Ramp Ships 500+ Features Using Claude Code

If you want to master building enterprise-level AI products from scratch and future-proof your career with the most important AI skills, this #1 AI PM Certification is for you.

Run by real AI operators: Rohan Varma (ex-cofounder, first ever PM at Cursor, now at Codex) & Henry Shi (former co-founder of Super.com, a $200M+ ARR company, now technical staff at Anthropic Labs, working directly with the founders).

3,000+ AI PMs graduated  ·  1,000+ reviews on Maven — highest in any category

#1 𝕏

Peter Yang: Ramp shipped 500+ features last year with just 25 PMs using Claude Code’s 3-phase skill—phase 1 frames the problem with defendable pushback questions, phase 2 spins up 6–10 parallel agents to scan competitors, Gong calls, Zendesk tickets and code, and phase 3 conv...

#2 𝕏

Santiago processed PDFs with Claude Code by copying them into a folder and asking it to read them. The tool then auto-installed poppler and pdftoppm, enabling seamless opening and processing of the files.

#3 𝕏

There's An AI For That launched MedOS, a Stanford-Princeton built clinical co-pilot combining AI reasoning, XR smart glasses and robotics. It’s already live in Stanford hospitals and was showcased at NVIDIA GTC 2026.

#4 in

Marc Baselga found that teams adopt coding agents best by starting with one specific workflow and assigning Carl Vellotti’s CC Course as pre-work to prevent overwhelm and build a solid foundation.

#5 in

Dharmesh Shah says the new 1M-token context window for agentic coding isn’t just about handling more code—it frees him from context anxiety so he can steamroll through tasks without ever hitting the limit.

#6 𝕏

dharmesh confirms that cracking the SMB market is “hard mode” for HubSpot, but once you solve the unit economics, it becomes a powerful moat.

#7 𝕏

Aravind Srinivas Perplexity has surpassed 100M+ cumulative Android downloads and is set to boost distribution further with an upcoming Samsung native integration.

#8 📝 Simon Willison

Sunsetting Jazzband - Jazzband is ending its previous open-membership model because the recent flood of AI-generated spam PRs and issues makes shared push access unsafe. The post argues that in an environment where many AI-generated PRs fail to meet standards and even bug bounties suffer low confirmation rates, permissive push access is no longer viable.

#9 𝕏

Andrej Karpathy endorses @vivek_2332’s autoresearch-rl framework for autonomous RL hyperparameter tuning, noting that any multi-knob process with objective criteria can achieve substantial productivity gains.

#10 𝕏

Boris Cherny explains that “Ultrathink” in Claude delivers maximum effort for a single turn, while “/effort max” (or `claude --effort=max`) sustains peak effort for the entire conversation.

#11 📝 Simon Willison

My fireside chat about agentic engineering at the Pragmatic Summit - Simon participated in a fireside chat at the Pragmatic Summit in San Francisco discussing Agentic Engineering, hosted by Eric Lui from Statsig. A recording (YouTube thumbnail) and a long write-up (3,340 words) accompany the post describing the session and related topics.

#12 in

Peter Yang shows how Ramp’s 25 PMs shipped 500+ features last year by using Claude Code’s three-phase workflow—framing the problem with targeted Q&A, launching 6–10 parallel research agents, and iteratively shaping a concise 2-minute spec.