TechBrief — تازه‌ترین اخبار فناوری

مرجع روزانه خلاصهٔ اخبار و تحلیل‌های کوتاه از منابع معتبر.

آخرین خبرها

The 1X Neo Robot Has Freaky Fast Fingers

The soft, weirdly sexualized home-chore robot has been given some very tactile hands.

Auditory and spontaneous movement responses to music over first postnatal year

Article URL: https://elifesciences.org/articles/107088

Comments URL: https://news.ycombinator.com/item?id=48848111

Points: 4

# Comments: 0

AI Content Is Everywhere on Social Media, Especially LinkedIn

Article URL: https://www.pangram.com/blog/ai-in-your-feed

Comments URL: https://news.ycombinator.com/item?id=48847940

Points: 50

# Comments: 24

Schlage’s Sense Pro unlocks the door so I don’t have to

The Schlage Sense Pro is a beautiful smart lock. Sleek, discreet, and simple to use, it's Schlage's smartest lock to date. Thanks to ultra-wideband (UWB), it unlocks as I walk up to my front door; I don't need to enter a code or tap my phone or press my finger against it. I've tested several […]

Show HN: Reverse-engineering web apps into agent tools

Hey HN! We built a browser-based agent that runs inside an authenticated web app, watches how the app calls its own APIs, and automatically turns those into agent tools. You can think of it as an auto-generated MCP server that self-updates as the host app changes.

The result is a skilled AI assistant that actually integrates deeply with any product (not just chat and RAG) with minimal effort.

Check out these short demos below that show the agent in software you're probably familiar with:

- Jira: https://demo.frigade.com/hn?skill=jira

- Spotify: https://demo.frigade.com/hn?skill=spotify

- Hacker News (lol): https://demo.frigade.com/hn?skill=hackernews

- Full Demo: https://demo.frigade.com/hn?skill=full-demo

As you can see in the examples, you can do way more (and faster) than what you normally would be able to via point and click. And we never even touched the source code of these products!

Why do this?

In an ideal world, every application has an MCP server or an easily-digestible API available for AI agents to feed from. In practice, we found that even very modern software tends to have a spider web of confusing APIs and services that AI agents simply cannot use out of the box. Security also becomes a huge issue as applications have different (often homebrewed) standards for how endpoints are secured (JWTs/cookies/mix of both). Finally, having an actual browser agent go in and use the application on behalf of the user (i.e. computer-use), is simply too brittle, slow, and burns a lot of tokens.

We took our existing browser agent that’s already trained to use and learn authenticated applications, and added an extra step that automatically turns the app’s authenticated APIs into "recipes". A recipe is a mix of the following:

- API endpoint + method

- Authentication method (and how to retrieve refresh auth tokens/cookies)

- Response schema

- Input schema (for POST/PUT)

- Human readable description of what the tool does

Putting it all together, these become reusable tools for LLMs, all without writing or maintaining any code. Even if the APIs change our agent figures this out and replaces the recipe for the tool with the updated version.

Adding tools to an AI agent becomes super simple this way:

- Our agent trains on the app and builds the recipes

- The app owner enables discovered tools from our dashboard

- The agent can now take actions on the user’s behalf directly inside the application. For instance, saying something like "invite my teammate to my workspace" would securely call the existing API endpoint for inviting users without proxying or relaying through a third party.

Of course, there's a ton of edge cases you run into when you try to do this - every application is intrinsically different despite how many "standards" exist. Fun fact: graphql was by far the worst API to work with in standardizing the recipes.

Looking forward to your feedback/comments!

Comments URL: https://news.ycombinator.com/item?id=48847834

Points: 6

# Comments: 0

Launch HN: Context.dev (YC S26) – API to get structured data from any website

Hi Hacker News, I’m Yahia. I built Context.dev (https://www.context.dev/) to make it really easy to integrate web data into your products and agents.

Here’s a demo video: https://www.tella.tv/video/build-faster-with-context-dev-api...

Since it’s an API, here are the docs: https://docs.context.dev/quickstart.

You can send us a URL and get back clean Markdown, rendered HTML, screenshots, extracted images, etc.. You can also send us a domain and get company or brand context: name, description, logos, colors, fonts, social links, screenshots, style information, and related metadata. For more custom use cases, you can send a URL plus a JSON Schema and ask us to extract structured data from the site into that shape. For example, you might ask for pricing plans, product categories, office locations, support links, integration partners, or anything else that is visible on the public site.

The goal is to give developers the output they actually want. Raw HTML is rarely the useful thing; the useful thing is usually Markdown for a model, JSON for an application, a logo for a UI, or a structured company profile for an agent.

Before, I worked at Amazon and Sunrun, and co-founded StockAlarm.io & essense.io, both of which were acquired. Also, I built knifegeek.io, which scraped pocket knives from across the internet and listed them easily. The project is outdated now (coming back soon) but back then it hit the frontpage of hacker news and people seemed to like it: https://news.ycombinator.com/item?id=34604281.

Just before Context.dev, I built Brand.dev. The idea was that your software product should automatically know about your customer if they sign up with a corporate email. The API pulled brand data such as logos, backdrops, name, description, industry, and more from the public web and surfaced it to your product to integrate as part of their onboarding experience. That’s worth doing because conversion rates on onboarding improve dramatically when you go from “enter all this info” to “confirm all this info” (and there was never any privacy concern all the information is public).

That was a nifty niche, but the more customers used it, it became obvious that “brand data” was only one slice of a larger need. People started asking for things like screenshots, structured extraction, and LLM ready data. So I expanded to Context.dev, and applied to YC (got rejected after an interview), then kept going and re-applied at which point I got in as a solo founder.

People use Context.dev in more ways than I can list, but here are some: keeping context up to date on customer websites for chatbots - building beautiful brand assets/ads for customers - enrichment flows using agent harnesses like eve.dev - crawling customer websites into chatbot knowledge bases - turning GitHub repos into branded docs sites - academic journal and PDF crawling. There are a ton more examples at https://www.context.dev/customers.

We know that many crawlers are not behaving like good citizens on the web, and the entire space has a bad reputation as a result. At the same time, customers are not usually trying to buy “scraping”. They are trying to make a support bot work, personalize onboarding, enrich CRM records, generate docs, monitor leads, or let an agent research a company. There are lots of legit use cases. We want to satisfy those while being respectful of everyone involved.

We maintain a caching layer and avoid hammering websites. Customers can configure the cache, but if we find we’re sending too many requests to a url in a certain amount of time, we step in and tone it down. Websites can opt out of our service, and we respect these requests and add them to our block list.

We focus on customers who want to build cool things for their users. Enriching onboarding is a popular use case. So is integrating context about their own websites (things like support bots), and building agents that can automatically reason about complex tasks involving the internet.

We only allow customers to use brand data to identify a specific customer on their software, you cannot use it in your own materials or to imply endorsement.

I'd love to hear your feedback about the product in the comments, thanks!

Comments URL: https://news.ycombinator.com/item?id=48847562

Points: 20

# Comments: 19