scripod.com

How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)

How I AI

6 HOURS AGO
How I AI

How I AI

6 HOURS AGO

Shownote

Daniel Blum is a product manager at Melio, a B2B payments company, and one of the most systematic thinkers I’ve had on the show when it comes to personal AI infrastructure. He’s spent the past year building a Claude- and Cowork-based productivity system that manages his Notion board, processes his Slack and email, and runs self-improvement loops every week without needing to be prompted. Beyond his own workflow, Daniel built and scaled a “Workstation” onboarding plugin that gets any Melio employee up and running with a personalized Claude setup in about 15 minutes. What you’ll learn: 1. Why Daniel says the two rules that make any AI system powerful aren’t about the tool you pick 2. How his weekly prep automation fills an entire Notion board from scratch every Sunday, without his touching it 3. The morning brief feature that teaches Claude new internal terms on its own, so company jargon never slows it down 4. Why he describes Notion as “read-only” now, and what that says about how PM workflows are changing 5. The self-improvement loop that watches Daniel’s edits, spots recurring friction, and suggests new skills to build 6. How he uses a skill called “Improve” to filter the endless flood of AI tips without drowning in them 7. What he built to scale his personal system to every PM at Melio, and the UX lesson he learned the hard way 8. The capability gap that’s still keeping him from running 100% of his work through Claude — Brought to you by: Optimizely [https://optimize.ly/3KD565S]—Your AI agent orchestration platform for marketing and digital teams Jira AI SDLC [https://ad.doubleclick.net/ddm/trackclk/N320202.6053656HOWIAI/B36397005.454541156;dc_trk_aid=648366078;dc_trk_cid=262806969;dc_lat=;dc_rdid=;tag_for_child_directed_treatment=;tfua=;gdpr=$%7BGDPR%7D;gdpr_consent=$%7BGDPR_CONSENT_755%7D;ltd=;dc_tdv=1]—Get your tokens’ worth with Jira — In this episode, we cover: (00:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw]) Daniel’s background and the PM overhead problem he needed to solve (03:30 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=210s]) His AI stack at Melio (05:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=300s]) The two rules that make any AI system genuinely powerful (06:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=360s]) The Notion board Cowork built for him (and manages on his behalf) (07:30 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=450s]) How he contextualizes Claude with voice memos, links, and recurring updates (09:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=540s]) His weekly prep automation (11:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=660s]) His morning brief (15:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=900s]) How Claude flags unknown internal terms and saves them to context (17:30 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1050s]) Running 70% to 80% of his workday through Cowork (19:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1140s]) Chrome connector vs. MCPs for tools without integrations (20:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1200s]) The real ROI question: why the early weeks feel slow, and why you push through anyway (25:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1500s]) Scaling the system to the team with the Workstation plugin (26:30 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1590s]) The self-improvement loop (31:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1860s]) How the Improve skill separates actually useful AI tips from the hype (32:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=1920s]) The Workstation onboarding flow, and the UX lesson from distributing “Spectacular” (38:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=2280s]) The 20% Claude still can’t do, and what changes when it can (41:00 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=2460s]) What Daniel spends his reclaimed time on (42:30 [https://www.youtube.com/watch?v=p2qmX6TM0kw&t=2550s]) Claude rage — Tools referenced: • Claude: https://claude.ai [https://claude.ai/] • Notion: https://notion.so [https://notion.so/] — Other references: • From a $6.90 newsletter to $3M API: How a non-coder built Memelord | Jason Levin: https://www.lennysnewsletter.com/p/from-a-690-newsletter-to-3m-api-how?utm_source=publication-search [https://www.lennysnewsletter.com/p/from-a-690-newsletter-to-3m-api-how?utm_source=publication-search] • How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman: https://www.lennysnewsletter.com/p/how-the-founder-of-morning-brew-built?utm_source=publication-search [https://www.lennysnewsletter.com/p/how-the-founder-of-morning-brew-built?utm_source=publication-search] — Where to find Daniel Blum: LinkedIn: https://www.linkedin.com/in/blumd/ [https://www.linkedin.com/in/blumd/] Website: https://www.imdanielblum.com [https://www.imdanielblum.com/] — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ [https://www.chatprd.ai/] Website: https://clairevo.com/ [https://clairevo.com/] LinkedIn: https://www.linkedin.com/in/clairevo/ [https://www.linkedin.com/in/clairevo/] X: https://x.com/clairevo [https://x.com/clairevo] — Production and marketing by https://penname.co/ [https://penname.co/]. For inquiries about sponsoring the podcast, email jordan@penname.co.

Highlights

This episode explores how Daniel Blum built an AI-centered operating system to reduce the administrative burden of product management and create more time for higher-value work.
02:53
AI exposes the problems productivity tools missed
03:35
Cowork transforms how work gets coordinated
05:04
The real value is a self-rewriting system
06:05
Cowork turns scattered tasks into organized priorities
07:32
Deep context makes Claude more effective
09:03
Connected data keeps AI workflows current
11:03
Useful systems must reflect reality, not just plans.
15:00
Morning briefs turn scattered information into actionable context.
17:30
Claude preserves terminology while managing the board.
19:01
AI handles most routine computer work
20:00
AI's value compounds with continued use
25:01
AI must scale across the product team
26:30
AI improves fastest when it studies your edits
31:03
Rejected edits drive continuous improvement
37:40
Shared AI skills create a stronger company-wide baseline
38:02
AI compresses a week of PM work into one day
41:05
Automation creates space for deeper product work
42:34
AI frustration deserves a benchmark

Chapters

Daniel’s background and the PM overhead problem he needed to solve
00:00
His AI stack at Melio
03:30
The two rules that make any AI system genuinely powerful
05:00
The Notion board Cowork built for him (and manages on his behalf)
06:00
How he contextualizes Claude with voice memos, links, and recurring updates
07:30
His weekly prep automation
09:00
His morning brief
11:00
How Claude flags unknown internal terms and saves them to context
15:00
Running 70% to 80% of his workday through Cowork
17:30
Chrome connector vs. MCPs for tools without integrations
19:00
The real ROI question: why the early weeks feel slow, and why you push through anyway
20:00
Scaling the system to the team with the Workstation plugin
25:00
The self-improvement loop
26:30
How the Improve skill separates actually useful AI tips from the hype
31:00
The Workstation onboarding flow, and the UX lesson from distributing “Spectacular”
32:00
The 20% Claude still can’t do, and what changes when it can
38:00
What Daniel spends his reclaimed time on
41:00
Claude rage
42:30

Transcript

Daniel Blum: I cannot describe how powerful it is. I'm really able to do in a day now what used to take me a week. But more than that, I'll say it's a lot of deeper work. There's things that I do today that I just wasn't able to do before, whether it's mor...