Dev Interrupted

Are you confusing a skyrocketing AI token bill with actual engineering value? This week on Dev Interrupted, Kraken's Engineering Operations Lead, Nik Sudan, joins the show to break down the harsh realities of moving agentic AI projects from pilot to production without compromising code health. He unpacks why raw AI adoption is a flawed vanity metric, detailing how his team uses tools like the LinearB MCP server to combine high-level engineering metrics with granular repository data to uncover hidden workflow bottlenecks. Finally, Nik reveals his exact playbook for translating complex data, like P90 cycle times, into a clear, business-driven narrative that secures vital buy-in from non-technical stakeholders. 
Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io 
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
LinearB MCP Server: Learn how to chat with your engineering data and uncover hidden bottlenecks at linearb.io/platform/mcp-server
The APEX Framework: Read LinearB's guide on the operating model for AI-era engineering teams at linearb.io/resources/apex-framework
Kraken: Learn more at www.kraken.com
Website / Follow Nik: niks.space
OFFERS
Start Free Trial: Get started with LinearB's AI productivity platform for free.
Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.
LEARN ABOUT LINEARB
AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.
AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.
AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.
MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Is the golden age of exponential AI growth already flattening out? This week on the Friday Deploy, Ben and Andrew unpack Steve Yegge's "Flat Curve Society" theory to explore what happens when frontier models stop getting exponentially better. The hosts also dive into the evolution of loop-driven development, the value of markdown based local knowledge bases, and why comparing different AI models usually just exposes the flaws in your own prompts. Finally, they review Midjourney's bizarre new echolocation spa concept and explore the true limits of AI disruption through the hilarious allegory of "The Wizard with the Very Defensible Pond." 
Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io 
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's stories:
A New Era of Midjourney
The Flat Curve Society
From Test-Driven to Loop-Driven Development
A failed universal language explains why you keep picking the wrong AI output
Building a Local Knowledge Base in Google's Open Knowledge Format (OKF)
The Wizard With the Very Defensible Pond
OFFERS
Start Free Trial: Get started with LinearB's AI productivity platform for free.
Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.
LEARN ABOUT LINEARB
AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.
AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.
AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.
MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Developers are like water: if you make your security protocols too difficult, they will find a way to flow right around them. This week on Dev Interrupted, bestselling author and OWASP Top 10 Project Leader Tanya Janca returns to unpack why vibe coding has officially made the list of the most critical security risks in software development. Tanya breaks down the psychology of bad code, explains why the modern software engineer has become the primary attack surface, and shares actionable strategies for shifting security left directly into your AI prompts. Finally, she provides practical, behavioral solutions for building a golden path that makes secure coding the easy choice for your engineering team. 
Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
SheHacksPurple: Learn secure coding from Tanya at shehackspurple.ca
DevSec Station: Listen to Tanya's bite-sized security podcast for developers at devsecstation.com
Secure My Vibe: Download Tanya's free AI secure coding prompt library at securemyvibe.ca 
The Psychology of Bad Code: Read Tanya's insightful blog series on behavioral economics and application security on the SheHacksPurple Blog
OWASP Top 10: Learn more about the most critical security risks to web applications at owasp.org
Tanya’s Newsletter: Sign up for Tanya’s newsletter at  newsletter.shehackspurple.ca  
Connect with Tanya: LinkedIn | Twitter/X
OFFERS
Start Free Trial: Get started with LinearB's AI productivity platform for free.
Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.
LEARN ABOUT LINEARB
AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.
AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.
AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.
MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Ben and Andrew unpack the sudden disappearance of Fable 5 and discuss whether Meta's aggressive pivot to AI data labeling is destroying its legendary engineering culture. The hosts also explore the rise of highly capable open source Chinese models like GLM 5.2 and why tech giants are considering them to slash skyrocketing inference bills. Finally, they dive into new research proving that as AI execution takes over, human domain expertise and strict production observability are more critical than ever. 
Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's stories:
Kayfable
Why is Meta destroying its engineering organization?
AI demands more engineering discipline. Not less
Z.ai’s open-weights GLM-5.2 beats GPT-5.5 on multiple long-horizon coding benchmarks for 1/6th the cost
Microsoft Mulls China’s DeepSeek for Copilot, Probably to Trump’s Chagrin
Agentic coding and persistent returns to expertise
OFFERS
Start Free Trial: Get started with LinearB's AI productivity platform for free.
Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.
LEARN ABOUT LINEARB
AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.
AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.
AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.
MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

What if the secret to fixing your overwhelmed SDLC is not a better AI coding model, but a smarter productivity context engine? This week on Dev Interrupted, LinearB founders Ori Keren and Dan Lines join the show to discuss the messy middle of AI adoption and the painful transition from the traditional SDLC to the Agentic Development Life Cycle. They unpack why the era of cheap AI experimentation is over, how rising token costs are forcing engineering leaders to prioritize strict business ROI, and how autonomous tools are fundamentally changing the daily workflow of developers.
Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
LinearB: Learn how to transform your SDLC and build an engineering context engine at linearb.io
gitStream: Explore LinearB's workflow automation tool for routing pull requests at linearb.io/platform/gitstream
Follow Ori and Dan on LinkedIn: Ori Keren | Dan Lines
OFFERS
Start Free Trial: Get started with LinearB's AI productivity platform for free.
Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.
LEARN ABOUT LINEARB
AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.
AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.
AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.
MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.