The Velocity Lab

Dave O'Dell and Dan McAulay
  • 5.0 (1)
  • Technology

Dave O'Dell and Dan McAulay work inside engineering organizations every day, helping them ship faster with AI — not in theory, but inside their actual teams. Each week they share what they're seeing in the field: what's working, what isn't, and what most people are getting wrong. Covering Claude Code updates, AI-enabled SDLC acceleration, and personal AI agents. No hype, no BS.

  1. 1d ago

    How We Accidentally Built an Open-Source Alternative to Devin

    Episode Summary Dave and Dan tell the origin story of App Vitals — from LiveKit AI-voice tutorials to an AI-transformation consultancy to shipping their own open-source autonomous coding agent. They unpack the 37signals philosophy that shapes how they build, how a mobile-dev side project quietly became Shipwright, and why test readiness is the real on-ramp to autonomous programming. Key Topics The 37signals model — build products for yourselves first, let consulting pay the bills How Shipwright started as a Claude Code plugin and grew into a managed autonomous coding agent Shipwright vs. Devin — open source, runs in your own infrastructure, fully customizable vs. a closed SaaS black box Coding asynchronously in Slack: planning and reviewing while the agent handles execution, PRs, review, and deploy The ski-trip story — building and deploying a website by voice from a chairlift, no laptop Test readiness as Phase Zero: fixing flaky, slow, low-coverage tests before you can trust an agent to ship Notable Quotes "There's no reason to be in a terminal. There's no reason to write code anymore." "While I was skiing, it built a different version of solitaire and deployed it to Vercel — and I never saw my laptop the whole day." "We ship hundreds of PRs a week for us and our clients with no human interaction." 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

    16 min

  2. Jun 30

    You're Choosing Not to 10X Your Team for Free

    Episode Summary Major announcement: Dave and Dan are open-sourcing Shipwright, the autonomous coding agent they've been building since November. It takes you from PRD to production deployment with no human intervention ~99% of the time — and it built itself. Across ~500 pull requests, they say they barely read a line of code. The core provocation for leaders: if a free tool can 10X your engineering throughput and you choose not to adopt it, that's a decision you'll have to justify. Key Topics Open-sourcing Shipwright (MIT) — PRD → plan → code → tests → PR → CI → review → merge → deploy, mostly hands-off "Shipwright built Shipwright" — ~500 PRs, the founders read essentially none of the code The 14-step dev-task checklist (TDD, green CI, docs) vs. raw Claude Code's half-baked PRs Human-in-the-loop only where it must be — Terraform applies, secret/key updates, GitHub access Run it in your own cloud (EC2/EKS/AKS/Kubernetes) — you control security, secrets, and tokens The economics: 10X throughput for free, but it also 10X's token spend and pressures headcount Portable by design — a thin Claude shim means it can move to OpenCode/Pi and open-source LLMs later Notable Quotes "If you have an engineering team and you're choosing not to adopt this, you are choosing not to 10X your throughput on purpose." "Shipwright created Shipwright. It has 500 pull requests... I didn't look at a single line of code." 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

    27 min

  3. Jun 21

    We Built an Agent That Ships 85 PRs a Week

    Episode Summary Dave and Dan pull back the curtain on the autonomous coding agent they built — an agent that lives in the cloud, takes instructions in Slack, and runs a full plan-to-deploy pipeline 24/7. In the last seven days alone, their agents opened 85 pull requests. They walk through exactly how the system works and why "build the system" beats "write the code." Key Topics Talk to your agent in Slack — an agent that lives in the cloud, writes code, and runs around the clock. 85 PRs in a week — the metric that frames the whole episode, and what it says about building systems over writing code. Brainstorm → PRD → Plan → Tasks — the interactive front of the pipeline, where the human stays in the loop. The four crons — dev task, review, patch, and deploy fire every 30 minutes and only burn tokens when there's real work pending. Right-sized tasks — why a 1,000-line PR fails and how the plan session breaks work into manageable, one-commit-sized tickets. Mandatory canary deploys — merge to main, canary, promote to prod, with automatic rollback and Slack alerts when telemetry looks wrong. Everything is metered — PostHog metrics on every step, used to wake up to "what did the agents do overnight?" and to keep improving the system. Notable Quotes "We said it a million times — you don't need to code anymore if you build a system. So we built a system." "You're gonna flip your laptop open on Monday morning and there's 24 PRs — all done, all passing green, all ready to be reviewed and deployed." "If you build the right system, not only do you not need to code — you don't even need to watch your deploys." 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

    23 min

  4. May 28

    Anyone Can Vibe Code. Did You Build the System?

