Beyond Coding

Latest Episodes:

How Senior Engineers Use Coding Agents On Prod Infrastructure Oct 21, 2026

Show notes

How do senior engineers use coding agents on prod infrastructure when “make no mistakes” is just a polite request? Kerim Satirli (HashiCorp, an IBM company) explains why prompt rules don’t hold in production, and what he runs instead.

In this video, we cover:

How Infrastructure as Code (Terraform, Contentful, Datadog, Okta, Cloudflare providers) evolved from open-source PRs to automated agent harnesses
Why AI skills files and “make no mistakes” prompts are only requests, and what replaces them in production pipelines
How AI-generated pull requests are overwhelming open-source maintainers (and why projects like cURL are pushing back)
Personalized “software factories”, spec-driven development (GitHub Spec Kit), and cutting AI documentation noise with BLUF (Bottom Line Up Front)
What open-source Rust clones of Adobe mean for the future of SaaS

For infrastructure engineers, DevOps practitioners, and software architects who want to move past one-shot prompting and run coding agents on production infrastructure without losing control.

Timestamps:
00:00:00 - Why “Make No Mistakes” Is a Polite Request
00:00:38 - How Open Source Terraform Changed Provisioning
00:01:59 - Why API-First Services Matter Beyond AWS and Azure
00:04:19 - How AI Agents Changed Terraform Provider Updates
00:07:03 - Why “Make No Mistakes” Won’t Stop Your Agent
00:10:31 - Bringing Determinism Back to Agentic Workflows
00:13:07 - How AI Pull Requests Are Overwhelming Open Source
00:15:41 - Why Every Engineer Is Building a Software Factory
00:18:52 - Why AI-Generated Documentation Slows Down Humans
00:23:12 - Using Agents to Filter Noise and Summarize Specs
00:27:02 - Escape Hatches for Automated Terraform Applies
00:29:03 - Where the Joy in Engineering Lives Now
00:31:24 - Spec-Driven Development and the Return of Architecture
00:34:51 - Open-Source Rust Clones, Reverse Engineering, and SaaS
00:38:19 - How to Build Software Products People Actually Want

Guest: Kerim Satirli, Senior Developer Advocate at HashiCorp, an IBM company.

https://www.linkedin.com/in/ksatirli

#Terraform #CodingAgents #DevOps

Lead Architect Reveals His Rules for Coding Agents Oct 14, 2026

Show notes

Lead Architect Carlos Kelkboom shares his rules for coding agents and how great engineers architect software with AI. One of the great ones is: he throws away generated code the moment he doesn't understand it. He breaks down why coding agents fail at iterative changes, why his main agent never touches files, and how he scaffolds projects for one-shot execution.

In this video, we cover:

Why AI coding agents struggle with iterative changes (SlopCodeBench) and excel at one-shot execution
How to manually scaffold code, types, and folder boundaries before letting sub-agents run
Designing a distributed Markdown and indexed-search graph harness for progressive context disclosure
Using Git worktrees to run parallel coding agents and merge the best implementations
Why dynamic memory and the heap need to disappear in favor of deterministic programming languages
How AI bubbles and solo coding impact junior engineers and team collaboration

This episode is for software engineers, tech leads, and system architects who want to move beyond "vibe coding" and build maintainable, deterministic production software with AI agents.

Connect with Carlos:

https://www.linkedin.com/in/carlos-k-4016b8225

Timestamps:
00:00:00 - Why Carlos Throws Away Working AI Code
00:00:53 - Why Pull Requests and Team Collaboration Are Dying
00:03:50 - The Trap of Starting Projects You Never Finish
00:06:06 - Escaping the Solo AI Developer Bubble
00:11:54 - How to Scaffold Code Before Using AI Agents
00:15:54 - Learning New Programming Languages With AI Agents
00:21:14 - Why We Must Get Rid of the Heap
00:28:32 - Building a Shared Language Across Engineering Teams
00:31:31 - Vibe Coding vs Deep Software Engineering
00:40:12 - Code Is Cheap: Git Worktrees for Parallel Agents
00:41:45 - How Deep to Scaffold Before the Agent Runs
00:45:09 - Democratizing Software, Missing Juniors, and the AI Bubble
00:53:33 - Designing a Graph Harness for AI Agent Context
00:58:18 - Why His Main Agent Never Touches Files
01:03:07 - Throw Away Code You Don't Understand
01:06:25 - Rethinking Code Reviews and Mutation Testing for AI

#CodingAgents #SoftwareEngineering #AgenticEngineering

What the Best Engineers Built for Their Coding Agents Oct 07, 2026

Show notes

What happens when coding agents see your entire system: code, services, infrastructure and live traffic, all connected? Most agents are blind to everything outside the repo. Adyen Staff Engineer Mat Jones explains what changed once theirs weren't, and why he calls it somewhat scary.

