Episode Summary

Dave and Dan run a two-person AI consulting company where the back office has quietly disappeared into automation: time tracking, invoicing, payroll, the weekly newsletter, and this very podcast all run on agents rather than people. That leads them to the question the whole episode circles — if two people can automate this much, what does a 200-person company actually need all those people for?

Key Topics

• Finance on autopilot — hourly billing, monthly invoicing, and S-corp payroll and distributions handled by their own agents alongside Gusto, with a CPA still owning tax compliance
• Marketing and podcast production — a weekly newsletter assembled from blog content, and a podcast pipeline that records, edits, publishes, clips, and schedules itself
• Build instead of subscribe — replacing Cal.com with their own scheduling tool to cut the bill and add the features they actually wanted
• The internal stack — Shipwright for autonomous coding, Vitals OS for time tracking, and Squadron for goal-driven autonomous projects
• Where automation still falls short — marketing results lag, and closing a deal is still a human skill AI has not replaced
• Two paths for AI adoption — cut headcount for margin, or keep the team and use the same automation to move faster and build more

Notable Quotes

• "We haven't written a line of code in eight months. We plan, and we validate, for Shipwright."
• "Software engineers do not need to write code anymore. That's a solved problem."
• "200-person company, right? What does that mean when, if we can automate it, shouldn't they be able to automate all this stuff out?"

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Real AI adoption doesn't stall on tooling — it stalls on two human prerequisites: trusting the AI, and trusting your team. Dave and Dan unpack why AI transformation is genuinely hard, how they stopped hand-writing code entirely, and why the organisations that substitute process for trust are the ones that can't move.

Key Topics

• Why AI transformation is hard — it threatens managers' headcount and engineers' identity as people who write code
• Trusting AI — you have to watch it succeed repeatedly first; eight months without hand-writing code, and 10,000 PRs shipped across their own company and clients
• The plan-then-validate workflow — PRD to task to agent execution, and why a non-coder and a developer arrive at trust by completely different routes
• Multitasking as the underrated soft skill of the AI era — going from single-threaded work to running parallel planning sessions
• Trusting your team — bureaucracy exists so organisations don't have to trust people, which is exactly why small teams outrun big ones
• Verification as the third pillar — automated testing and canary deploys, so a mistake rolls itself back

Notable Quotes

• "You're asking human beings to make a massive change in how they work."
• "Trusting your teammate is an organizational issue."
• "We haven't written a line of code in eight months, and shipped 10,000 PRs for not just our company, but other companies."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Dave and Dan break down the harness — the orchestration layer wrapped around an AI coding agent — and why it increasingly matters more than the model underneath it. They get into Anthropic deleting 80% of Claude Code's system prompt with nothing breaking, what that does to your token bill, and the thesis they land on: the better the models get, the smaller the harness you want.

Key Topics

• What a harness actually is — and why Shipwright sits on top of Claude Code instead of replacing it
• General vs. domain-specific harnesses: how Shipwright gets opinionated about PRs and reviews
• Dan's second harness — an upstream, KPI-driven planning layer that writes no code at all
• Boris's reveal: 80% of Claude Code's system prompt deleted, nothing broke, and what that saves you in tokens
• Model economics in practice — Sonnet vs. Opus vs. Fable, and the pull toward Groq and DeepSeek
• Token anxiety: six agents running 24/7, a $2,000 overage month, and what a Fortune 200 team spends vetting open-source models

Notable Quotes

• "Boris said that they deleted 80% of the system prompt for Claude Code and nothing broke."
• "The better the models get, the smaller the harness you want."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Dave O'Dell and Dan McAulay argue that the software engineer's role isn't disappearing, it's changing dramatically, and that raw coding ability is no longer what separates a viable developer from an obsolete one. They break down the four soft skills they now interview for: articulation, curiosity, delegation, and full software development lifecycle awareness.

Key Topics

• Why they adopted AI early — fear of being left behind, and the bet that a huge share of developer jobs change within five years
• Articulation — describing both what you want and what success looks like, which Dan connects to "loop engineering": a goal plus a way to verify it
• Curiosity — agents run autonomously, so you have to stay curious about what the system is doing and why instead of blindly trusting it
• Delegation — a learnable, teachable skill rather than an innate one, and why building trust in the system is the hard part
• Full SDLC awareness — why being siloed to one repo and its APIs no longer works when AI writes the code
• The hiring bar — what Dave looks for in interviews, and why being an introvert isn't a blocker when you're mostly directing agents

Notable Quotes

• "These are not nice to have. In my brain, if you don't have these, I'm not hiring you."
• "I'm guessing a huge percent of the developers five years from now are gonna be having completely different jobs. I don't wanna be one of those."
• "Building trust in the system is a huge one for delegating."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Thirteen months ago DHH called AI "slop" and a fancy autocomplete. Today he runs his own agent-orchestration project and reviews PRs from an inbox. That turnaround is the jumping-off point for a bigger question: why can't companies with the best engineers in the world and effectively unlimited resources move as fast as two people with six agents?

