标签：#ai

Grab's security team built Palana, a Kubernetes-native secure execution platform, to run autonomous AI agents safely. Unlike deterministic software, model-driven agents exhibit unpredictable tool-use, code-writing, and prompt injection risks. Palana contains these threats at the infrastructure level using isolated namespaces, out-of-process control planes, and proxy-mediated, Vault-backed secrets. By Patrick Farry

Exposing your app to an AI agent over MCP is basically handing someone a master keyring and trusting them to only open the doors they're supposed to. That trust is a bug waiting to happen. This week I wired up a batch of MCP tools over a multi-tenant Laravel app, and the whole exercise was really about one question: how do I let an agent drive the app without letting it drive someone else's data? Here's the thing about MCP tools — each one is an endpoint. An agent calls list_events , publish_event , check_in_participant , and your server runs code on the caller's behalf. The moment you have more than one tenant, every single tool needs to answer two questions before it does anything: are you allowed to do this , and are you allowed to do it *here *. Authorization and scope. Skip either and you've built a confused deputy. The trap: ambient scope doesn't exist under token auth In a normal web request, multi-tenancy is comfortable. You've got a logged-in user, a global scope on the model that quietly appends where organization_id = ? , and you mostly forget it's there. Everything Just Works because there's an ambient "current organization" sitting in the session. MCP tools don't have that. The caller authenticates with a token, there's no session, no middleware stack that set up a current-tenant context. If you lean on a global OrganizationScope that reads "the current org" from somewhere, it reads nothing — and a query you assumed was fenced returns every tenant's rows. That's the kind of bug that doesn't throw an error; it just silently leaks. So the rule I settled on: under token auth, never rely on ambient scope. Filter explicitly, every time, in one place. That "one place" is a small trait every event-scoped tool pulls in: trait ResolvesOrgEvents { protected function resolveOrgEvent ( Authenticatable $user , string $uuid ): ?Event { if ( empty ( $user -> organization_id )) { return null ; } return Event :: query () -> withOrganization ( $user -> organization_id )

Sometimes, the best ideas come when you least expect them — like at 2 AM, scrolling through social media with nothing exciting to do. That’s exactly how IGram, my latest side project, came to life. No grand plans, no investors, no pressure — just a spark of curiosity and a desire to build something fun. In this post, I’ll share the story of how IGram started, what it is, the challenges I faced, and what I learned along the way. If you’ve ever wondered what it’s like to build a messaging app from scratch or are just curious about side projects, this one’s for you. HOW IT BEGAN _**A few days ago, stuck in an endless social media scroll loop, I suddenly thought, “Why not build my own messaging app?” Not to compete with the giants like Telegram or WhatsApp, and certainly not because I had a startup idea or funding. Simply because I wanted to see how far I could take it. That spontaneous idea turned into IGram, a project born purely out of boredom and a hunger to learn. What Is IGram? IGram is a modern messaging app inspired by platforms like Telegram and Discord. But it’s not a clone. Instead, it’s designed to feel fast, smooth, and enjoyable—an experience I wanted to craft from the ground up. It’s my personal challenge and learning experiment, built solo and fueled by the excitement of creating something new. Features You’ll Find in IGram Even though it started as a simple idea, IGram has grown to include a solid set of features: One-to-one messaging Group conversations Channel support Message reactions, editing, and deletion Reply and message forwarding Search functionality Dark and light themes Responsive design and mobile-friendly layout User profiles and modern UI animations Every feature is designed to keep the app feeling smooth and responsive, because the user experience matters just as much as the functionality. The Biggest Challenge: User Experience Surprisingly, writing the code wasn’t the toughest part—it was designing how everything flows and feels. Modern

Part 4 of the Building Enterprise AI Automation Systems Series Introduction Most Named Entity Recognition (NER) tutorials end with a prediction. The model successfully extracts: COMPANY INVOICE CONTRACT PURCHASE_ORDER The article ends. The notebook prints a beautiful JSON response. Mission accomplished. Or so it seems. In real enterprise systems, extracting entities is only the beginning. Consider the following prediction: { "COMPANY" : "ALPHABRIDGE" , "INVOICE" : "MFG-INV-000157" } At first glance, everything looks correct. But from a business perspective, the system still knows almost nothing. Questions remain unanswered. Which ALPHABRIDGE? Which customer record? Which contract? Which invoice? Which business relationship? These questions belong to a completely different problem known as Entity Resolution. Entity Resolution transforms extracted text into business knowledge. Without it, AI understands words but not businesses. NER Finds Text Named Entity Recognition answers one question: "What pieces of text represent meaningful entities?" For example: PAYMENT FROM ALPHABRIDGE SOLUTIONS MFG-INV-000157 becomes { "COMPANY" : "ALPHABRIDGE SOLUTIONS" , "INVOICE" : "MFG-INV-000157" } This is extraction. Nothing more. The model has no idea whether: the company exists, the invoice exists, the invoice belongs to the company, the invoice has already been paid, the contract is still active. Extraction is syntax. Enterprise automation requires semantics. The Hidden Problem Imagine the following customer master. CUS-00001 ALPHABRIDGE SOLUTIONS Now imagine receiving these transaction narratives. PAYMENT FROM ALPHABRIDGE PAYMENT FROM ALPHABRIDGE LTD PAYMENT FROM ABS PAYMENT FROM ALPHA BRIDGE Humans immediately recognize these as the same customer. Machines do not. To a computer, every string is different. Without resolution, automation immediately breaks. What Entity Resolution Actually Does Entity Resolution answers a different question. Instead of asking: "What entity is this?"

