Dev Interrupted

Capital One SVP Abhijit Bose, who leads the company’s enterprise AI and ML platforms, has spent more than 20 years in AI and ML, and his answer is to make governance the platform’s job instead of the developer’s. This week on Dev Interrupted, he joins Dan Lines for LinearB’s AI Enablement Series to walk through how every harness change at Capital One now runs through evals that measure token cost, latency and quality before it reaches users. Abhijit also explains how MACAW, the bank’s multi-agent framework behind Chat Concierge, went from 12-second responses to targeting under a second.
Save your seat: Deliver outcomes when human attention can't keep up
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
Chat Concierge: Driving the future of car buying with agentic AI. The multiagent car-buying assistant that runs on Capital One’s GenAI platform.
MACAW: Capital One at EMNLP 2025. Capital One’s introduction to MACAW, the multi-agent framework behind Chat Concierge.
VulnHunter: Announcing VulnHunter. The open-source agentic code security tool Abhijit points to when talking about AI and cybersecurity.
Connect with Abhijit: LinkedIn
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.
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, Dev Interrupted takes a field trip all the way down to the GPU. Leading the way is Together AI’s VP of Kernels Dan Fu, a co-author of FlashAttention who also runs a research lab as an assistant professor at UC San Diego. He joins Andrew to talk about how ideas now move from the lab into production models within months, and what it means to build a cloud for AI. Dan argues that AI is an accelerant for individual engineers, and that the more domain expertise they bring, the faster it lets them go. They close the conversation on how DRIs and managers keep track of ownership and AI spend when your star players get even faster 
Save your seat: Deliver outcomes when human attention can't keep up
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
OpenWALDO: The open source AI project Greg launched, built on open weights, artifacts, licenses, data and origins
OpenWALDO Slack: Join the community Greg invites listeners into
OpenWALDO on GitHub: The project’s code and tooling
CIQ: Greg’s company, where he is founder and CEO
Rocky Linux: The enterprise Linux distribution whose community Greg set up
Why Open Source Matters for AI: Tim O’Reilly’s piece on open weights, protocols and the architecture of participation
Connect with Greg: LinkedIn
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.
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.

Most companies control the prompts they send to a model, but not what went into it. That’s the gap CIQ founder and CEO Gregory Kurtzer, who set up the community that built Rocky Linux, wants an AI bill of materials to close. This week on Dev Interrupted, he joins Andrew to make the case for OpenWALDO, a community-backed corpus of AI training data built on open weights, artifacts, licenses, data and origins. Greg explains why open weights alone don’t make a model open source, and why a model trained on copyleft code raises a licensing question nobody has litigated. They close the conversation on why the community side of open source matters more than ever now that AI lets more people contribute.
Save your seat: What your software factory is doing to your engineers
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
OpenWALDO: The open source AI project Greg launched, built on open weights, artifacts, licenses, data and origins
OpenWALDO Slack: Join the community Greg invites listeners into
OpenWALDO on GitHub: The project’s code and tooling
CIQ: Greg’s company, where he is founder and CEO
Rocky Linux: The enterprise Linux distribution whose community Greg set up
Why Open Source Matters for AI: Tim O’Reilly’s piece on open weights, protocols and the architecture of participation
Connect with Greg: LinkedIn
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.

Agents made each engineer faster, but the handoffs between them still run through copy and paste. OpenClaw Foundation chief architect Vincent Koc ran into that friction on his own team, and their answer was to move the engineering work of building OpenClaw inside OpenClaw itself. This week on Dev Interrupted, he joins Andrew to walk through the multiplayer setup behind OpenClaw 2.0, where teammates and their agents can jump into each other’s sessions on shared servers and pick up work when someone goes to sleep. Vincent explains how tools like Git Crawl keep their agents aware of everything happening across the repo, and why the piece that’s still missing is the why behind a decision. 
Save your seat: What your software factory is doing to your engineers
Join us at AGNTCon + MCPCon on Oct 22 & 23 in San Jose. Use code MEDIA25 for 25% off your ticket.
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
OpenClaw Foundation: openclaw.org The foundation behind OpenClaw, which Vincent serves as chief architect.
OpenClaw: openclaw.ai The open source personal AI assistant at the center of the conversation.
OpenClaw 2.0, Accidentally: openclaw.ai/blog/openclaw-2-accidentally The release post for OpenClaw 2.0 and its multiplayer features.
OpenClaw on GitHub: github.com/openclaw The org’s open source repos, all under MIT.
OpenClaw security: openclaw.ai/security The project’s security page, which Vincent points to for the full record of reported vulnerabilities.
Git Crawl: github.com/openclaw/gitcrawl The team’s GitHub issue and pull request crawler that keeps their agents aware of work across the repo.
Crabbox: github.com/openclaw/crabbox The testing infrastructure the team built when nothing out there fit.
Tideglass: github.com/vincentkoc/tideglass Vincent’s side project for inferring intent and preference profiles for agents.
Beads: github.com/steveyegge/beads Steve Yegge’s git-backed issue tracker for coding agents.
Wikinomics: dontapscott.com/books/wikinomics The book on mass collaboration that Vincent keeps coming back to.
Connect with Vincent: LinkedIn | 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.

LinearB's software factory spends more time on the spec than on the code. VP of Engineering Ariel Illouz spent the last year moving his team of about 30 engineers from vibe coding to spec-driven development, starting with a single spec-writing skill and a rule that every story above three story points gets a spec. This week on Dev Interrupted, he and returning guest Ofer Affias, LinearB's senior director of product, join Andrew to walk through a project Ariel puts at six months without AI that shipped in roughly four weeks, at least two of them spent on specs. Ofer explains why proving the impact meant measuring AI adopters as separate cohorts. They close the conversation on where the software factory goes next, as agents take over more of the loops humans run today. 
Save your seat: What your software factory is doing to your engineers
Join us at AGNTCon + MCPCon on Oct 22 & 23 in San Jose. Use code MEDIA25 for 25% off your ticket.
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
LinearB Metrics Builder: The custom metrics builder Ariel's team built spec-first, a project he puts at six months without AI. 
LinearB AI benchmarks: The AI engineering productivity gap: how elite teams pull ahead in 2026. 
Connect with Ariel: LinkedIn 
Connect with Ofer: LinkedIn
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.