    Episode Summary If AI handles the coding, then being an engineer means planning and reviewing — the work of staff and principal engineers. But that breaks the career ladder: how does anyone become senior when the junior rungs disappear? Dave and Dan dig into where senior engineers come from now, why juniors still add value on top of Claude, builders versus maintainers, and how interviewing changes when anyone can vibe-code. Key Topics The vanishing junior rung — if seniority is "planning and reviewing," how do you climb without junior work to learn from? Adding value on top of Claude — good juniors ship more complete PRs than Claude alone, and compress a 5–10 year career into a couple of years. Builders vs. maintainers — the "commandos and palace guards" framing, reimagined: builders extend the system, maintainers keep the harness healthy. Claude is no longer a junior — with the right harness it plans, tests, lints, simplifies, and reviews like a solid mid-level or senior engineer. Robots ship, humans plan — the autonomous agents do the shipping 24/7; the builder's thrill now comes from queuing tasks, not typing code. Interviewing in the agentic era — show what you built with Claude, then show the system you built to build it. Anyone can vibe-code; the differentiator is the system. Notable Quotes "Right now, as of May 2026, if you're writing code, you shouldn't be. You're doing something wrong." "Anyone can vibe code anything nowadays — but the differentiator is, did you build a system to build it?" "You and I aren't shipping anything. Our autonomous coding robots that live in the cloud and work 24 hours a day, they're the ones actually shipping." 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

    18 min

  5. May 26

    I Had a Therapy Session with Claude

    Episode Summary Dave and Dan get candid about the most uncomfortable question in software right now: is my career still safe? Dan recounts a literal "therapy session with Claude" that exposed his 20-year sense of job security as a false one — and the two work through what to actually do about it. The throughline: AI isn't ending engineering, it's reshaping it, and the people who refuse to engage are quietly opting themselves out. Key Topics The career-identity crisis — "Am I gonna be a waiter a year from now?" and why even all-in AI users feel it False security — how a 20-year "solid foundation" got disrupted, and the story your brain still tells you From DevOps engineer to "Claude Code something" — losing and rebuilding a professional identity Self-selecting out — why opting out of AI tooling is opting out of a career Layoffs vs. AI — separating balance-sheet cuts from the real AI signal, and why AI-forward companies are hiring The advice for every developer in May 2026: embrace change, go all in, and go build the side projects you never could Notable Quotes "If you're choosing to not use Claude Code, you are self-selecting yourself out of a career at this point." "Stability in my career feels like it might be crumbling underneath my feet — and Claude told me that was a false sense of security all along." 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

    11 min

  6. May 22

    If You're Still Writing Code, You're a Dinosaur

    Episode Summary Org-wide AI transformation keeps failing — not because the tech doesn't work, but because trying to move 200 engineers at once turns into a slog. Dave and Dan break down what they see in the field: tool sprawl, the very real fear engineers feel about being the ones disrupted, and the trap of tripling your Claude bill without shipping any faster. Their fix: skip the org-wide rollout, embed a small tiger team on your most important product, and build a system the rest of the company can adopt later. Key Topics Why moving the whole org is too slow — and why a small embedded team builds momentum faster Tool sprawl: pick one (Claude Code) instead of juggling Copilot, Codex, Cursor, and a now-canceled Gemini CLI The fear factor — engineers wired for change now find themselves the target of disruption The bill-tripled-but-no-faster trap as a clear signal AI adoption has failed Flattening the org: top-heavy management and bureaucratic gates slow speed AI should unlock "If you're still writing code, you're a dinosaur" — the shift from writing code to planning, reviewing, and mentoring the system Notable Quotes "Listen, CEOs and CTOs, if your developers are still writing code, you're behind the curve. They should not be writing code." "We doubled our bill, but we're not shipping faster — that's a symptom that your org-wide AI adoption has failed." "Don't try to move the whole org. Get in with a small team and see things move fast." 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

