Supercharge Claude Cowork with your own AI Second Brain
Sesha Pratap
AI Consultant and Advisor
A second brain is the easiest way to supercharge your use of Claude Cowork
Your project doesn't live in one place. It's spread across meeting notes, Slack threads, email, and documents. The problem is that Claude sees almost none of it.
Claude answers from the files you upload to a Project, so it answers with a fraction of the full context of your project. And nothing accumulates: every insight you work out remains locked in a chat session.
An AI second brain fixes both problems. It's a living, interlinked wiki inside your Claude Project that Claude writes and maintains itself, so every source you add makes every future answer sharper.
In 2.5 hours, you'll build one end-to-end second brain that works for you. We'll scaffold it inside a Project, then ingest your real sources — meeting notes, Slack threads, email, documents.
You'll also learn the upkeep routine: how to set up skills to ingest new information as it arrives, how to reconcile it with what's already there, and how to run a health check so the brain never goes stale. You'll also learn to run separate brains for separate clients without the wires crossing.
Bring a real project. You'll leave with a live, populated second brain that keeps itself current and supercharges your project.
What you’ll learn
Learn to build AI knowledge bases, and become the person whose projects never lose context — however many you're running
Build a complete second brain inside a Claude Project with the full folder and file structure
Learn how to build an AI second-brain skill so you start with working scaffolding instead of a blank project
Ingest your real project sources: meeting notes, Slack threads, email, documents, and research
Claude answers from the whole project rather than the handful of files you remembered to upload.
Configure the CLAUDE.md rules that govern how Claude summarises, files, cross-references and links new material
The second brain stays coherent as the project wiki grows, instead of degrading into a dumping ground of stale context.
Design the upkeep routines that ingest new information as it arrives and reconcile it against what's already there
Automatically handle situations when new sources contradict old ones, so the context remains robust and relevant
Generate an actual deliverable from your wiki - a synthesis, brief, or report that leverages the knowledge in the project wiki
Compound outcomes back into the brain, so every piece of work you do adds to the project wiki and makes it more valuable
Architect multiple project brains that stay isolated from each other, with a shared layer for knowledge worth reusing
Run several clients or projects without cross-contamination, or learn how to share project brains with coworkers
Workshop agenda
Set up your workspace and choose the project you'll build a brain for
Get Cowork ready, pick a live project with real sources behind it, and see the finished structure before we start, so you know exactly what you're building and why each part exists.
Scaffold your second brain inside a Claude Project
Run the ai-second-brain skill to create the raw/, wiki/, and CLAUDE.md structure in minutes, then walk through what each part does and examine the whole output of markdown files.
Write the CLAUDE.md rules that make Claude a disciplined librarian
Configure how Claude summarises, files, names, and cross-links pages. These rules are what keep a wiki coherent at 200 pages instead of degrading into an unstructured dumping ground.
Ingest your real sources: meeting notes, Slack, email and documents
Pull in the material your project already generates and watch Claude compile each source into interlinked wiki pages, rather than parking it as one more static file to search.
Build the upkeep routine that stops your brain going stale
Set up how new information arrives, how Claude reconciles it against existing pages, and what happens when sources contradict each other. Then run a health check on what you've built.
Generate a real deliverable, then compound it back into the wiki
Use your brain to produce something you actually need — a synthesis, brief, or report — then file the result back in, so every piece of work you do makes the next one faster.
Run multiple project brains, and keep yours alive after today
Structure separate brains for separate clients with a shared layer for reusable knowledge, plus the habits that keep them current. Open Q&A to finish.
Learn directly from Sesha
Sesha Pratap
Startup founder, AI consultant, AI product manager
Who this workshop is for
Product and project leaders on complex, long-running work. Your work history is spread across multiple sources
Consultants and fractional leaders running several clients at once. You switch between clients, each one with its own context and history.
Founders, executives or managers who are their project's key memory. Everything important is in your head or in files you have to re-read
What's included
Live sessions
Learn directly from Sesha Pratap in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$200
USD
6 days left to enroll
1–3pm EDT