How We Built ‘Claudie,’ Our AI Project Manager (Full Walkthrough) (47 min)
- Release date: 2026-02-04
- Listen on Spotify: Open episode
- Episode description:
A few weeks ago, Natalia Quintero wouldn’t have called herself technical. But since the beginning of January, she has woken up at 6 a.m. to vibe code with Claude. The AI project manager she built saved her 14 hours a week. Getting there meant scrapping the system three times and starting over. But the result handles everything from onboarding new clients to generating weekly updates across all projects.Natalia is the head of AI consulting at Every. As part of the role, she's spoken with over 100 organizations in the past year and worked with a select two dozen, including hedge funds, private equity firms, and Fortune 500 companies. She’s seen what separates companies thriving with AI from those floundering, and it comes down to patterns that have nothing to do with having the most resources or the fanciest tools.Dan Shipper had her on AI & I to share what she’s learned from this front-row seat to AI adoption. Quintero reveals how a private equity firm cut investment memo creation from three weeks to 30 minutes, why AI adoption needs to come from the top down, and what happened when she learned from her early morning experiments.She also explains why the companies going furthest with AI are the ones that give employees permission to fail—and how that counterintuitive approach is revolutionary.If you found this episode interesting, please like, subscribe, comment, and share! Want even more?Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free.To hear more from Dan Shipper:Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Ready to build a site that looks hand-coded—without hiring a developer? Launch your site for free at www.Framer.com, and use code DAN to get your first month of Pro on the house.Timestamps: 00:00:00 - Introduction00:01:30 - Why successful AI adoption requires coordinated, top-down effort00:07:05 - How a private equity firm reduced investment memo creation from weeks to 30 minutes00:13:30 - The benefits of connecting AI to proprietary context00:15:20 - The plan-delegate-assess-compound framework for engineering teams00:17:55 - How non-technical team members are becoming vibe coding addicts00:20:50 - Building Claudie: an AI project manager from scratch00:23:00 - Why creative exploration time outside the 9-to-5 is essential00:27:50 - Live demo: How Claudie automates client onboarding and tracking00:38:40 - The human side of AI: spending less time in spreadsheets, more time with peopleLinks to resources mentioned in the episode:Natalia Quintero: Natalia Quintero (@NataliaZarina)What Natalia learned from working with companies on AI adoption: https://every.to/on-every/the-next-chapter-of-every-consultingEvery’s compound engineering plugin: https://github.com/EveryInc/compound-engineering-plugin
Summary
- 👑 Top-Down Commitment: AI succeeds with CEO-led coordination, not delegation; active use sets organizational pace and culture.
- 🏆 Champion Power Users: Elevate early adopters to train peers, fostering experimentation and scaling wins across teams.
- 🗺️ Task Mapping Magic: Detailed workflow audits reveal high-leverage AI spots, like 30-min investment memos vs. weeks.
- 🔄 PDAC for Engineers: Plan-Delegate-Assess-Compound framework yields 2 weeks’ work in an afternoon for big problems.
- 🤖 Agent Revolution: Claudie auto-manages projects via subagents, slashing admin time and freeing humans for relationships.
Insights
Why does top-down leadership make or break AI adoption in companies?
Time: 2:48 – 5:52
Category: AI in Workforce DisruptionAnswer: Successful AI integration requires coordinated efforts from leadership to identify use cases, track usage, and empower teams, preventing it from being limited to a few power users. Companies thrive when CEOs actively use tools like Claude, setting the pace for the organization. This contrasts with past software adoptions where bottom-up worked fine. (Start at 2:48)
How can empowering AI champions unlock creative experimentation across teams?
Time: 4:10 – 7:13
Category: AI in Workforce DisruptionAnswer: Identifying and elevating natural early adopters allows them to train peers and rethink roles, fostering a culture of trial, failure, and scaling wins. This bottoms-up energy, combined with top-down support, spreads high-leverage AI use. Standups sharing new use cases exemplify organic spread. (Start at 4:10)
What makes detailed task mapping the secret to high-leverage AI in finance?
Time: 8:59 – 11:10
Category: AI-Driven Innovation EconomyAnswer: Mapping every investor task—from research to memos—reveals precise AI opportunities, like drafting investment memos in 30 minutes vs. 2-3 weeks using firm-specific theses. An internal champion understanding people dynamics ensures tailored solutions. This precision drives bandwidth and quality gains. (Start at 8:59)
How do custom prompts turn AI into a dependable ‘analyst’ for complex workflows?
Time: 11:28 – 15:52
Category: AI-Driven Innovation EconomyAnswer: Tailored prompts incorporating decade-old investment theses and sector-specific thinking synthesize data into high-quality drafts rapidly. Connecting AI to proprietary data with clear instructions on metrics elevates it beyond generic use. This ‘Savile Row’ customization creates reliable leverage. (Start at 11:28)
Why is adding a ‘planning’ phase revolutionary for AI in engineering teams?
Time: 16:26 – 18:27
Category: AI in Workforce DisruptionAnswer: The plan-delegate-assess-compound framework scaffolds big problems; engineers lacking planning solved small issues but not meaty ones. With it, they now generate 2 weeks of work in an afternoon, compounding leverage. This targeted enablement turns AI into a high-leverage machine. (Start at 16:26)
How does ‘vibe coding’ early mornings spark addictive AI innovation?
Time: 19:36 – 26:13
Category: AI in Everyday LifeAnswer: Carving out unstructured time outside 9-5 for tinkering—like building a project manager agent—leads to breakthroughs after iterations. Paired with expert partners, non-technical leaders codify workflows into agents. This risk-free play shifts mindsets from horse-and-buggy to cars. (Start at 19:36)
Can AI agents like Claudie replace project managers and free humans for high-value work?
Time: 30:11 – 44:50
Category: AI in Everyday LifeAnswer: Claudie uses subagents to scan Gmail, Calendar, Drive, and transcripts, auto-populating dashboards with client data, open items, and sessions—reducing 10-15 hours/week to 1. Ongoing iteration builds reliability, like managing staff. This shifts focus to client relationships and strategy. (Start at 30:11)
Why must AI agents know their ‘job description’ and data conventions like humans?
Time: 30:31 – 35:23
Category: AI in Everyday LifeAnswer: A Claude.md file provides context on role, colleagues, data sources, ID conventions for relational tracking, and principles like proactivity and accuracy. This ensures consistent, high-fidelity outputs across commands like client onboarding. Boundaries make smart models like Opus excel. (Start at 30:31)