React Native on iOS doesn't support ReadableStream. When users switch apps mid-response, the AI keeps generating to nothing. This dev solved it by making the server keep going after disconnect and persist the full response to the DB. { author: @juandastic } dev.to/juandastic/i-built-a-…

12 years building web apps. Zero mobile experience. Last month I needed an iOS app for my side project so I just built one. Took 3 days. The real unlock was not React Native or Expo. It was having AI in the workflow. It did not write the app for me but it removed the friction of learning a new platform. I moved at the same speed I move on the web. Then iOS broke everything. Turns out when your user switches to WhatsApp mid-response, iOS kills your network request. The AI keeps generating server-side, burning tokens, but the response never arrives. Had to rethink the whole streaming architecture to handle disconnects gracefully. Full writeup: dev.to/juandastic/i-built-a-…

Building AI side projects is fun until you have to pay for it I built Synapse, an AI companion for my wife with a memory system that makes Gemini know her life, her patterns, her emotional triggers. She uses it daily. Two weeks ago, I connected PostHog to track costs. $24. One session alone: 28 messages, $2.42. Every message sends ~30K tokens of context. 80-90% of those tokens are the exact same compiled knowledge, repeated every turn. Most AI providers offer automatic caching. Send the same prefix enough times, and they might cache it for you. But you have no control. One small change in the prompt (like a datetime updating every turn) breaks prefix matching. You never know if it is working. 𝗚𝗲𝗺𝗶𝗻𝗶'𝘀 𝗲𝘅𝗽𝗹𝗶𝗰𝗶𝘁 𝗰𝗮𝗰𝗵𝗶𝗻𝗴 𝗔𝗣𝗜 𝗶𝘀 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁. You create a cache resource, get a name back, and reference it on every request. Guaranteed hit. 75% cheaper on cached tokens. You decide what gets cached and you can verify it is working. I separated the stable knowledge compilation (~25K tokens) from the volatile parts of the prompt, cached the compilation after hydration, and referenced it by name on every message. The client sends both the cache_name and the full compilation on every request. If the cache is hot: 75% savings. If it expired, the server inlines the compilation at full price. The user never notices. 𝗧𝗵𝗲 𝗻𝘂𝗺𝗯𝗲𝗿𝘀 Before: $0.017-0.039 per generation After: $0.0088 per generation That $2.42 session? Would cost ~$0.25 now. Same knowledge graph. Same memory quality. Just a lot cheaper to remember. Full breakdown: dev.to/juandastic/my-ai-send…

I built a bidirectional sync between a Neo4j Knowledge Graph and Notion for the @ThePracticalDev Challenge with @NotionHQ AI memory is usually a black box. Now, it's a fully editable, dynamically generated Notion workspace. Here is the architecture dev.to/juandastic/full-circl…

Context windows are expensive resources. This dev demonstrates how to tame a 120k token prompt by implementing a deterministic GraphRAG approach for more efficient memory scaling. { author: @juandastic } dev.to/juandastic/scaling-ai…

Congrats to our top 7 authors this week! 🏆 @dannwaneri, @madsstoumann, Julien Avezou, Peter Mulligan, Prithwish Nath, Vivek V, and @juandastic. This week's lineup features a CSS recreation of a Pantone color deck, a self-hosted Google Trends alternative using DuckDB, and much more. dev.to/devteam/top-7-feature…

Hey @bennettschwartz, I just saw your project on a @theo stream. I am also interested in the same problem. I experimented with Graphs, aiming to solve the same deep memory problem. I posted something about it in case you are interested. I will definitely go check Membrane to know more

Vectors are great for search, but graphs capture relationships. Building an AI companion with "Deep Memory" that uses Knowledge Graphs (plus vectors) so the system can recall structured personal context and causality, not just match keywords. { author: @juandastic } dev.to/juandastic/beyond-rag…