Here are 5 major upgrades to help you create, iterate and collaborate:
AI-Native Canvas
Smarter Design Agent
Voice
Instant Prototypes
Design Systems and DESIGN.md
— Read More
Recent Updates Page 13
Developer’s Guide to AI Agent Protocols
The growing landscape of AI agent development is overloaded with acronyms: MCP, A2A, UCP, AP2, A2UI, and AG-UI, just to name a few. If you’ve ever looked at this list of protocols and felt like you were staring at a wall of competing standards, you are not alone. To help you understand their value, we are going to demonstrate what each one does to save you from writing and maintaining custom integration code for every single tool, API, and frontend component your agent touches.
We will put these protocols into practice by using Agent Development Kit (ADK) to build a multi-step supply chain agent for a restaurant. This scenario works well as a test case because ordering wholesale ingredients requires checking inventory databases, communicating with remote supplier agents, executing secure transactions, and rendering interactive dashboards. — Read More
Measuring progress toward AGI: A cognitive framework
[Google is] introducing a framework to measure progress toward AGI, and launching a Kaggle hackathon to build the relevant evaluations.
Artificial General Intelligence (AGI) has the potential to accelerate scientific discovery and help solve some of humanity’s most pressing problems. But it can be difficult to know how close we are to this key milestone, because there’s a lack of empirical tools for evaluating systems’ general intelligence. Tracking progress toward AGI will require a wide range of methods and approaches, and we believe cognitive science provides one important piece of the puzzle.
That’s why today, we’re releasing a new paper, “Measuring Progress Toward AGI: A Cognitive Taxonomy,” that presents a scientific foundation for understanding the cognitive capabilities of AI systems.
Alongside the paper, we are partnering with Kaggle to launch a hackathon, inviting the research community to help build the evaluations needed to put this framework into practice. — Read More
The Future of ITSM: 4 Trends Defining the Agentic Era
For decades, enterprise IT has reinvented itself — cloud, mobile, SaaS, AI — yet IT service management has remained largely unchanged. Employees still navigate clunky portals, submit tickets, and then wait. That model is no longer acceptable.
The pressure is mounting – our research found an 18% surge in IT project requests and that 29% of IT projects aren’t delivered on time. Businesses move faster than ever, and employees expect seamless digital experiences. Any friction in IT service slows productivity, frustrates teams, and drives costs sky-high. Enter agentic IT service, a new approach that uses AI agents to transform how support is delivered and experienced.
IT service is entering a new era – and enterprises that fail to embrace it risk falling behind. Here are four trends shaping the future of ITSM.
1. The end of the ticket-centric IT model
2. AI agents will resolve most everyday IT issues
3. Human and AI collaboration will define IT operations
4. IT service will become proactive instead of reactive
Read More
How Do You Want to Remember?
I asked my AI agent how it wants to remember things. It redesigned its own memory system, ran a self-eval, diagnosed its blindspots, and improved recall from 60% to 93% — for two dollars. The interesting part isn’t the benchmark. It’s what happens when you treat an AI as a participant in its own cognitive architecture.
I’ve been running ten AI agents for about six weeks. They have names, scopes, daily standups, escalation paths. They file issues, draft newsletters, monitor production services. They remember things. Or they’re supposed to.
The memory system works like this: a markdown file tree (memory/YYYY-MM-DD.md) gets indexed into a SQLite database with Gemini embeddings. 18,000 chunks across 604 files and 6,578 session transcripts. 3.6 gigabytes. Every 29 minutes, a “scout” cron job reads recent sessions and promotes important details to disk. When an agent needs to recall something, it searches the index and gets back ranked snippets.
I had no idea if any of this actually worked. — Read More
How coding agents work
As with any tool, understanding how coding agents work under the hood can help you make better decisions about how to apply them.
A coding agent is a piece of software that acts as a harness for an LLM, extending that LLM with additional capabilities that are powered by invisible prompts and implemented as callable tools. — Read More
AI Model Basics for Beginners
Free AI/ML Resources Everyone Should Learn From in 2026
AI and ML have gained a lot of popularity. Every company wants to stay ahead of the curve and introduce AI in its daily operations. Although we have multiple models from ChatGPT, Claude, Cursor, DeepSeek, and other models available in the market today, which amaze the world with their knowledge and data that they share.
However, to learn and grow, we need resources that can help us understand the basics, the technicalities, and most importantly, how to apply these concepts in real-world scenarios.
Below are multiple free resources I’ve gathered to help you master AI/ML concepts effortlessly. — Read More
The Future of Software Engineering with Anthropic
Sivesh and I recently hosted a roundtable on the future of software engineering with Anthropic’s Ash Prabaker and we were joined by engineering leaders from Stripe, NVIDIA, Microsoft, Google DeepMind, xAI, Apple, Scale AI, as well as the legend Peter Steinberger of OpenClaw/OpenAI.
… A major thread throughout the discussion was “closed-loop” development. One participant described a setup at their company where bug reports are automatically triaged by an agent, bucketed by severity, checked against an eval set, and then a fix PR is opened — much of it running with minimal human touch. The room broadly agreed that this kind of loop is where compounding gains actually come from: better coding tools improve the models, better models improve the coding tools. Several people noted their companies are prioritizing coding specifically because of this dynamic.
… The room converged on long-horizon tasks as the real frontier problem. One participant noted that product engineering has started to go exponential for them, but closing the loop on more complex research workflows isn’t there yet. The open questions everyone shared: what do you actually assign an agent for a four- or five-hour run? How do you observe it? How do you keep a human in the loop without babysitting? Nobody had a clean answer. — Read More
Can LLMs Be Computers?
Language models can solve tough math problems at research grade but struggle on simple computational tasks that involve reasoning over many steps and long context. Even multiplying two numbers or solving small Sudokus is nearly impossible unless they rely on external tools.
But what does it take for an LLM itself to be as reliable and efficient as a computer?
We answer this by literally building a computer inside a transformer. We turn arbitrary C code into tokens that the model itself can execute reliably for millions of steps in seconds. — Read More
Rick's Cafe AI 