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