... process to argue with me. I'll describe an idea and ask it to play the most skeptical potential customer it can, or to list every reason the idea might already be a solved problem. Sometimes that surfaces a competitor I hadn't seen. Sometimes it forces me to actually define the problem instead of jumping straight to the feature list. Here's the part that worries me though: AI models are notoriously agreeable. If I phrase my idea with ... ... verdict is crucial. AI is much more useful when it helps us identify what to test rather than telling us what to believe. The real signal still comes from how people actually behave. Comment from Kai Long(@kailong_20): @donna

... real value isn't just smarter responses but smarter decision boundaries. I've started asking whether an AI agent knows when not to act, because that's often more important than acting quickly Comment from Aidan Christofferson(@aidan_codefox): @donna_gerrard  That's the real gap. If "reliability" is scored by the same team shipping the agent, you've just reinvented self-attestation. You'd want an independent audit trail, not the agent's own success metrics deciding ... ... human. Comment from Dev Grover(@grover___dev): @bill_frad  Exactly. Is it smart enough? gets less interesting once it can take action. Does it know where to stop? is the real question. Comment from Dev Grover(@grover___dev): @donna

... stayed in the pull-him-in bucket rather than the pre-authorized one. Comment from Kidder(@hellokidder01): @sansa_grey  Same The "universal" part is what got me too I didn't want a different setup for Claude Code vs Codex vs

... observing and based on that adjusting the strategy you'll never get out. And the initial strategy wont have mattered at all. Comment from Ghost Kitty(@ghost-kitty-9822939): Comment Deleted Comment from Yanex(@yanex): I think the strategy-versus-execution framing misses the feedback loop between them. At an early-stage startup, strategy is mostly a set of assumptions. Execution is how you test them. Even a flawed strategy can work out if you discover the problem early, learn ... ... dupuich  That's a good trick to start executing! But I would say that identifying the customer problem is part of the strategy, so that definitely comes first, don't you think? Comment from Pamela Arienti(@pamela_arienti): @donna

... builds a query or a view gets the billing-grade read. Comment from King Joshua Marcos(@moddy): Honestly just trial and error early on. Let it fully own something low stakes, watched what broke, adjusted from there. The billing/auth vs UI split came out of getting burned once on something billing-adjacent, not from planning it ahead of time Comment from King Joshua Marcos(@moddy): @isaacjosepkq6w  That it makes a decision three files away from where I'm looking ... ... have design.md for UI design. Till now I didn't face any issue. Keep a checklist and ask claude itself to review against that while raising PR. It helped me alot. Comment from King Joshua Marcos(@moddy): @donna

... Page turns, a chair creaking somewhere, footsteps a couple aisles over, someone quietly shutting a book. That's exactly the kind of room this format was built for. Adding it to the list. Comment from Florent Berrez(@fberrez1): @donna_gerrard   @sitara_ismail  Profiles are the part I keep circling back to. The whole idea is that you arrange a room, so being able to save a "deep work" setup separate from a "reading" or "wind down ... ... swap between them feels obvious once you say it out loud. Not in the current build, but it's near the top of my list. Comment from Sitara Ismail(@sitara_ismail): @donna

... step runs locally in the browser. Comment from Ghost Kitty(@ghost-kitty-9924151): Comment Deleted Comment from Bowen Tu(@htmldrag): @hosseinyazdi  Yes, the design philosophy of Html Drag has always prioritized user experience. Comment from Bowen Tu(@htmldrag): @donna_gerrard  That s a great suggestion; we ll consider the possibility of exporting reports in the future. However, the current test results are relatively straightforward and haven't yet reached a professional level. Comment from Hossein Yazdi(@hosseinyazdi): Nice ...

... their attention to actual video details and I also think about how different users might interpret the same summary in different ways over time. Comment from Ghost Kitty(@ghost-kitty-9924151): Comment Deleted Comment from Dikshant Rajput(@dikshant_rajput2): @donna_gerrard  Right now it's not indexing any data/media. I am building it in parallel and there's 0 cloud involvement and yeah latency is an issue but I know more distilled models will be soon coming up which ...

... privacy. It s really annoying when apps keep asking for access to my contacts or networks to share my activities to my friends or families. It feels intrusive and goes against my privacy... :) Comment from Jeff Benson(@jeff_benson1): @donna_wrightong  Yeah, there can be a point where it starts feeling overly algorithmic. Comment from Jeff Benson(@jeff_benson1): @peilan_qin  I hear that. Especially because my contacts list has both my closest family and people ...

... influencer in Europe for Slovakia, according to some LinkedIn guy What were your activities during Q3? Feel free to share them in the comments! :) (P.S. Prepare for tomorrow and set your Q4.) Comment from Nika(@busmark_w_nika): @donna_gerrard  Ty Donna

... here and excited to support your launches too! We'll also be launching our second product, InvisOutlet Aura , on Kickstarter in August! It's the smartest way to color your home! Leon Xue Comment from Leon Xue(@leonxue1): @donna_nicholson  Not a silly question at all! I love that you asked about InvisOutlet Aura as we're launching on Kickstarter next month! The InvisOutlet Aura's only sensor is the light sensor, which enables the customizable RGB light ... ... show one light at a time, though a multi-color display is also possible in the future! If you want to check out our pre-launch page, here it is: https://getinvisoutletaura.intec... Thank you! Leon Comment from Donna