    16 min

  7. May 20

    Anthropic Just Ended the AI Free Ride

    Episode Summary Anthropic is taking the gloves off. The VC-subsidized era of essentially-free AI agents is ending: OAuth tokens lose Open Cloud coverage, Claude Code Max plans are getting throttled for autonomous workloads, and Dave & Dan are staring at a $200/mo → $1,000+/mo jump for their ShipRight background agents. The episode is a candid talk about what changed, why it was inevitable (the Uber-pricing parallel), and the operator choices ahead: optimize aggressively, gate non-deterministic crons, mix cheaper models for execution, or just eat the cost as a line item. Key Topics What changed: OAuth/Open Cloud coverage cut, autonomous-coding workloads pushed toward per-token API pricing The numbers: $200/mo plan vs ~$1,000–$5,000/mo if the same work ran on API tokens (at least 10×) Why this was inevitable — the Uber bridge-toll parallel: VC subsidies don't last forever Operator optimization moves: gate crons behind deterministic checks, split planning vs execution across models, tighten permissions on always-on laptops Phone-as-prompter workflow: Caffeinate-running laptop + mobile Claude as the in-the-loop interface, OAuth-covered Why we're staying with Claude: ecosystem (skills, plugins, MCP) still beats Codex even if pricing changes What this means strategically: AI economics are about to look like real economics — plan accordingly Notable Quotes "We're seeing this happen with Anthropic right now. They're taking the gloves off. They're pulling out the subsidies." "$200 a month, if you're paying API tokens, would be like $5,000." "This is gonna force some of us to be a little bit more conservative about how we use AI." 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

    13 min

  8. May 18

    Testing Is Phase Zero for AI Agents

    Episode Summary Dave and Dan dig into service readiness — the industry calls it "harness engineering" — and why testing just moved to the #1 spot of their 13 repo-readiness pillars. Before you let agents ship code in the background, the question isn't 90% coverage; it's whether anyone actually trusts the tests. They walk through the onboarding plugin that gets a repo test-ready and how test decisions get baked into the agent's planning phase instead of left to human best-effort. Key Topics Why "no one has confidence in the tests" is universal — slow, flaky, and thin coverage everywhere Testing as pillar #1 of 13 for agentic-engineering readiness ("phase zero") The test-onboarding plugin: research versions → design the greenfield ideal → reconcile what to keep vs. throw out → a reviewed task list All four layers in scope: unit, integration, end-to-end, smoke — plus migrations, seeds, and integrations Baking "which tests does this need?" into the agent's planning phase rather than relying on a human to remember Coverage dogma vs. reality: test what matters, but keep 90% in CI as the practical proxy The daily cron that catches coverage gaps and staleness; local-first test execution for agents Notable Quotes "Every organization we've pretty much ever worked for — no one has confidence in the test. The tests are slow, the tests are flaky, and they don't cover enough stuff." "How do you know that you can trust your agent to ship code that's gonna work?" "We said 90% coverage — great philosophy. Three months later we realized maybe the 10% is the one that matters." 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

    19 min
See All (25)

About

Dave O'Dell and Dan McAulay work inside engineering organizations every day, helping them ship faster with AI — not in theory, but inside their actual teams. Each week they share what they're seeing in the field: what's working, what isn't, and what most people are getting wrong. Covering Claude Code updates, AI-enabled SDLC acceleration, and personal AI agents. No hype, no BS.

Information

  • Creator
    Dave O'Dell and Dan McAulay
  • Years Active
    2K
  • Episodes
    25
  • Rating
    Explicit
  • Copyright
    © 2026 Dave O'Dell and Dan McAulay
  • Show Website
    The Velocity Lab