By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
How I AIClaude Code for product managers: research, writing, context libraries, custom to-do system, more
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
At a glance
WHAT IT’S REALLY ABOUT
Teresa Torres uses Claude Code to automate PM workflows daily
- Teresa Torres explains why she shifted from browser-based AI and Trello-centric work to Claude Code in the terminal: speed, flexibility, and treating AI like a pair-programming partner for non-coding tasks.
- She demos a custom task management workflow built on local markdown files (viewed in Obsidian) and a /today slash command that compiles due/overdue tasks, in-progress ideas, and a daily research digest.
- She then shows an automated academic research pipeline (arXiv daily + Google Scholar weekly) that filters results, queues selected PDFs, and generates high-signal summaries focused on methods and effect size via scheduled scripts.
- Finally, she shares a scalable “context library” approach—many small, indexed files (style guide, business profile, products, audience, etc.)—so Claude can load only relevant context, enabling “lazy prompting” and faster resets when the model gets stuck.
IDEAS WORTH REMEMBERING
5 ideasTreat Claude Code like a pair-programming partner for everything.
Teresa’s core shift is mindset: once Claude sits “next to” your work in the terminal/VS Code, you can pair-manage tasks, research, and writing the same way engineers pair-program—iteratively and quickly.
Own your work by keeping tasks and notes as local markdown files.
She moved away from Trello as a personal system because notes felt locked in a third-party tool and were hard to search; markdown in a local folder is portable, inspectable, and AI-readable.
A single daily command can assemble your whole day’s operating view.
Her /today slash command compiles due tasks, overdue items, in-progress ideas, and research prompts into a generated “today file,” reducing decision fatigue and UI clicking.
Structure tasks with simple metadata so AI can query them reliably.
Each task is a file with YAML front matter (type, due date, tags). Claude (and scripts) can then accurately find “due today,” “past due,” or “sales-tagged” work without brittle manual filtering.
Let AI do the tagging and taxonomy maintenance, not you.
Instead of relying on human discipline to tag tasks, Claude proposes tags and Teresa refines a tag taxonomy in a project-level Claude.md—co-creating the system while offloading the grunt work.
WORDS WORTH SAVING
5 quotesBy moving my task management to Claude, now Claude sees my tasks, and I can literally start my day and be like, “Claude, what’s on my to-do list that you can just do for me?”
— Teresa Torres
I didn’t have to open a web browser… I literally just typed, like, off-the-cuff notes to Claude.
— Teresa Torres
The search is not that good… Claude will try every permutation of searches till it finds it.
— Teresa Torres
To do context well… we have to document everything in teeny-tiny files.
— Teresa Torres
When Claude gets stuck, I want Claude to go away… ‘Slash clear, we’re starting over.’
— Teresa Torres
High quality AI-generated summary created from speaker-labeled transcript.
