Skip to content
Aakash GuptaAakash Gupta

$10M ARR in 60 days with context engineering

Xiankun Wu built Kuse to $10M ARR in 60 days with zero VC funding and zero advertising. He reveals the context engineering framework that 99% of AI builders miss, the Threads growth hack (intern army + hundreds of accounts), and why MVO (Minimal Viable Output) beats MVP for AI products. Full Writeup: https://www.news.aakashg.com/p/xiankun-wu-podcast Transcript: https://www.aakashg.com/context-engineering-is-the-secret-how-kuse-hit-10m-arr-in-60-days-without-vc-funding/ ---- Timestamps: 0:00 - Intro 1:19 - Why Prompts Fail 5:23 - $10M ARR in 60 Days 7:23 - Hidden Story: Design Agent Pivot 9:07 - Threads Growth Strategy 11:28 - Ad Start 12:20 - Threads Accounts Demo 17:06 - Visual Context Engineering 20:10 - The Mom Analogy 22:12 - RAG vs Fine-Tuning vs Prompt Engineering 26:26 - MVO Before MVP 31:43 - Ad Start 32:48 - Demo: Creating PRD in Kuse 44:43 - Advice for AI Founders 56:12 - Outro ---- 🏆 Thanks to our sponsor: 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: https://www.linkedin.com/in/xiankunwu/?originalSubdomain=hk Threads: https://www.threads.com/@kusehq?hl=en Company: https://www.kuse.ai/ 👨‍💻 Where to find Aakash: Twitter: https://www.x.com/aakashg0 LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com #contextengineering #aipm #kuse #startupgrowth #productmanagement ---- 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 200K+ listeners. 🔔 Subscribe and turn on notifications to get more videos like this.

Aakash GuptahostXiankun Wuguest
Nov 21, 202557mWatch on YouTube ↗

CHAPTERS

  1. 0:00 – 1:19

    Why prompts fail: unrealistic expectations and missing context

    X.K. argues that the idea of a single “perfect prompt” is a myth because the model doesn’t know your goals, constraints, or progress. Prompt tweaking is often a symptom of insufficient context plus mismatched expectations about what AI can do from a short instruction.

  2. 1:19 – 5:23

    Context engineering as a product behavior: accumulate materials, compound results

    Rather than treating AI as a one-off chat tool, Kuse pushes users to build an evolving context base. Over time the system “knows you more,” reducing the need for complex prompts and improving outputs via a compounding loop.

  3. 5:23 – 7:23

    The real story behind “$10M ARR in 60 days”: long build-up before the spike

    X.K. clarifies that the headline compresses a much longer journey—Kuse was built quietly starting early 2024. The “60 days” reflects an inflection after sustained product development, community relationships, and groundwork.

  4. 7:23 – 9:07

    Pivot narrative: from design agent to horizontal knowledge/document AI

    Kuse began as a design agent, which explains the infinite canvas UI. Real usage showed people valued uploading and analyzing documents far more than generating designs, prompting a shift toward knowledge-work and document understanding.

  5. 9:07 – 11:28

    Threads growth playbook: underserved platform + geography + intern ‘content army’

    Kuse’s distribution edge came from going all-in on Threads—especially in Taiwan and Hong Kong—where it was growing fast but less crowded. They scaled content via many accounts run by interns, publishing daily use cases that drove awareness and demand.

  6. 11:28 – 12:20

    Threads accounts demo: what content formats worked and why

    X.K. shows examples of their many Threads accounts and the kind of posts that performed—practical, repeatable workflows and before/after transformations. They discuss market competition dynamics and why Threads had more “real users” than some assume.

  7. 12:20 – 17:06

    Visual context engineering: a marketing term for multi-modal intent expression

    X.K. frames “visual context engineering” as a shorthand to communicate their approach: using a 2D canvas to express intent and organize context. The canvas enables spatial relationships among documents, images, and outputs—making reuse and iteration easier than linear chat.

  8. 17:06 – 20:10

    The “mom cooking” analogy: context is personalized understanding + feedback loops

    To make context engineering intuitive, X.K. compares it to a mom who knows a child’s preferences and goals and cooks accordingly. The better the context, the better the output, reinforcing a positive loop of trust and usefulness.

  9. 20:10 – 22:12

    RAG vs fine-tuning vs prompt engineering—and Kuse’s async file processing twist

    They discuss common confusion between RAG, fine-tuning, and prompting, then outline Kuse’s approach. Kuse emphasizes RAG and robust document/OCR processing, with async pre-processing so files are ready before users query them.

  10. 22:12 – 26:26

    MVO before MVP: validate model outputs before productizing features

    X.K. introduces an internal product principle: build a Minimal Viable Output (MVO) before investing in a Minimal Viable Product (MVP). In AI products, if the model output isn’t reliable, shipping UI and workflows is wasted effort.

  11. 26:26 – 31:43

    Demo: creating a PRD in Kuse with minimal prompting but heavy context

    X.K. walks through Kuse’s workflow: drop files onto the canvas, select relevant materials, and ask for an artifact (like a PRD). The emphasis is on providing background docs, notes, and constraints so a simple prompt can produce strong results.

  12. 31:43 – 32:48

    Prototype generation and the ‘AI wrapper’ debate: usefulness over complexity

    They show generating a simple prototype via webpage generation, noting that the system summarizes context and hands it to a strong model (e.g., Claude). X.K. argues teams shouldn’t overcomplicate solutions just to avoid the “wrapper” label—users only care if it solves the problem.

  13. 32:48 – 44:43

    Founder guidance and philosophy: don’t fear model updates; follow users; think beyond productivity

    X.K. advises founders to avoid FOMO and loss aversion around rapid AI progress and instead stay close to users. He frames Kuse long-term as more than a productivity tool—potentially a “playground” that preserves meaning and satisfaction in a world where AI automates work.

  14. 44:43 – 56:12

    Bootstrapping and company structure: funding Kuse without VCs

    In response to learning context engineering, X.K. pivots to what he believes is more valuable: how they structured the company to stay focused. He explains they used profits from a trading business to fund Kuse, avoiding the distraction of fundraising cycles.

  15. 56:12 – 57:18

    Closing recap: context engineering as the core lever behind Kuse’s growth

    Aakash wraps by reinforcing the episode’s thesis: context, not clever prompts, drives reliable AI outputs and product value. He points viewers to additional resources (newsletter/podcast links) and ends with calls to subscribe and follow.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome