{"podcast":{"title":"Beyond Coding","slug":"beyond-coding-4008849","podcast_index_feed_id":4008849,"rss_url":"https://anchor.fm/s/5bb57eac/podcast/rss","website_url":"https://youtube.com/@beyondcoding","image_url":"https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/15286211/15286211-1783929849661-8f9c7578a34b2.jpg","author":"Patrick Akil","episode_count":260,"summary":"For software engineers ready to level up. Learn from CTOs, principal engineers, and tech leaders about the skills beyond coding: from technical mastery to product thinking and career growth. Created by Patrick Akil","last_synced_at":"2026-07-23T02:20:33.013268+00:00","page_url":"https://stenobird.com/podcast/beyond-coding-4008849"},"episode":{"title":"AWS Veteran: The Agent Blueprint Behind 1,400 Engineers","slug":"aws-veteran-the-agent-blueprint-behind-1-400-engineers","published_at":"2026-07-22T12:00:00+00:00","page_url":"https://stenobird.com/podcast/beyond-coding-4008849/aws-veteran-the-agent-blueprint-behind-1-400-engineers","show_page_url":"https://stenobird.com/podcast/beyond-coding-4008849","url":"https://podcasters.spotify.com/pod/show/beyond-coding/episodes/AWS-Veteran-The-Agent-Blueprint-Behind-1-400-Engineers-e3mcb1k","audio_url":"https://traffic.megaphone.fm/APO3546385739.mp3","summary":"\"I need to stop using Opus. This doesn't work.\" That was Heitor Lessa's conclusion after a refactor cost him 200 million tokens, and it forced him to rebuild the entire agent workflow now used across 1,400 engineers. Heitor spent 11 years at AWS, built Lambda Powertools to 230 billion API calls a week, and in this episode he walks through the full SDLC workflow on screen, from discovery to merge check. In this episode, we cover: The product loop: discovery, whiteboarding, and the /roadmap command Spec-driven development with Open Spec and why vanilla setups fail Three model tiers: SOTA for planning, mid-tier for implementation, cheap models for reviews Merge checks with adversarial reviewers and attestations that catch agents fabricating test results The /retro command: using the Socratic method to make your workflow more deterministic If you're an engineer figuring out how to work with agents at team scale without losing trust in your codebase, this is the workflow to steal. This is also the first Beyond Coding episode with visuals on screen, so let me know what you think of the format. Timestamps: 00:00:00 - The Math Doesn't Add Up 00:00:43 - Amazon Hypergrowth: 11 Years, 8 Different Roles 00:03:29 - Learning From the Trenches as a Technical Account Manager 00:08:38 - Developer Identity and the Birth of Lambda Powertools 00:10:20 - The Hard Parts of Working in Public 00:13:12 - How Powertools Hit 230 Billion API Calls a Week 00:16:42 - Career Advice: Learn Adjacent Roles, Not More Tech 00:19:37 - When Leadership Decisions Don't Make Sense to You 00:23:21 - The Product Loop Starts With Discovery 00:25:22 - From Whiteboard to /roadmap 00:27:37 - Why Humans Plan First and Agents Come Second 00:30:33 - Commands vs Skills Across 32 Different Models 00:33:38 - Adversarial…","meta_description":"\"I need to stop using Opus. This doesn't work.\" That was Heitor Lessa's conclusion after a refactor cost him 200 million tokens, and it forced him to rebu…","key_points":[],"chapters":[],"topics":[],"duration_seconds":6797,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/beyond-coding-4008849/episodes/aws-veteran-the-agent-blueprint-behind-1-400-engineers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/beyond-coding-4008849/aws-veteran-the-agent-blueprint-behind-1-400-engineers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}