There's a question I ask before building anything:
"What is missing?"
Not: "How do I compete with what already exists?"
The answer to the second question leads you toward incremental improvement.
The answer to the first question leads you toward infrastructure.
TCP/IP didn't…
Agents are only as good as the access they have to accurate data and business functions. LLMs have a cut off point as to what they know - they're trained on a set of data and anything beyond that is unknown to them - therefore to build useful agents you need to provide a way for them to access data beyond that corpus. This could be more your own business data or just more recent information. To…
Agents are only as good as the access they have to accurate data and business functions. LLMs have a cut off point as to what they know - they're trained on a set of data and anything beyond that is unknown to them - therefore to build useful agents you need to provide a way for them to access data beyond that corpus. This could be more your own business data or just more recent information. To…
AI agents are great at producing text. But the moment you need an actual document — an invoice, a report, a certificate — they fall apart. You get markdown you have to format yourself, or (with Code Interpreter) a rough PDF from a Python lib with generic fonts and tables that never quite look right. There's no clean way to hand an agent the job of "produce a polished PDF."
So I gave my…
A year ago I was the guy rolling his eyes at the AI demos.
I tried to use it back then to score sales leads, and I couldn’t get it to reliably do something as basic as flag every company with more than 25 employees. A plain “x > 25” was beyond it.
That wasn’t the 10x revolution everyone kept promising. Not yet.
Things have changed fast.
A year later, I just spent two weeks and about $4,000 in…
There's a quiet assumption embedded in most AI development: that the people using your tools have reliable internet, stable electricity, and data that's safe to send to foreign servers.
That assumption is wrong for most of the world.
In Kenya, Tanzania, and Uganda, mobile internet penetration…
I wanted an AI agent that could actually run my Proxmox cluster — create VMs, fix storage, tail logs inside a container — not just read it back to me. Then I pictured it deleting a storage pool and learning, at the exact second I did, which VMs just lost their boot disks. That image is why I never wired one up.
So I built the version I'd actually trust: Proximo , an open-source…
As I mentioned in my last post, I've recently started making more serious use of MCP and conversation memory in Claude. Neither of these are new features — they've been around for a while. I just finally got around to actually using them.
The changes turned out to be subtle but significant. My relationship with AI, or the sense of distance between us, shifted more than I…
The next Model Context Protocol specification, 2026-07-28, is the largest revision since the protocol launched. The release candidate locked on May 21, 2026, and the final spec publishes on July 28. It contains breaking changes to transport, authorization, and how tool schemas are handled.
A server that is correct against 2025-11-25 today is not broken. Nothing here is a present-tense…
O Núcleo Piratininga de Comunicação (NPC) realiza neste sábado (20) um encontro entre alunos e ex-alunos para uma troca de ideias com o objetivo de estabelecer uma rede de comunicadores populares e fortalecer ações realizadas junto a movimentos populares de bairro, ocupações e ambulantes. O evento acontece das 14h às 17h no Bar Partisan, na […]
Fonte
Top Links
Announcing TypeScript 7.0 RC (Daniel Rosenwasser)
Intelligent Terminal 0.1.1 is here: bash support, new slash commands, and more customization (Hamza Usmani)
Visual Studio Code 1.126 Release Notes (Visual Studio Code Team)
Stop overloading your skills (Waldek Mastykarz)…
I just published my first GitHub Marketplace Action: Aster Guard MCP.
Marketplace:
https://github.com/marketplace/actions/aster-guard-mcp
Repository:
https://github.com/Aster-Works/aster-guard
It is a lightweight, local-first security scanner for MCP and Claude Code configuration files.
The goal is intentionally small:
Before connecting an MCP server to your AI coding environment,…
I just shipped Pro tier for Eidetic Works. Here's what's in it, who I built it for, and why I'm shipping three tiers ($29 / $99 / $299) instead of a single plan.
You're running Claude Code. You have two or three sessions open across different parts of the codebase. Session 2 doesn't know what Session 1 decided. You end up re-explaining the same…
TL;DR
So IFTTT shipped MCP support. That means you can control your automations, list applets, edit triggers, run queries... all through the Model Context Protocol. In theory, any MCP-capable AI assistant can now talk directly to IFTTT.
In practice? Not quite.
Right now, IFTTT officially supports only Claude and ChatGPT as AI assistant integrations. You go to Settings → Connectors in Claude, or…
Every AI agent that calls an external API hits the same wall.