Introduction Most developers today are learning how to “use AI APIs.” But that’s not enough anymore. The real shift happening in software engineering is this: We are moving from building APIs → to building AI-powered systems. And that requires a completely different mindset. The Problem with Most AI Tutorials Most tutorials show this: Call OpenAI API Get response Print output That’s it. But in production systems, this approach fails because it ignores: Context management State handling Reliability Tool integration System design In real applications, AI is not a function call — it is an orchestrated system. What an AI System Actually Looks Like A production AI system usually includes: 1. Input Layer Validation Preprocessing Safety checks 2. Reasoning Layer (LLM) Prompt engineering Context injection Model selection 3. Tool Layer APIs Databases Search engines Internal services 4. Memory Layer Conversation history Vector DB / embeddings User context 5. Output Layer Formatting Validation Response filtering Simple Example: From API Call → AI Agent Thinking Instead of this: response = client . chat . completions . create (...) We design something like this: class AIAgent : def __init__ ( self , llm , tools ): self . llm = llm self . tools = tools def run ( self , user_input : str ): context = self . build_context ( user_input ) response = self . llm . chat . completions . create ( model = " gpt-4o-mini " , messages = context , temperature = 0.2 ) return self . post_process ( response ) Now AI becomes: ✔ structured ✔ extendable ✔ production-ready Key Shift in Thinking Old mindset: “How do I call the model?” New mindset: “How do I design the system around the model?” That’s the difference between: ❌ AI script ✅ AI product system Why Tools Matter More Than Prompts Modern AI systems are not just text generators. They are tool-using systems . Examples: Search APIs (RAG systems) Databases (SQL, NoSQL) External APIs Internal business logic This turns AI from “chatbot” into “agent

Part 3 of the Building Enterprise AI Automation Systems Series Introduction Named Entity Recognition (NER) is one of the oldest problems in Natural Language Processing. Most tutorials introduce NER using examples like: Person Organization Location Date A sentence such as: Elon Musk founded SpaceX in California. becomes PERSON ORGANIZATION LOCATION While this is useful for learning NLP fundamentals, it has very little relevance to enterprise software. Businesses do not automate biographies. They automate operations. Enterprise documents contain an entirely different language. Invoices. Contracts. Purchase Orders. Bank Statements. Remittance Advice. Payment Narratives. ERP Exports. The entities that matter inside these documents are not "PERSON" or "LOCATION". Instead, they are business concepts such as: Customer Contract Invoice Purchase Order Payment Type Understanding these entities is the first step toward intelligent automation. In this article, we'll build a Financial Named Entity Recognition pipeline capable of transforming raw enterprise transaction narratives into structured business knowledge. The Difference Between Generic NER and Enterprise NER Traditional NER focuses on linguistic entities. Enterprise NER focuses on operational entities. Consider the following sentence. PART PMT ALPHABRIDGE SOLUTIONS MFG-INV-000157 A generic language model may identify: Organization and ignore everything else. From a business perspective, this is almost useless. What we actually need is: PAYMENT_TYPE COMPANY INVOICE The objective is not language understanding. The objective is business understanding. Step 1 — Designing the Business Taxonomy Before training any model, define what the model should learn. This is one of the most overlooked stages in machine learning projects. Many teams immediately begin annotation without first defining a taxonomy. As a result, annotations become inconsistent. Models become confused. Evaluation becomes unreliable. For our transaction intell