In this video, we cover:

Running five or six coding agents in parallel with git worktrees and Atrium, an internal tool that lets agents coordinate and share memory
Architect: nine connected graphs in Neo4j covering services, code, DNS, data stores and infrastructure
Ingesting 7 million trace spans a second with Kafka and Apache Flink, and what collapsed on the first try
Sentinel: anti-pattern monitoring, with agents that raise the fix as a merge request
MCP vs APIs vs CLI tools, and how to deal with tool bloat

This episode is for software engineers and platform teams who want coding agents to reason about real systems, not just the repo in front of them. You'll leave with a concrete place to start and an honest view of the risks.

00:00:00 - Intro

00:00:42 - Running Five Coding Agents in Parallel

00:01:35 - Atrium: How Agents Avoid Stepping on Each Other

00:06:57 - Why Graphs Save Coding Agents Tokens

00:12:25 - What Is Architect? Nine Graphs in One Database

00:16:54 - What Broke at 7 Million Spans a Second

00:20:37 - The Timeline From Proof of Concept to Production

00:27:59 - Tracing Code Changes to Critical Payment Flows

00:30:26 - How to Start: Build Scrappy, Then Earn Buy-In

00:35:07 - Making a Codebase Agent Friendly With Skills and Hooks

00:42:07 - Why You Should Start With a Service Graph

00:44:46 - The Downside of Everyone Seeing Everything

00:48:34 - Sentinel: Agents That Find and Fix Anti-Patterns

00:53:01 - Are We Going Too Fast With AI?

01:01:55 - Two Engineers, Four Months: Why Big Bets Got Cheaper

01:07:11 - MCP vs CLI Tools and the Tool Bloat Problem

Guest: Mat Jones, Staff Engineer at Adyen
https://www.linkedin.com/in/mathewwjones

#codingagents #softwareengineering #platformengineering

Why Coding Agents Keep Making Your Codebase Worse Sep 30, 2026

Show notes

HumanLayer CEO Dexter Horthy, who coined "context engineering", on why AI agents degrade codebases over time. He breaks down a benchmark that measures AI code quality across features, and how his team ships with agents without drowning in slop.

In this video, we cover:

SlopCodeBench, SWE-bench and which coding benchmarks to trust
Token maxing, dark factories and the "Instagram phase" of AI engineering
Why 2-4x productivity beats chasing 100x
Pull requests, design docs and how engineers build taste now
Dex's agentic engineering workflow: one-shots, overnight janitor bots and research-design-plan

For engineers and engineering leaders adopting AI coding agents who want to know what's real and what works in teams at scale.

Timestamps:
00:00:00 - The Man Who Coined the Term: Context Engineering
00:00:54 - SlopCodeBench: Proof AI Makes Codebases Worse Over Time
00:05:49 - Background Agents and the Enterprise Friction Problem
00:08:13 - Why You'll Never One-Shot a Big Feature
00:11:18 - Scaling Agentic Engineering to 1,000 Engineers
00:16:19 - Dark Factories, Fake Hype and Token Maxing
00:19:55 - Why 2-4x Faster Beats Chasing 100x
00:21:31 - Should Teams Stop Doing Pull Requests?
00:24:20 - Can Deterministic Tools Replace Code Review?
00:27:37 - How to Build Engineering Taste When AI Writes Code
00:33:05 - Dex's Agentic Workflow: One-Shots and Janitor Bots
00:35:18 - Research, Design, Plan: Shipping Big Features With Agents
00:38:35 - Why Overnight Agents and Heavy Parallelism Backfire
00:40:10 - Subscription Maxing vs Paying Per Token
00:42:40 - Parallelize Like Poker, Not a Slot Machine

Dex Horthy: https://x.com/dexhorthy
Dex's talks and deep dives: https://aithatworks.bold.video

#AgenticEngineering #AICoding #SoftwareEngineering

How Amp Ships 50 Times a Day With AI Agents Sep 23, 2026

Show notes

Amp ships to production around 50 times a day with AI agents, but the change that makes their team ship faster isn't AI at all. Dario Hamidi, AI engineer at Amp, makes the case that pull requests are holding your team back, and explains what replaces them.

