Romy Abbrederis

Agentic AI isn’t just changing travel - it’s challenging the legacy systems behind it. As Vivek Bhogaraju explains, the shift is toward AI agents that can execute tasks, not just generate responses. 📰 Read more: hubs.li/Q04fY36p0

Every customer call is useful. Every customer visit changes the product. You learn more in one hour in their office than in ten hours on Zoom.

Bureaucratic systems exist to make average performance acceptable. High performers don’t need approval chains. They need ownership.

Everyone says build an MVP. Almost nobody says implement as an MVP. Big bang rollouts die in friction. Pick the smallest slice, get one fast win with the customer, expand from there.

🚨 CLAUDE CODE BUILDERS 🚨 THIS is the ultimate resource bible for Claude Code: ↓ 🧵

Software is not a moat. Whatever you build, three other founders are building the same thing this week. AI compressed that timeline. The moat is whoever reaches the customer first and stays there.

If you have ADHD and you are a founder, the hardest advice you will hear is: focus on one thing. The anxiety isn’t about the work. It’s the fear that if you don’t do it all now, you never will. The fastest path to everything is one thing at a time.

Choosing your beachhead is the decision founders procrastinate the most. It feels like closing doors. It’s not. A beachhead doesn’t define your future, it shapes your next six months. Founders confuse “first” with “only.” They’re not the same thing.

A chain we want to sell to is already doing what we built, manually. They hired people for it. First reaction: oh no. Second reaction: best validation I’ve gotten all year. Nobody pays humans to do tedious work unless the problem is real.

100 Claude Repos that will completely change your life: (save this) 1. Terminal AI coding agent github.com/anthropics/cla… 2. Ready-to-use starter apps github.com/anthropics/cla… 3. Official agent skills github.com/anthropics/ski… 4. Plugin marketplace github.com/anthropics/cla… 5. Full ecosystem github.com/orgs/anthropic… 6. Master list github.com/hesreallyhim/a… 7. 1000+ plugins github.com/quemsah/awesom… 8. Huge skills library github.com/sickn33/antigr… 9. Curated skills github.com/VoltAgent/awes… 10. Cross-platform skills github.com/alirezarezvani… 11. LLM pipelines github.com/langchain-ai/l… 12. Agent workflows github.com/langchain-ai/l… 13. Multi-agent systems github.com/microsoft/auto… 14. Team-based agents github.com/crewAIInc/crew… 15. AI dev team github.com/metaGPT/metaGPT 16. Code agents github.com/gpt-engineer-o… 17. Auto PR fixes github.com/sweepai/sweep 18. AI coding assistant github.com/continue-repl/… 19. Code search github.com/BloopAI/bloop 20. Agent standards github.com/agentprotocol/… 21. Productivity plugins github.com/anthropics/kno… 22. AI SDK github.com/vercel/ai 23. Memory layer github.com/upstash/contex… 24. Voice agents github.com/fixie-ai/ultra… 25. Deploy agents github.com/superagent-ai/… 26. Web agents github.com/xlang-ai/OpenA… 27. Reasoning agents github.com/ysymyth/ReAct 28. Long-term memory github.com/mem0ai/mem0 29. AI apps infra github.com/helixml/helix 30. API layer github.com/trpc/trpc 31. Clean UI github.com/ChatGPTNextWeb… 32. Self-hosted UI github.com/open-webui/ope… 33. Modern UI github.com/mckaywrigley/c… 34. Desktop app github.com/lencx/ChatGPT 35. Next.js clone github.com/Nutlope/chatGP… 36. Template github.com/vercel-labs/ai… 37. Claude-ready UI github.com/Yidadaa/ChatGP… 38. Minimal UI github.com/ivanfioravanti… 39. Lightweight UI github.com/louislam/ChatG… 40. Adaptable UI github.com/zk-ml/chatglm-… 👇

“Your DMs with your co-founders are fragmenting the team.” I never noticed once. For months. Especially when you’re remote, there’s no hallway, no overheard call. If it’s not in the channel, it didn’t happen for everyone else. Smallest habit, biggest drift.

I just built this for my grandma. Meet Sam, the first AI caretaker for seniors. Order one of the first 1,000 units (see below).

If you want to be a successful entrepreneur: You have to literally learn to enjoy getting punched in the face. It’s not normal. It’s masochistic. But the journey will be too brutal if you don’t thrive off it.

A Google DeepMind researcher cornered me at a bar in Hayes Valley I was showing my Polymarket PNL to a friend. She leaned over. Didn't introduce herself. "That's not a trading app. Show me your stack" I told her. Claude Code. Four repos. $25 a month. She set down her drink. "We tested this internally. You connect Claude directly to a dataset. It builds its own detectors. But nobody ships it because compliance kills everything" I asked what she meant. She took my phone. Opened one link. github.com/warproxxx/poly… 86 million trades. Every wallet. Every entry. Every exit. "You don't tell Claude what to look for. It finds the wallets that win. Then it finds WHY they win. Then it copies the pattern" Her team spent 9 months building this for a hedge fund. 14 people. $2M budget. "The part that took us the longest - exit logic. Everyone thinks entries matter. They don't. Exits are the entire game" I told her my bot cuts at 85% of expected move or on a 3x volume spike. She went quiet. "Who taught you that" Claude Code found it in poly_data. Top wallets exit before resolution 91% of the time. They capture the move and leave. She opened another link. github.com/Polymarket/pol… "This is the scanner. Three commands. 500+ markets. No API key. Claude scores them in 20 minutes" "That's our exact infra. Except it took us 9 months and you did it in a weekend" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 19 days. 4 agents. 74% win rate. Copytrade here: @lunar" target="_blank" rel="nofollow noopener">kreo.app/@lunar I showed her the article where I broke down every repo, every command, every dollar. She read it for five minutes. Then: "You just open-sourced our entire pipeline" She texted me the next day. "My team lead saw your thread. Take it down" Too late.

one of the best sales advice we picked up during YC is the "McKinsey Model" a lot of deals at early-stage startups die for the same reason: your champion is afraid to advocate for your product if they push for it internally and it doesn't work out, their job is on the line so they never come back to you and hit you with the "we need to align internally first" that's why you need to be their McKinsey consultant: instead of them pitching, you personally take the blame after every demo, send them: - a one-pager - a security doc - an ROI calculator with their numbers - useful context/overview of your industry that can help with what they're struggling with right now - a pre-written slack message they can forward make it as easy as possible for your champion to forward your material without them feeling responsible for integrating your solution or "fighting" for it

I use a very specific prompt to push Claude to check its work and do a lot of testing and thinking about perf and refactoring. I find I can do big features (4K LOC+ with full testing) in about an hour.

“We used to review every line of code before it went into production”.

I'm going to #TechCrunchDisrupt2025! Get 15% off and join me and 10k tech leaders in SF! app.ingo.me/q/igexp

Stop reacting to feature requests from customers. Your job as a startup founder is to find out, WHY they wanted it and WHAT are they are trying to solve.