If you've ever watched a hacker movie and seen someone plug in a USB and own a machine in seconds — that's not Hollywood magic. That's a Rubber Ducky. And I built one for under ₹150. Here's exactly how I did it, what it taught me, and why every security student should build one. What Even Is a Rubber Ducky? A Rubber Ducky is a USB device that pretends to be a keyboard. The moment you plug it in, the operating system trusts it completely — because keyboards don't need driver approvals or admin permissions. Once trusted, it starts "typing" pre-programmed commands at superhuman speed. We're talking 1000 keystrokes per second. By the time you blink, it's already opened PowerShell, run a script, and closed the window. The original Hak5 Rubber Ducky costs around $80. I built mine for ₹150. What I Used DigiSpark ATtiny85 — ₹120–150 on Amazon India Arduino IDE — free A Windows test machine (my own laptop) 15 minutes That's it. No soldering. No special skills. Just a tiny microcontroller the size of a thumb. Setting It Up Step 1 — Install Arduino IDE Download from arduino.cc and install normally. Step 2 — Add DigiSpark Board Support Go to File → Preferences and paste this into Additional Board Manager URLs: http://digistump.com/package_digistump_index.json Then go to Tools → Board → Board Manager, search Digistump and install. Step 3 — Install Drivers DigiSpark needs Micronucleus drivers on Windows. Download from the official Digistump GitHub and run the installer. Step 4 — Write Your First Payload This opens Notepad and types a message — my first ever "attack": cpp#include "DigiKeyboard.h" void setup() { DigiKeyboard.delay(2000); DigiKeyboard.sendKeyStroke(KEY_R, MOD_GUI_LEFT); // Win+R DigiKeyboard.delay(500); DigiKeyboard.print("notepad"); DigiKeyboard.sendKeyStroke(KEY_ENTER); DigiKeyboard.delay(1000); DigiKeyboard.print("Hello. Your keyboard is now mine."); } void loop() {} Upload it, plug in the DigiSpark, and watch it type on its own. That moment hits different when y

Part 2 of the Building Enterprise AI Automation Systems Series Introduction One of the biggest obstacles in enterprise AI is not choosing a model. It is finding data. Most tutorials assume that training data already exists. Reality is very different. Large organizations rarely share operational datasets. Financial transactions contain confidential information. Contracts contain sensitive agreements. Invoices reveal commercial relationships. Bank statements expose customer activity. For legal, regulatory, and competitive reasons, these datasets almost never become public. This creates a difficult problem for AI engineers. How do you build intelligent systems when the data you need cannot be accessed? The answer is synthetic data. Unfortunately, most synthetic datasets found online are little more than randomly generated CSV files. They contain names. Numbers. Dates. But they completely ignore something far more important: Business relationships. In this article, we'll explore how to design synthetic enterprise datasets that preserve real business logic and can be used for machine learning, automation, benchmarking, and AI engineering. Random Data Is Not Synthetic Data Many developers believe synthetic data simply means generating fake values. For example: Customer,Invoice,Amount John,INV001,500 Alice,INV002,1200 Bob,INV003,900 Technically, this is synthetic. Practically, it is useless. Why? Because enterprise systems are built around relationships. Invoices belong to contracts. Contracts belong to customers. Payments reference invoices. Purchase orders authorize invoices. Bank transactions settle invoices. Without these relationships, there is nothing meaningful to learn. A machine learning model trained on isolated records learns isolated patterns. Real enterprise automation requires connected data. Thinking Like an Enterprise System Before writing a single line of Python, ask one question: "How does the business actually operate?" Imagine a manufacturing company. A

As ASML CEO Christophe Fouquet told TechCrunch in May, what China can currently buy are older-generation deep ultraviolet tools — gear first shipped about a decade ago — the same machines the MATCH Act would now put off limits.

Backed by Mayfield and Aramco Ventures, Vishal Sikka’s new venture brings together veterans from SAP, Infosys, and VianAI.

Thariq Shihipar, engineering lead for the Claude Code team, recently published a blog post (Using Claude Code: The Unreasonable Effectiveness of HTML) arguing that HTML, with its richer visualizations, color, and interactivity, improves the productivity of human-agent communication in many settings, especially when compared to default Markdown outputs. By Bruno Couriol

In its first earnings report since going public, the AI chipmaker forecast a narrower gross margin in its core business, scaring investors.

The silicon race is heating up amid the struggle to keep up with demand.

While AI dominates the layoff narrative, engineers as a share of total new hires have actually increased, according to SignalFire data.

Top AI researchers Jonas Adler and Alexander Pritzel are leaving Google for Anthropic, following departures from top scientists Noam Shazeer and John Jumper.

Revenue quadrupled to $41.45 billion compared with the same period a year ago. The company's profit, meanwhile, rose from $1.88 billion to an incredible $28.2 billion year-over-year.

One universal AI agent sounds convenient. One agent to read tickets, write code, generate tests,...