Dave and Dan argue the bottleneck was never talent or compute. It's process — the PRD review, the design doc meeting, the meeting about the meeting — and you don't fix that by adopting AI slowly.

Key Topics

• DHH's 13-month reversal, and what it says about where the skeptics land
• Why unlimited resources stopped being a moat — everyone has them now
• Two people, six agents: what a two-person company actually ships in a year
• The human-to-human bottleneck is bureaucracy, not conversation
• The two adoption paths: slow drip, or pull your best engineers off everything for 6–12 months
• Why flattening the org is the precondition, not the reward — and what managers should automate first
• Building your own tools instead of buying: the booking and billing stack behind App Vitals

Notable Quotes

• "Oh my God, how cute, someone's still paying you to write code? Good luck, buddy."
• "Take a handful of your best engineers, remove them from any company function whatsoever, and say, we are going to adopt AI for every single process across the board."
• "You gotta flatten your org or you're not gonna be competitive."
• "Let builders build. You have to do it. You can't stop 'em."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Open-source models have caught up to Sonnet on the benchmarks, so does it still matter which model you use? Dave and Dan argue the model stopped being the differentiator a while ago. They break down why they default to Sonnet over Opus, why a free model matching Sonnet still doesn't make them switch, and what you're actually paying Anthropic for.

Key Topics

• Is the model still the moat? Why open-source parity with Sonnet doesn't change how they work
• Trust as the real switching cost — you don't adopt someone else's evals, you build your own confidence
• Default your org to Sonnet, not Opus (Sonnet runs ~40% cheaper) — and when to reach for Opus
• The spend framing: expect an engineer to run $50k/year on an LLM, and expect them to at least double their throughput for it
• Don't fragment across tooling — pick a stack and build a system around it
• Anthropic's real product is enterprise adoption: a whole-org toolset plus hands-on help getting teams to actually use it

Notable Quotes

• "You should expect an engineer to spend $50,000 a year using an LLM. But they should double their throughput."
• "Make your default model Sonnet."
• "We can prove the newer models don't really matter, 'cause we don't even use them."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Dave was dead set against building a Human-in-the-Loop mode for Shipwright — then Dan shipped it overnight using autonomous agents, and Dave came around completely. This episode is the story of why they built it: a low-risk on-ramp that lets AI-nervous teams watch autonomous coding happen, approve each step, and build trust before handing over the keys.

Key Topics

• Why Human-in-the-Loop exists — meeting teams that are nervous about AI escaping the sandbox or leaking secrets
• The three ways to try Shipwright: Claude Code plugins (one task at a time) → local Human-in-the-Loop → fully autonomous in your own cloud
• The feature was built by autonomous agents overnight — the medium is the message
• Trust as the real product: HITL is a confidence-builder, not the destination
• Laptop vs. cloud permissions — why you'd never run full-autonomous on a machine holding all your tokens
• Getting developers out of the terminal without taking away the safety of watching

Notable Quotes

• "I was dead set against this... and now I'm going the opposite."
• "You don't write code anymore. That's the real experience."
• "Turn your phone off, go boating, and a day later it's shipped."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS

Episode Summary

Teams are finally staring at their AI bills — and the reflex is to use the LLM less. Dave and Dan make the opposite case: the answer isn't a cheaper model or less AI, it's a system. The harness around the model — how you plan, review, patch, and deploy — matters more than which model you run.

Key Topics

• The harness beats the model — a real system on an older/cheaper model out-executes ad-hoc prompting on the latest one.
• Why bills exploded — adoption without measurable speed gains, and the instinct to "just stop using LLMs" is the wrong lever.
• Deterministic pipelines — code → review → patch → deploy, ~14 steps each, so every change gets the same treatment every time.
• Model selection per task — only ~3% of tasks hit the expensive default (Opus); 70%+ run on a model 84% cheaper.
• Systems are optimizable, ad-hoc work isn't — you can't standardize or tune what everyone does differently.
• Enforcing org standards — one shared system means changing how everyone builds APIs or runs migrations is trivial.

Notable Quotes

• "The harness — basically how you use the LLM — is much more important than the actual model itself."
• "If you don't have a system, then you cannot enforce standards across your organization."

About The Velocity Lab

Dave O'Dell and Dan McAulay work inside engineering organizations every day helping them ship faster with AI. No hype, no BS — just what's working in the field.

Subscribe: RSS