In this video, we cover:

Why Amp works without pull requests or feature branches, and how to try it with your own team
Agent permissions, approval fatigue, and building environments where you can trust agents
Orbs: remote agent execution, parallelism, and multiplayer sessions
Short-lived credentials and workload identity federation for cloud agents
Triaging 60+ bug reports a day with agents without frying your brain

For engineers and engineering leads who want to ship faster with AI agents and are ready to question the workflows they've always used.

Timestamps:
00:00:00 - Is It Time to Kill the Pull Request?
00:00:45 - What Happens If Every PR Gets Auto-Closed Tomorrow
00:05:04 - Pull Requests Were Built for Strangers, Not Teammates
00:07:20 - Does Dropping PRs Hurt Quality at Scale?
00:08:53 - Agent Permissions: Why No Default Makes Everyone Happy
00:12:42 - Don't Juggle Knives: Building Environments You Can Trust
00:14:56 - The Hidden Hard Parts of Cloud Agents
00:16:39 - What's an Orb? Remote Agent Execution Explained
00:19:10 - How to Give Agents Credentials Without Leaking Secrets
00:22:51 - Why Orbs Live Forever (and Multiplayer Orbs)
00:25:49 - The State Management Problem Nobody Talks About
00:29:22 - When Will Everyone Have Remote Dev Environments?
00:32:23 - Orbs That Spawn Orbs: Orchestrating Agents at Scale
00:34:42 - How Dario Triages 60 Bug Reports a Day With Agents
00:39:23 - Avoiding Burnout When Agents Remove the Ceiling

#AIAgents #SoftwareEngineering #PullRequests

How Top Engineers Still Get Hired When Most Get Ghosted Sep 16, 2026

Show notes

How do top engineers still get hired in 2026 when most applicants get ghosted, 120,000 people have been laid off this year, and hiring managers say they can't find talent? A recruiter, a hiring lead, a career coach and an open source engineer explain why your resume is dead on arrival when every CV looks the same, and what actually gets you in the room instead.

In this episode, we cover:

Why 120,000 tech layoffs and 60,000 open engineering roles exist at the same time
Why only 20% of LinkedIn messages get a reply, and how to write the ones that do
Why one hiring team bans AI tools in interviews and is building an agentic coding session instead
Adaptability and resilience: the two soft skills that keep you in the room
Getting hired through GitHub, referrals and open source when your CV can't stand out
Whether junior engineers still have a path, and which engineering cohort is at risk in 3 to 5 years
Titles vs scope: how to grow when your title never changes

For software engineers, students about to graduate, and anyone in tech who wants to know what recruiters and hiring managers are actually filtering on right now.

Timestamps:
00:00:00 - Intro: 1,000 Layoffs a Day
00:00:47 - How Bad Is the Tech Job Market in 2026?
00:02:05 - Why 120K Layoffs and 60K Open Jobs Don't Add Up
00:03:40 - Why AI Tools Are Banned From Interviews
00:06:28 - Hard Skills Get You In, Soft Skills Keep You There
00:09:20 - "I'm a University Dropout": How GitHub Got Me Hired
00:10:18 - CVs Are Too Good Now: Why Referrals Win
00:13:04 - How to Get Your Open Source PR Merged
00:15:02 - Why 80% of Your LinkedIn Messages Get Ghosted
00:16:51 - How Open Source Led to a HashiCorp Job Offer
00:19:15 - Is There Still a Place for Junior Engineers?
00:22:00 - The Engineers Who'll Be Obsolete in 3 to 5 Years
00:24:20 - Should You Contribute to Open Source at All?
00:26:05 - AI Skills Required, Algorithms Still Tested
00:27:54 - Stop Chasing Titles: Scope, Impact and Owning Your Career

