026 · 9 min read
- 03Production-Grade AI Agents: A Survival Guide for Engineering LeadersWhy AI agent prototypes fail in production, and what engineering leaders need instead: reliability, cost controls, observability and PromptOps.5 Jan 2026 · 9 min read
- 04How to Write Robust Prompt Files for GitHub Copilot in VS CodeHow to write reusable prompt files for GitHub Copilot in VS Code: where they live, the anatomy of a robust prompt, and examples for refactoring and tests.20 Dec 2025 · 6 min read
- 05Comparing the Latest AI Agent Frameworks in 2025A practical comparison of TypeScript AI agent frameworks in 2025, including the Vercel AI SDK, LangChain.js and Mastra: features, trade-offs and when to use each.20 Nov 2025 · 9 min read
- 06Create Jira Tickets from VS Code with GitHub Copilot and MCPSet up VS Code, GitHub Copilot and MCP servers for Sentry and Atlassian to create well-structured Jira tickets straight from your editor.9 Oct 2025 · 6 min read
- 07Event-Driven Architecture on AWS: EventBridge, Lambda, SNS and SQSAn introduction to event-driven architecture on AWS: how EventBridge, Lambda, SNS and SQS let loosely coupled services communicate through events.25 Jun 2023 · 6 min read
- 08AWS Serverless with Node.js 22: Lambda, DynamoDB and SAMAWS serverless with Node.js 22: build a TypeScript Lambda that writes to DynamoDB with the AWS SDK v3, test it with Vitest and deploy it using AWS SAM.21 Jun 2023 · 12 min read
Liked this?
Get the next field note
New posts and tools on engineering with AI agents and serverless, when they're ready. No schedule, no spam.
About
I build robust back ends and interfaces people enjoy using, mostly in TypeScript on AWS.
Lately I spend my time on the question every team is asking: how do you get real, shippable work out of AI agents without becoming the bottleneck? This is where I write up what's worked. New here? Start with the series.
Say hello —
hello@danielbroadhurst.co.ukSet in Newsreader, Inter and Caveat.
Built with Astro, served from Cloudflare.