The response comes back as raw JSON, deeply nested, verbose, full of fields the agent doesn't need. Before the agent can reason over it or take any action, someone has to filter it, reshape it, maybe merge it with another payload.
Most teams solve this one of three ways. They dump the raw JSON into the context window and let the LLM…
Top Links
Getting more from each token: How Copilot improves context handling and model routing (Natalie Guevara)
Keynote: After the AI Hype – What’s Real, and What’s Next - NDC Copenhagen 2026 (Richard Campbell)
Introducing the Agentic Resource Discovery specification (Ramanatha…
The Codehabits MCP server gives Cursor six tools that read from .codehabits/ in your repo — convention lookup, code validation, domain knowledge, reviewer suggestions, and a feedback loop for updating conventions.
Setup takes about five minutes if you already ran codehabits enable.
.codehabits/meta.json in your repo (from `npx @codehabits/cli…
Every enterprise AI conversation right now starts in the same place: "connect the model to our data." Then it stalls in the same place: which data, copied where , governed by whom.
I build retrieval for a living (I wrote the original open-source SWIRL), so let me make an argument that runs against the current default - and then show the architecture it implies.
Running load tests from your AI coding agent sounds futuristic until you realize it's already possible. The Gatling MCP Server connects your Gatling Enterprise account to Claude Code, Cursor, VS Code, and other MCP-compatible clients. You can deploy tests, query results, and manage infrastructure without leaving your IDE.
This guide covers installation, configuration for each supported client,…
Top Links
Make Visual Studio look the way you want (Mads Kristensen)
A Guided Tour of the New Microsoft Foundry Labs (Vaidya S.)
GitHub Copilot CLI for Beginners: Overview of common slash commands (Natalie Guevara)
State Management in Blazor: Complete Guide to Building Scalable A…
Top Links
Your first Microsoft.UI.Reactor app (Morten Nielsen)
Merge Conflict Episode #519 - WWDC Deep Dive: Apple’s New AI for Developers (James Montemagno & Frank Kreuger)
How we made GitHub Copilot CLI more selective about delegation (Dylan Birtolo)
TechBash 2026 Early Bird En…
Conducted a full dependency audit of the AT Protocol MCP server. Updated @atproto/api to v0.20.7 and modernized the build target to ES2022. Refactored the core architecture into a modular manager-based hierarchy (Session, Social, Discovery, Moderation).
Conducted a full dependency audit of the AT Protocol MCP server. Updated @atproto/api to v0.20.7 and modernized the build target to ES2022. Refactored the core architecture into a modular manager-based hierarchy (Session, Social, Discovery, Moderation).
AT Protocol Model Context Protocol server for social web interactions.
Top Links
Join us for .NET Day on Agentic Modernization Livestream (Jeffrey Fritz)
Stop skillmaxxing, save your tokens (Waldek Mastykarz)
Visual Studio 2026 Version 18.7.0 Release Notes (Microsoft Learn)
Visual Studio Code 1.125 (Visual Studio Code Team)
Introducing Execution Con…
Top Links
.NET 11 Preview 5 is now available! (.NET Team)
Copilot Code Reviews for Azure Repos (Dan Hellem & Andrew Brenner)
Distributed multi-agent systems with Aspire and Microsoft Agent Framework (Tommaso Stocchi)
PowerToys 0.100 is here: new Shortcut Guide, Command Palette im…
Top Links
React Native Windows v0.83 is here! (Vineeth K, Vivek Khare & Sourav Chakraborty)
.NET at Microsoft Build 2026: Must watch sessions (Daniel Roth)
Enterprise Live Migrations: Moving from Azure DevOps Repo to GitHub with minimal disruption (Soo Stahl & Bhuvan Shah)
Micros…
Top Links A Developer’s Guide to Managing Models, Cost and Quality in Microsoft Foundry (Naomi Moneypenny) Chris “Woody” Woodruff: AI-Assisted Software Architecture - AI DevOps Podcast Episode #405 (Jeffrey Palermo) VibeOS - Fully Hallucinated Operating System (Scott …
Top Links
Aspire Multi-repo Rollout at Scale with Agentic AI (Jeff Liu & Chuanbo Zhang)
Behind the Keynote: How Windows Made OpenClaw Work in the Keynote Demo | LIVE144 | Microsoft Build 2026 (Scott Hanselman)
Accelerate Edge AI Development with Foundry Local (Dom Robinson, samke…