#softwareengineering #techjobs #careeradvice

Why an Ex-Googler Bet Everything on an Open-Source Database Sep 09, 2026

Show notes

Jordan Tigani helped create Google BigQuery, then got fired as Chief Product Officer on a Friday morning. He planned to hack on DuckDB to learn Rust. Investors offered to fund it before he'd decided to start a company. That company became MotherDuck

In this episode, we cover:

The DuckDB Labs partnership: why MotherDuck gave the open-source creators a co-founder share instead of going open-core
From alpha to paid product: 11 founders, 3 to 4 months to alpha, two years to something people would pay for
AI on top of the data warehouse: vibe-coded dashboards (Dives), pipelines (Flights), a context layer (Guides), and why business users catch mistakes analysts miss
Are dashboards dead? Jordan wrote "Big Data Is Dead"; his answer on dashboards is different
Career advice: why you shouldn't want to work on the query optimizer, and the skill Jordan says matters more

For engineers curious about database and infrastructure companies, open-source business models, and how AI is changing who gets to ask questions of data.

Timestamps:
00:00:00 - Intro
00:00:32 - Fired on a Friday: how MotherDuck accidentally started
00:04:50 - Giving DuckDB Labs a co-founder share of the company
00:07:43 - Why most open-source SaaS products are just "managed"
00:09:31 - Why VCs said yes: Snowflake, DuckDB, and BigQuery credibility
00:10:50 - The 11-person founding team that skipped the wrong designs
00:12:20 - Alpha in 4 months, beta in a year, paid in two
00:15:20 - Vibe-coded BI: Dives, Flights, Guides, and an agent harness
00:20:10 - The questions business users ask that analysts never do
00:24:14 - Are dashboards dead in the age of agents?
00:27:57 - Everybody wants to work on the optimizer (don't)
00:31:23 - The engineer superpower most engineers look down on
00:33:20 - Writing: the one skill Jordan would learn (and still hates)
00:36:05 - Does contributing to DuckDB get you hired at MotherDuck?
00:37:20 - Why a database company leaned into the duck

#MotherDuck #DuckDB #SoftwareEngineering

How the Best Engineers Build a World Model (Google Earth Creator & Niantic Spatial CTO) Sep 02, 2026

Show notes

Niantic Spatial CTO Brian McClendon on how the best engineers solve problems most give up on — from a 4D model of the world to shipping research in months. He built Google Earth and ran Google Maps for over a decade, and he's been there, done that. What he's building now is harder, and it's already live for customers. Along the way: who makes it on his team and who doesn't, and the one piece of advice he'd give every engineer using AI.

In this video, we cover:

- The 4D model of the world: visual positioning, change detection, and treating a pile of photos like a database

- Gaussian splats and real-to-sim: capturing a room and loading it into Nvidia Isaac to train robots

- Turning a research idea into a production service in six months

- What Google Maps taught him about building for robots instead of humans

- Designing problems AI can self-check, and why token maxing is a waste

For engineers and engineering leaders who want to work on problems that don't have a known answer yet — and who want to know what a CTO who's built the definitive product in his field looks for in the people he hires.

Recorded at the AI4 conference 2026.

Timestamps:

00:00:00 - Google Earth? Been There, Done That
00:00:46 - Turning a Research Idea Into Production in 6 Months
00:02:37 - How Any Photo Gets Located Within Half a Meter
00:06:37 - The Long-Term Goal: A 4D Model of the World
00:08:37 - Treating a Pile of Photos Like a Database
00:11:58 - What Google Maps Taught Him About Training Robots
00:15:22 - Gaussian Splats Explained in Plain Terms
00:17:42 - The Unsolved Problem: Scale and Semantic Change
00:20:34 - Why Google Earth Is Good Enough
00:22:09 - Who Makes It on His Team and Who Doesn't
00:23:38 - Designing Problems AI Can Self-Check
00:26:03 - The Insights Hidden in the Physical World
00:28:18 - Digital Twins, Cities, and Ready Player One
00:31:35 - Visual Positioning When GPS Gets Spoofed
00:33:24 - Token Maxing Is Bullshit: Advice for Engineers

Guest: Brian McClendon, CTO at Niantic Spatial. The engineer behind Google Earth; ran Google Maps for over a decade.

https://www.linkedin.com/in/brianmcclendon

#NianticSpatial #GoogleEarth #SoftwareEngineering

How New Staff Engineers Build Judgment Without Years of Experience Aug 26, 2026

Show notes

How do new staff engineers build judgment without the years of experience that used to come with the role? Mallika Rao, engineering leader in big tech, explains why the data-structures-and-algorithms foundation everyone was trained on is no longer enough on its own, and where the complexity has actually shifted now that AI writes the implementation.

