DAILY NEWS

Stay Ahead, Stay Informed – Every Day

Advertisement
hack with Hyd 2.0 – DEV Community



Support bots that forget every conversation aren’t support bots. They’re expensive FAQ pages.I built SupportMind to fix that — a customer support agent that actually remembers.The architecture is two layers:Memory (Hindsight): After every interaction, the agent stores structured context in a vector namespace per user. Next session, it recalls semantically — “payment problem” retrieves “Visa charge failing” even if the words don’t match.Routing (cascadeflow): Not every query needs GPT-4. Password resets go to Groq’s free tier. Complex billing disputes escalate. Every decision is logged with model, cost, latency, and reason.The delta that matters:Session 1: “Can you tell me your card details and the error you’re seeing?”Session 3 (same user, same issue): “I see you’ve had recurring issues with your Visa ending in 4242. Last time, clearing billing cache fixed it — want to try that first?”Same infrastructure. Completely different agent.On a typical support workload: ~80% simple queries handled by the cheap model. Cost per query dropped from ~$0.012 to ~$0.002.The part I didn’t expect: routing and memory compound. When Hindsight shows a user has had the same issue four times, cascadeflow automatically classifies their next message as complex — even without explicit signals. That fell out of the architecture. 👇https://lnkd.in/gn8NwP6Z

hashtag#AIAgents hashtag#AgentMemory hashtag#Hindsight hashtag#cascadeflow hashtag#LLM hashtag#AI



Source link

I’m a high-school student and I built a free app to stop forgetting everything over the summer



Hey everyone,

The school year is almost over, and every summer I hit the same problem: by September I’ve forgotten most of what I learned. It happens with everything. I feel confident with math formulas while I’m using them, but after a few months away they look like I’ve never seen them. Same with languages — my English and German feel solid at the end of the year or after finishing a book, and a few weeks later my vocabulary and grammar have basically evaporated.

So I built a small app to fight that, called Revise: https://revise-o1t7.onrender.com/

The idea is simple: give yourself regular practice on the things you’ve actually studied, so they stick. You can practise math, history, languages, chemistry and biology — it generates exercises, reading texts (which you can translate word-by-word right in the app) and flashcards, all on a spaced-repetition schedule so things come back just as you’re about to forget them.

It works with whatever AI you already use: you copy a generated prompt into ChatGPT, Claude or Gemini (the free versions are fine), and paste the reply back. No API key, no subscription. It’s free, and you can install it to your phone from the menu.

I’ve been using it for a while and it’s genuinely helped me remember things, not just learn them once. I’d love your feedback — what’s confusing, what’s missing, what you’d want next (there’s a feedback button in your account settings).

Thanks for reading, and I hope it helps someone! 🙂



Source link

I scraped Chrome Web Store reviews to find abandoned extensions that still have 100k+ users



I’ve shipped 4 Chrome extensions and 2 VS Code extensions. The advice that always sounds smart — “find a popular extension the dev abandoned, rebuild it better” — is miserable in practice. You open the Web Store, see 100k users and a 4.4 rating, think you found gold, then burn a weekend reading reviews only to realize half the complaints are unfixable traps (sync died, login broke, backend gone).

So I built a small pipeline to do the boring part automatically.

The method

Scrape public Chrome Web Store metadata — users, rating, last-updated date.
Filter: 20k–300k users, 18+ months without an update, rating 3.3–4.4 (good enough to prove demand, bad enough to prove pain).
Pull up to 50 recent reviews per candidate via public CWS data.
Score each one:
score = log10(users)10 + months_stale0.5 + feature_request_count2 – trap_count1.5
The key part is trap_count — I subtract points for complaints about sync/login/server issues, because those are unfixable without inheriting someone else’s dead backend. High “demand” with high trap count is a mirage.

One example

Extension Manager — 100k users, 4.4★, last updated ~25 months ago. Looks healthy until you read the 1–2★ reviews:

“The site-specific rules feature simply does not work… the core feature advertised is broken.”
“It won’t save any changes made… extensions are re-enabled automatically.”
A user even posted an RCE report: the dev parses JSON with a Function(str)() fallback — executing arbitrary code from untrusted input.

That’s not “build a clone.” That’s “fix the rules engine, kill the eval, add local backup, ship something 100k people already want.”

The counterintuitive part

The highest-scoring extension in my list (200k users, abandoned ~4 years) is actually the worst business opportunity — it’s a simple toggle utility whose users will never pay, and the original asks for camera/mic permissions (adware-grade). Raw download counts would put it at the top of your build list. Revenue potential buries it.

That gap between “looks like an opportunity” and “is actually monetizable” is the whole reason I started scoring monetization separately.

What I did with it

I analyzed 30 of these — 14 deep-dives and 16 honest “avoid this” verdicts — with demand, the gap, build difficulty, monetization reality, and why nobody rebuilt it yet. Packaged it with the raw CSV here if it’s useful to anyone: https://tuanspark85.gumroad.com/l/wnnxyq (there’s a free Top-3 preview too).

Happy to answer questions about the scraping pipeline in the comments — what tripped me up was the CWS review endpoint and pagination.



Source link