... pulls full document context instead of keyword matches. Reads across multiple policy sections to catch exclusions and limits. Redesigned perk tracker - Built for people with redundant benefits (2 Priority Pass memberships, overlapping coverage). Shows what you're actually using vs. paying for. Better card recommendations - Considers your actual insurance coverage, not just earn rates. Amex Green 3x vs

... adopt your agent, and where did you go wrong? Let's learn from each other's mistakes and build better, more resilient AI agents together. What's your story? Comment from Priyanka Gosai(@priyanka_gosai1): This hit home, Hansel. One of our early AI agent attempts was for auto-tagging support tickets. We assumed NLP + semantic matching would solve everything. But here s what went wrong: Misjudged User Needs: Users didn t want full automation. They wanted confidence suggestions ... ... assume automation is always the goal. Sometimes augmentation wins. And give users override + feedback loops from Day 1. Curious what kind of agents you re building now and how you're designing for trust this time around? Comment from Hansel

... think are absolutely nailing this new era of design? Would love to hear your examples and thoughts on what makes them effective. Excited to learn from this amazing community of builders, designers, and enthusiasts! Let's chat. Comment from Hansel(@hanselh): @azam_sultan  That seamless integration you described with Notion AI is spot on when the AI enhances the experience without being a distraction, it feels truly 'smarter.' Do you think this 'invisible AI' approach, where it just works ...

... limitations create significant unmet needs or inefficiencies. What other core human needs, or fundamental limitations in how things are currently done, can we identify that might be completely re-architected if AI capabilities were a foundational assumption? Comment from Hansel(@hanselh): @yeedoong88  So glad the 'first principles' thinking resonated. You've perfectly articulated the shift: AI not just as a task-doer, but a 'systems thinker.' Your experience with 'connecting the pieces' for non-coders is a prime example ... ... finding this particularly true in my work on AI for workplace well-being. Really appreciate you sharing that it prompted a pause on 'automating the known' that's a win for first-principle thinking right there! Comment from Hansel