MCP-инструменты научились возвращать интерфейс: разбираем OpenSearch MCP Apps
Обычный MCP-инструмент возвращает агенту текст или структурированные данные. Агент анализирует результат и пишет тебе что-то вроде: Глубже
Последние новости
⚑ Сообщить о проблемеTech news from the best sources
Все темы
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Instinct raised $350M. The moat is your app permissions
Instinct , the AI startup that lets you text and call an assistant wired into your own apps, has raised $350 million at a $2.5 billion valuation. Te…
A silent failure looks exactly like a feature you never built
Your system has memory. Your user is typing into someone else's chat box. That gap is the whole problem, and it is not a retrieval problem. The plac…
I Treated Agent Sessions as Portable Cache and Moved Control to a Policy Plane: Vendor Lock-In Became Manageable
I wanted to know whether portable coding-agent sessions materially reduce vendor lock-in, or merely make a future migration look easier than it is.…
What Bedrock AgentCore Actually Puts on Your A2A Agent Card
This article provides a step by step look at the A2A agent card a Strands agent publishes on Amazon Bedrock AgentCore Runtime, and how it compares f…
From Static RPA to Dynamic AI Agents: Hyper-Automating Enterprise Operations for 40% ROI
Introduction & Industry Context The pursuit of operational efficiency has long been a cornerstone of enterprise strategy. For decades, Robotic P…
How to Calculate ROI on an AI Agent Before You Build It
Calculate ROI by comparing what the manual process actually costs today (fully-loaded labor, error correction, missed volume) against the one-time b…
EventBridge Pipes for AI Agents: Building a Self‑Contained Plan‑Act‑Observe Loop in Node.js
Imagine an AI agent that can plan, act, and observe without a single Lambda function acting as glue. EventBridge Pipes let you stitch together LLM c…
Mix and Match: One Agent, Three Clouds, One Protocol
This article provides a step by step comparison of the same research agent built three times, on Google ADK, AWS Strands and Microsoft Agent Framewo…
Mix and Match: Serving an ADK Agent to AWS and Azure
This article provides a step by step look at running a Google ADK agent on Cloud Run, and serving it over the A2A protocol to callers that are not A…
From Demo to Production: The Guardrails That Make an AI Agent Safe to Ship
From Demo to Production: The Guardrails That Make an AI Agent Safe to Ship Hook: Most "AI agents" you see on the internet are demos. Here's the sing…
Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks
This article was originally published on BuildZn . Everyone's running local LLMs now, which is great. But then they hit the wall: "Why does my 7B mo…
TrueForge: открытая обвязка, которая превращает LLM в полноценного агента
Собрать демо-агента сегодня несложно. Подключаешь модель, добавляешь пару инструментов — и она уже читает файлы, вызывает API и бодро обещает выполн…
DeepSeek Harness Puts Its Breaking-Changes Warning Before the Install Steps
The loudest sentence in the DeepSeek Harness README is set in all caps: "THERE WILL BE COMPATIBILITY-BREAKING CHANGES." That is not a footnote burie…
I Let an AI Agent Run a SaaS Like a Solo Founder. It Made the Same Mistakes Humans Make.
I expected the audit to find broken code. That's what I was bracing for going in — a pile of half-working features, sloppy logic, the kind of mess y…
Your compiled DSPy program re-sends up to 20 few-shot demos on every single call
DSPy's pitch is that you stop hand-writing prompts and let an optimizer compile them for you. You write a program out of modules, hand it a metric a…
Cumora Makes Agent Coordination the Product, Not a Chat Feature
Cumora’s public repository presents a cross-platform team chat application in which AI agents occupy the same conversational spaces as people: direc…
AI Reviewing AI Is Not Review
Originally published at tddbuddy.com . Related reading: Where the Review Point Moved is the direct predecessor; this post argues the industry's resp…
Three Clouds, One Brief: What Actually Differs Between ADK, Strands and Agent Framework
All three hyperscalers now ship an agent framework, and all three speak A2A. The protocol page will tell you that is the interoperability story fini…
Strands on AgentCore, Answering Two Other Clouds: The Contract, the Header, and the microVM
Strands ships no A2A server integration, which turns out to be the easiest starting position of the three frameworks I used: you drop the agent behi…
I Handed 41 Tasks to an AI Loop. The Bottleneck Was Judgment, Not Code
Is there a region at the bottom of your task ledger you haven't scrolled to in weeks? Mine held 41 tasks across two repositories. I use AI agents ev…
Two Verifiers, One Verdict: Closing the 'Self-Reported Exit Code' Hole
Two Verifiers, One Verdict: Closing the "Self-Reported Exit Code" Hole Repo: github.com/dengyier/OpenWorkProof This update: 04e62d5..ec0e72e (29 com…
Screenpipe YC S26: Record Workflows to Power AI Agents
What Happened Screenpipe, a startup that closed a Series A round as part of Y Combinator’s S26 cohort, unveiled a tool that records on‑screen activi…
Cockpit for Claude Code agents in Rust – a new UI for AI workflow con…
What Happened A developer posted a new project on Show HN titled Cockpit for you Claude Code agents in Rust . The release is a lightweight UI writte…
Show HN: Designing the GUI for AI Agents
What Happened A Show HN thread titled "What should the GUI for AI agents look like?" sparked debate among developers, designers, and ops engineers.…
Notion AI Agents in 2026: What They Can Replace (and Can't)
Notion spent most of its life as a place to write documents and organize databases. In 2026 it repositioned itself as something closer to an operati…
The Hottest AI Framework Right Now Has a Fatal Flaw Nobody Mentions
I spend a lot of time in the AI space -- reading papers, building things, talking to engineers who are actually shipping. And there is a gap between…
Building an AI Assistant: flutter nodejs ai browser automation
This article was originally published on BuildZn . Figured out how to tame web automation with an LLM. Everyone talks about AI agents, but getting t…
Cleared Kimi Slides Repository Leaves Its Core Claims Unverifiable
GitHub’s page for Binaryify/open-kimi-ppt-skill says the repository was archived and made read-only after its contents were cleared for copyright re…
My 9-Day Journey Building a Real-Time AI Voice Agent | VoiceForBharat
10 Days of AI Voice Agents — VoiceForBharat Edition Over the past 9 days, I built and improved a real-time AI voice agent as part of the 10 Days of…