The Replay is a weekly newsletter for dev and engineering leaders.
Delivered once a week, it’s your curated guide to the most important conversations around frontend dev, emerging AI tools, and the state of modern software.
Oct. 1: A spec-first workflow for building with agentic AI – What’s the best way to provide context for AI agents? The answer: establishing a “spec-first” workflow, according to Andrew Evans, Principal Engineer & Tech Lead at CarMax. Evans walks through a method for building a spec-first workflow using Claude Code.
Sep. 24: 6 easy ways to level up Claude Code – The future of AI-assisted development isn’t just about the model you use. It’s about how you shape it to fit your team. David Turnbull, Staff Content Design Engineer at Lingo.dev, shares six tips that help you move beyond simply entering prompts into a text box.
Sep. 17: How to stop your AI agents from hallucinating – How do you trust AI when you can’t reliably predict its output? Alexandra Spalato, full-stack developer and fractional AI officer, is using n8n to help devs move from “I think my AI works” to “I have measured its accuracy at 98% under these conditions.”
Sep. 10: What you actually need to build and ship AI-powered apps in 2025 – Shruti Kapoor writes about the four layers that underly every production-grade AI system: compute & foundational models, data & retrieval, deployment & orchestration, and observability & optimization.
Sep. 3: A dark age is coming for dev leadership if we automate away the ladder – Software engineer and YouTuber Jack Herrington warns that automating the very tasks that once taught devs how to think critically and debug in the wild could leave us without anyone to step into senior roles.