If you're building AI agents that work with browser screenshots, you already know the pain. You take a full 1920×1080 screenshot, pass it to GPT-4o or Claude, and watch your token bill climb — while the model downscales the image anyway and blurs the exact text you needed it to read. There's a better way. The problem Vision LLMs are expensive for two reasons when you feed them full screenshots: Token cost — a full screenshot can cost 10–20x more tokens than a small crop Accuracy loss — models internally downscale large images, blurring fine text, labels, and UI elements But your agent already knows where to look. Browser automation tools like Playwright and Puppeteer give you getBoundingClientRect() — the exact pixel coordinates of any element on screen. So why are you sending the whole screenshot? The solution I built a stateless pay-per-use API that takes a screenshot and pixel coordinates, and returns just the cropped element as a lossless PNG — ready to pass directly to your vision LLM. POST /crop { "image" : "<base64 screenshot>" , "x" : 120 , "y" : 45 , "width" : 640 , "height" : 80 } Returns: { "success" : true , "data" : { "base64" : "iVBORw0KGgo..." , "mime" : "image/png" , "width" : 640 , "height" : 80 , "bytes" : 4821 } } A 4KB crop instead of a 2MB screenshot. Same information. 95% fewer tokens. How payment works Here's where it gets interesting. The API uses the x402 payment protocol — HTTP's long-dormant 402 Payment Required status code, finally put to use. There are no API keys. No accounts. No subscriptions. The agent pays $0.0005 USDC per crop on Base L2 automatically. The flow: 1. Agent POSTs to /crop (no payment header) ← 402 with payment instructions in headers 2. Agent transfers 0.0005 USDC to recipient wallet on Base (near-zero gas, ~2 second settlement) 3. Agent POSTs again with x-payment-tx-hash header ← 200 with cropped PNG The entire exchange happens inside the HTTP request cycle. No human intervention. No billing dashboard. The money lands

Your product might rank on page one of Google and still be invisible to AI. When someone asks ChatGPT "what's the best project management tool for small teams," does your product show up? For most SaaS companies under 50 employees, the answer is no. At Inithouse, we built Be Recommended to answer that question with a number: a single AI visibility score from 0 to 100 that tells you exactly where you stand across four major AI engines. Here is how the scoring works under the hood. What the score measures The Be Recommended score captures how often, how prominently, and how positively AI engines mention your product when users ask category-relevant questions. A score of 0 means no AI engine mentions you at all. A score of 100 means every tested prompt across all four engines names your product as a top recommendation. The four engines we test against: ChatGPT (OpenAI), Perplexity , Claude (Anthropic), and Gemini (Google). Step 1: Prompt generation We start by building a bank of 50+ real prompts that a potential customer would actually type into an AI assistant. These are not keyword-stuffed test queries. They mirror how real people ask for recommendations. For a CRM product, that looks like: "What CRM should a 10-person startup use?" "Best alternatives to Salesforce for small businesses" "Compare CRM tools with good API integration" "Which CRM has the best free tier in 2026?" We group prompts into three categories: direct (user names the product category), comparative (user asks for alternatives or comparisons), and situational (user describes a problem without naming a category). Each category tests a different signal: brand recognition, competitive positioning, and contextual relevance. Step 2: Multi-engine querying Each prompt gets sent to all four AI engines through their APIs. We capture the full response text, not just a yes/no for whether your product appeared. The raw responses go into a structured analysis pipeline. We run queries from neutral accounts with n

TL;DR - A finished app that only runs on one laptop is a private demo. Getting it online means connecting three things: a place to store the code (version control), a place to run it (a host), and an address people can type (a domain). The same AI tool that helped build the app can walk a beginner through all three, often without ever opening a terminal. An important step you don’t want to skip is the security check before going live, because the fastest way to ruin a launch is to ship with the database wide open. So you’ve done it. You built your first tool. And it works. The button does the thing. Now’s the moment. It’s time to get your tool online, but how? A project running on a laptop is real, but it lives in exactly one place, the machine it was built on. Nobody else can open it. Getting that project online is its own small skill, separate from building, and it trips up more beginners than the building did. A new coder can finish a working photo booth app in an afternoon and still have no idea how to hand it to a friend short of pulling up the GitHub link while sitting together over coffee. The good news is that the part that used to eat a whole weekend now takes a conversation. Three Things Every App Needs to Go Live Almost every deployment, whatever the tool, comes down to three things working together. Version control: This is a place to store the code and track every change made to it. For most people that means GitHub, which we’ve talked about before. The same way Google Docs keeps a version history, GitHub keeps one for a project. This piece does not re-explain it; the GitHub walkthrough covers the whole thing. A host: A host is really just a computer that stays powered on and connected to the internet with a public address of its own. When a visitor types in the app's address, their browser sends a request across the internet to that machine, the machine runs the code, and it sends the finished page back. A laptop was quietly doing both jobs during the