CEO @ Mindstudio, ex-CTO @ MySpace
GenAI Product Builder @Google, ex-Meta

.webp&w=768&q=75)
3 people enrolled last week.
Master Claude Code & Hermes Agent hands-on, then learn to evaluate agentic systems like a pro. Go from simply using AI to building full-stack applications & deploying autonomous agents.
3 learnable skills: directing Claude Code like an eng team, operating a Hermes Agent that runs 24/7 on your own infrastructure & gets smarter every week, & evaluating agentic systems so you can prove they work instead of hoping they do.
3 weeks. Your machine. Your real work. By the end, you have running agents.
✨ Week 1 — Hands-on Claude Code: Specs, plans, subagents, skills, MCP. You'll ship a working tool by Friday.
✨ Week 2 — Hands-on Hermes Agent: Deploy it on your own infra, connect it to Slack/Telegram, put it on a schedule, & customize it to your specific use cases.
✨ Week 3 — Evals for Agentic Systems: Define success, build eval sets, catch failure modes & ship agents you can defend in a roadmap review.
𝙏𝙤𝙤𝙡 𝙡𝙞𝙨𝙩 Claude Code, Hermes Agent & practical eval tooling & patterns you can apply to any agent.
No coding experience required. If you can write a paragraph, you can drive these tools.
Go from demoing AI features to deploying — and rigorously evaluating — agents that automate real work!
Use plan mode, subagents, and skills to manage complex multi-step work.
Connect Claude Code to your data and tools via MCP.
Use Garry Tan’s GStack to evaluate your product specs, architecture, and roadmap, exactly like they do at YCombinator.
Install Hermes Agent. Configure it for your custom use cases.
Set up Garry Tan’s GBrain for long-term memory – never forget a person, meeting, etc.
Set up intelligent multi-model routing (for quality and cost control)
Use Hermes's skills system to turn one-off solutions into permanent capabilities.
Shape agent behavior with smart context injection and persistent memory / recall.
Set up self-learning, self-tuning loops that are constantly making your agent better.
Define what "working" means before you ship — success criteria, not vibes.
Build eval sets that catch regressions, hallucinations, and silent failures.
Set up cost controls, guardrails, and sophisticated observability.
Leave with deployed Claude Code project(s) AND a running, personalized Hermes agent.
Clearly understand the fundamentals of agentic systems, so that you can understand where things are going, and what is real / hype.
Earn a certification you can put on LinkedIn and back up in an interview.
Ongoing Skool community of PMs and operators shipping agents.
Share skills, eval templates, and deployment patterns after the course ends.
Get feedback on your real-work agent projects, not toy demos.

CEO @ Mindstudio, ex-CTO @ MySpace
.webp&w=384&q=75)
Gen AI PM Lead @ Google | ex-Meta, Fellow @ Harvard | TED AI Speaker | 40 u 40
Product Leaders & Senior PMs that want to lead in an AI-native world—not just react to it
Founders & Operators that want to replace manual workflows with agents and build real leverage
Live sessions
Learn directly from Dmitry Shapiro & Dr. Marily Nika 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.
8 live sessions • 16 lessons
Jul
25
Jul
21
Jul
23
Jul
30
Aug
1
Jul
28
![AI Agent Building Bootcamp for Product Managers [2hrs] cover image](/_next/image?url=https%3A%2F%2Fd2426xcxuh3ht5.cloudfront.net%2F5HwyGB34Rj6NyjSFsu8P_3.jpg&w=768&q=75)
Learn the exact steps to turn a concept into a working agent—without needing to write code.
See how to link multiple components together so your agent does something useful, not just impressive.
Use a proven framework to explore ideas quickly, iterate effectively, and avoid common mistakes.
By the end of the bootcamp, you will have fundamental skills to build AI Agents for you, your team, and your customers.
Live sessions
2-4 hrs / week
Sat, Jul 25
4:00 PM—5:00 PM (UTC)
Tue, Jul 21
6:00 PM—7:00 PM (UTC)
Thu, Jul 23
5:00 PM—6:30 PM (UTC)
Projects
1-6 hrs / week
Optional Capstone participation impacts time commitment.
Async content
1-3 hrs / week
Additional content to help you level-up.
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$1,999
USD
2 days left to enroll