People struggle with AI prompts because the model lacks background on their goals and progress. The solution is 'Context Engineering': creating an environment where the AI continuously accumulates user-specific information, materials, and intent, reducing the need for constant prompt tweaking.
Adopting the philosophy of 'building for dying' (向死而生), the founder views his AI product not just for current productivity, but as a future 'playground.' In a world where AI automates most jobs, the product's purpose will shift to providing fulfillment and the pleasure of 'pretend work.'
Cues achieved rapid growth by targeting overlooked markets (Taiwan, Hong Kong) on an underutilized social platform, Threads. They created hundreds of accounts managed by an 'intern army' to post use cases daily, exploiting the platform's generous organic reach before it became saturated or monetized.
Cues uses 'Visual Context Engineering' to let users communicate intent without complex text prompts. By using a 2D canvas for sketches, graphs, and spatial arrangements of objects, users can express relationships and structure visually, which the AI interprets for more precise outputs.
Cues' initial product was a specialized AI design agent. However, they observed that users were more frequently uploading files to use it as a knowledge base. Recognizing this emergent behavior, they pivoted to a more horizontal product, which was key to their rapid growth and product-market fit.
To maintain product focus and avoid the 'raising money game,' the founders of Cues established a separate trading company. They used the profits from this successful venture to self-fund their AI startup, enabling them to build patiently without being beholden to VC timelines or expectations.
For AI products, the quality of the model's response is paramount. Before building a full feature (MVP), first validate that you can achieve a 'Minimum Viable Output' (MVO). If the core AI output isn't reliable and desirable, don't waste time productizing the feature around it.