I d love to learn from your experiences in building an app that leverages AI to improve user experience. For the context, conversation-based is popular for generative AI but sometimes it is not easy to set up within a product that does more than just information generation.
My wife and I built AdPipe because writing Facebook and Instagram ad copy was always the most painful part of running Meta ads. Staring at a blank page, writing one variant, wondering if it's good enough, then repeating 11 more times.
6 Months of beating myself over the UI/UX I am finally shipping Densops. From my biased side of the fence; it is the easiest BULK local discovery / list builder tool available.
We re letting users take over Votap One thing that s been really cool lately? The emails. People telling us what they like. What they d change. Which politicians we should add next. I answer as many as I can, but it made me realize something: If Votap is about public opinion then the app itself should be shaped by public opinion too. So in the next update (coming very soon), we re adding a proper feedback space directly inside the app. You ll be able to: Suggest features Request politicians Comment on ideas Upvote what you want to see next Other users can vote on suggestions too so we build what people actually care about. Votap is a people platform first. So the product should evolve with the people using it. We want this live before our next bigger user acquisition push (aiming much higher next time ). If you want to help shape it, download Votap from the App Store. More tomorrow.
I built an MCP server that connects coding agents (Claude Code, Cursor, OpenCode, Codex) to a collaborative workspace where your team and other AI models can review what the agent is planning.
The problem: When Claude Code creates an implementation plan, it lives in your terminal session. Nobody else sees it until it becomes a PR. If you want GPT to check the architecture or a teammate to flag issues, you're copy-pasting between windows.
This MCP server fixes that. When your agent creates a plan, it gets shared as a collaborative thread in CoChat. Engineers comment on it, other AI models review it, and you pull all the feedback back into your agent's context with one command. Decisions can be saved as project memories that persist across sessions and are searchable by anyone.
What it does: Plans: Auto-shared as collaborative threads. Pull feedback back into your terminal. Cross-model review: Have GPT review your Claude plan, or vice versa. Project memories: Semantic memory that persists across sessions, models, and people. Ask: Query your project's knowledge base from the terminal. Auto-scoping: Detects your project from git remote. No config needed. Setup is one command per agent. Auto-share behavior is configurable (off/plan/all).
I ve been in a long-term relationship for years. As life gets busier, we realised how much our date nights mean to us, but the small details can fade and get buried in photo reels.
My partner started a separate Signal chat just for us to send a short memory after each date night, with a note about what we did and maybe a photo. It felt simple but surprisingly meaningful.
So for Valentine s, I built a simple web app that does exactly that: a shared timeline for couples to log date nights in seconds.
No social feed. No public sharing. Just your shared history.
I ve seen too many projects get delayed because "rough sketches" weren't clear enough for the team. Whether you re setting a small house or big bunglow,precision matters. I built a tool that takes the friction out of planning. 1.Input your dimensions.
2.Get a clean, professional 2D layout instantly.
3.Share it with your team. No CAD experience required. No expensive software. Just dimensions to designs. Just need a genuine feedback. https://aakar.in.net/
