Show notes
Today’s EpisodeWhy do your prompts keep failing?You write the perfect prompt. The AI spits out garbage. You tweak. You iterate. You spend hours getting mediocre results.XK built Cues to $10M ARR in 60 days with zero VC funding and zero advertising. Today, he’s dropping the complete playbook:-----Check out the conversation on Apple, Spotify and YouTube.Brought to you by:Reforge http://reforge.com/aakash-----Key takeaways:1. Context engineering beats prompting - One prompt won't work. Like hiring someone who knows nothing about your company—impossible to get results in 5 seconds. Accumulate context, build knowledge base, let AI know you over time. Combines system prompts, user prompts, memory, and RAG.2. The Mom analogy - Your mom knows your preferences, goals (grow taller for basketball), what makes you happy. She doesn't need detailed instructions. That's context engineering. AI that knows you creates better results and positive loops.3. Threads growth hack - Created hundreds of accounts posting use cases daily. Zero ad spend. Why it works: Threads gives traffic generously, less crowded than X, no creator hierarchy. Result: 3M impressions/month, hundreds of daily visits. Targeted Taiwan/Hong Kong markets.4. MVO before MVP - Traditional: Feature → PRD → Design → Ship. Xiankun's way: Get model output right FIRST. Use RAG, prompting, fine-tuning for Minimal Viable Output. Then productize. "If no desired outputs, don't spend time productizing."5. Visual context engineering - Use spatial tools: draw squares, graphs, sketches. AI understands spatial relationships. Unlike ChatGPT where files disappear, Kuse gives 2D space to store/reuse. Graphic operating system for AI that compounds.6. The pivot story - Started as design agent. Users uploaded documents instead. Knowledge base usage far exceeded design. Pivoted to horizontal knowledge-based AI. Listen to your users.7. Why X sucks for growth - Structured creator hierarchy. Can't farm traffic without famous connections. Good for VC fundraising, terrible for user acquisition. Threads and Instagram are underserved with real users.8. Compounding context power - Regular chatbots: one-off, context disappears. Kuse: processes files when you're away, pre-prepares everything. Like having ingredients ready vs ordering each time. Each interaction improves.9. Trading company origin - Co-founded YC company, created trading company, made money, funded Kuse with profits. Built without VC pressure. "Entrepreneurship is a game of focus." Building without chasing VC gives fresh perspective.10. Future vision: productivity playground - "Not building productivity tool, building playground." When AI takes jobs (2030-2040), people need fulfillment. Kuse is amusement park where people pretend to work, feel satisfaction. Going to pure pleasure, not efficiency.----Where to Find Xiankun Wu* LinkedIn* Threads* Company----Related ContentPodcasts:* We Built an AI Employee in 62 mins* Conversation with the CEO and Founder of Bolt* This $20M AI Founder Is Challenging Elon and Sam Altman | Roy Lee, CluelyNewsletters:* Context Engineering Guide* Prompt Engineering in 2025* How to become an AI Product Manager----PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!----If you want to advertise, email productgrowthppp at gmail. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe