How I AIClaude Code for product managers: research, writing, context libraries, custom to-do system, more
Claire Vo and Teresa Torres on teresa Torres uses Claude Code to automate PM workflows daily.
In this episode of How I AI, featuring Claire Vo and Teresa Torres, Claude Code for product managers: research, writing, context libraries, custom to-do system, more explores 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.
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
QUESTIONS ANSWERED IN THIS EPISODE
5 questionsCan you show the exact /today prompt and the Python script responsibilities—what’s handled by Claude vs. code?
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.
What’s your tag taxonomy for tasks (e.g., sales pipeline), and how do you prevent tag sprawl as Claude suggests new tags?
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.
How do you handle recurring tasks, subtasks, and projects in your markdown-based system without recreating a full PM tool?
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.
What does your research summary template look like (methods, effect size, limitations), and how did you prompt/implement it to avoid generic abstracts?
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.
How do you track “papers already seen” across arXiv and Google Scholar, and how do you de-duplicate near-identical preprints/versions?
Chapter Breakdown
Teresa Torres’ background and why she’s all-in on Claude Code
Teresa Torres (Continuous Discovery Habits) explains how her AI usage evolved from web chat tools into Claude, then into Claude Code inside VS Code. The key shift is treating Claude like a pair-programming partner for non-coding work too.
Escaping Trello lock-in: building a personal task system with Claude
Teresa shares the motivation behind creating her own task management workflow: heavy note-taking and fear of losing or locking away her data in Trello. Moving tasks into a text-first system makes them searchable, portable, and AI-actionable.
Demo: the /today slash command that generates her daily plan
Teresa demonstrates a custom Claude Code slash command that compiles her day automatically. It creates a “today” file, pulls in due/overdue tasks, ongoing ideas, and research digest items—turning a daily ritual into a one-command workflow.
Under the hood: Markdown + Obsidian as the task database
The system is built on plain Markdown files stored in Obsidian, where each task has structured YAML front matter. Claude (and scripts) can reliably query these files by due date, type, and tags, enabling fast automation without a GUI.
Creating a new task in seconds (and why speed matters)
Teresa shows how she creates a new task by simply typing an instruction to Claude while working in the terminal. The benefit is avoiding slow, click-heavy interfaces and capturing tasks in the same environment where she’s already operating.
Claude-driven tagging and flexible views (e.g., sales pipeline on demand)
A major advantage of Teresa’s system is that Claude handles task tagging, making it easy to generate dynamic views like a sales pipeline without manual upkeep. She maintains a tag taxonomy with Claude to keep the system consistent over time.
Embedding work notes inside tasks for powerful retrieval
Teresa keeps in-progress notes directly inside the task file, including bugs and partial work state. This creates a searchable “work journal,” and Claude helps recover details even when she only vaguely remembers what she wrote.
Daily automated research digest: turning an academic firehose into a routine
Teresa explains a workflow that delivers a daily research digest into her task list. She scans titles/abstracts, manually downloads a few PDFs, and gets high-quality method-focused summaries the next day.
How the research plugin works: scripts, cron jobs, and summarization agents
She built the research system as a plugin backed by two Python scripts running on cron schedules. One gathers new papers from sources; the other detects newly saved PDFs and triggers Claude Code agents to produce structured summaries.
Summaries that emphasize rigor: methods, measures, and effect sizes
Teresa intentionally designed her summarization prompt to focus on the parts that matter for judging research quality. This lets her quickly spot weak measurement choices and decide whether a paper is credible or useful.
Extending the idea: competitive analysis and other information digests
Beyond academic research, Teresa describes using Claude to “Google for her” and generate structured reports like competitive analyses. She also imagines similar digests for social content (e.g., LinkedIn), though API access is a constraint.
Context libraries: building small, reusable files for ‘lazy prompting’
Teresa maintains an “LLM context” vault: many small, focused Markdown files covering business and personal context, plus a writing style guide. She learned that too much context hurts performance, so she uses indexes to load only what’s needed.
Claude as a writing partner: research checks, critique, hooks, and typos
Teresa doesn’t want to automate her writing, but uses Claude heavily for augmentation: validating claims, strengthening hooks, critiquing sections, and cleaning up errors. The custom style guide makes feedback specific and aligned to her voice.
Lightning round: tool stack, feature wishes, and what to do when Claude gets stuck
Teresa shares she mostly sticks with Claude Code + VS Code rather than chasing new tools like Cursor. When Claude derails, she resets with /clear and relies on documentation/context files to restart without re-explaining everything.
EVERY SPOKEN WORD
Install uListen for AI-powered chat & search across the full episode — Get Full Transcript
Get more out of YouTube videos.
High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.
Add to Chrome