In this video, we cover:

Why "how does AI affect engineers" is the wrong question, and what to ask instead
Rehearsing multiple futures: what judgment looks like in a staff engineer
The case method: building judgment from incident reports and system design history instead of waiting years for it
Cognitive coordination, code review load, and the surprise ask for more meetings at staff level
Tiger teams vs scaled teams, trust as architecture, and building evals from a spreadsheet
Splitting planning from execution so engineers stop falling behind with agents
Taste vs judgment, and how to build both outside of software

If you've just made staff, or you're about to, this conversation gives you a frame for what the level actually demands now and how to grow into it faster than the old apprenticeship allowed.

Recorded at the AI4 conference 2026.

Timestamps:

00:00:00 - How AI Is Changing Senior Engineering Careers

00:00:41 - Why "How Does AI Affect Engineers" Is the Wrong Question

00:03:26 - What Judgment Actually Is: Rehearsing Multiple Futures

00:05:24 - Why Data Structures and Algorithms Are No Longer Enough

00:07:22 - Learning Judgment From Incident Reports Like the 2017 S3 Outage

00:11:13 - The New Staff Engineer's Core Challenge: Cognitive Coordination

00:14:48 - What Managers, Universities, and Shakespeare Each Owe You

00:17:55 - Code Review Load, Meeting Notes, and the Surprise Ask for More Meetings

00:23:59 - Trust as Architecture: Why Evals Started as a Spreadsheet

00:27:09 - Tiger Teams vs Big Teams: Product Managers Reviewing Code

00:32:39 - Why Some Engineers Can't Keep Up With Agents

00:35:46 - Local AI Champions and Splitting Planning From Execution

00:38:38 - Go Deep or Go Broad? Search in a World of Agents

00:44:12 - Taste vs Judgment: Thinking in 50 Layers

Guest: Mallika Rao, engineering leader in big tech.

Rehearshing the Future framework

If by Rudyard Kipling

Amazon AI Lead: What Differentiates The Best AI Coding Models Aug 19, 2026

Show notes

How does Amazon build its agentic AI? Michael Giannangeli, Head of Product for Amazon Nova and Agentic AI, breaks down evals, RL gyms, and model routing.

He also explains why the bottleneck in software has shifted away from engineering hours and what takes its place.

In this video, we cover:

The eval lifecycle: building from real failure modes, saturation, and why 100% means delete
RL gyms: training models on real environments like migrations, DevOps, and pen testing
Model routing, cost-per-token trade-offs, and why routing isn't solved
The agent stack of an Amazon product lead: Claude Code, Codex, and Kiro
Autonomous migrations, trust, and how much human-in-the-loop survives

For engineers and product people building with AI agents who want to see how a frontier lab actually closes its feedback loops.

Recorded at the AI4 conference 2026.

Timestamps:
00:00:00 - Intro
00:00:36 - The Agents an Amazon Product Lead Uses Daily
00:03:36 - Why Nobody's Heard of Amazon Nova
00:04:55 - Model Costs and the Routing Problem
00:08:10 - Why Building Good Evals Is So Hard
00:10:05 - When Evals Saturate and Get Deleted
00:12:17 - Turning Real Failure Modes Into Hundreds of Evals
00:15:26 - Improving Models Without Training on Customer Data
00:18:26 - If Everyone Uses Agents, You Need Agents
00:20:22 - The Bottleneck Is No Longer Engineering Hours
00:23:20 - Ship Fast to Validate the Right Thing
00:26:44 - Staying at the Frontier Amid Constant Noise
00:29:37 - Spend 10-20% of Your Time Experimenting
00:32:54 - RL Gyms: How Models Learn From Failure
00:37:09 - Will Migrations Become Fully Autonomous?

Guest: Michael Giannangeli - Head of Product, Agentic AI & Amazon Nova at Amazon

#AmazonNova #AgenticAI #AIEngineering

Our TOPPODCAST Picks

Follow Us

Stay Connected

Related Podcasts

Links

Stay Connected