-
Digital Provenance as a Trust and Compliance Requirement
For most of computing history, trust was implicit. You installed the package from npm because it was on npm. You believed the photo in your feed because photos were hard to fake convincingly. You trusted the data in your warehouse because someone you knew had loaded it. None of that trust was verified — it was assumed, because forging the alternative was expensive or obvious. That assumption has collapsed on three fronts simultaneously, and the collapse is why digital provenance — the verifiable record of a digital asset’s origin, authorship, modifications, and chain of custody — has gone from a… Go to Post
-
Pre-emptive Cybersecurity
Security has one brutal piece of arithmetic at its core: defenders must be right every time; attackers only need to be right once. For decades the response to that asymmetry was reactive — build taller walls, install faster alarms, and when something gets through, detect and respond. Detection-and-response (D&R) is the model that gave us SIEMs, SOCs, EDR, and the entire incident-response playbook. It works by waiting for an attack to begin, then reacting. In 2026, that model is buckling, and the reason is speed. Machine-speed attacks broke the reactive window The reactive model depends on a window: the time… Go to Post
-
New AI-Era Attack Vectors
For years the most effective attackers have avoided bringing malware at all. Why smuggle in a payload your EDR will flag when the target machine already ships with everything you need? This is living off the land (LOTL): abusing legitimate, pre-installed tools — PowerShell, WMI, signed system binaries (“LOLBins”) — to operate. Because the tools are allowlisted and the activity looks normal, LOTL leaves no malware signature and blends into routine operations. By 2023, CrowdStrike reported that roughly 6 in 10 detections involved LOTL techniques rather than traditional malware. It works because the safest tool to attack with is one… Go to Post
-
Securing the Agent Harness
Start with a number. An agent that opens 1,000 pull requests a week at a 1% vulnerability rate ships 10 new vulnerabilities every week — quietly, confidently, indefinitely. That’s the uncomfortable arithmetic of autonomy: a small per-action error rate, multiplied by machine-speed volume, becomes a steady stream of security holes. A human writing ten PRs a day can’t produce vulnerabilities fast enough to matter at that scale. An agent fleet can. This reframes the whole problem. Security for AI agents isn’t a model-quality question you can solve with a better prompt. It’s a systems question, and the answer to “how… Go to Post
-
RAG for Knowledge-Grounded Agents
An ungrounded agent is a confident liar. Ask it about your company’s refund policy, last quarter’s numbers, or a customer’s order history, and it will produce a fluent, plausible, well-structured answer — drawn from its training data, its priors, or nothing at all. The words are right; the facts may be invented. That’s the hallucination problem, and it’s the single biggest barrier between a demo and a system you’d let talk to customers. Retrieval-Augmented Generation (RAG) is the answer the industry converged on, and in 2026 it’s the default architecture for any agent that needs to answer from private or… Go to Post
-
Why Agentic Projects Fail
Almost everything written about agentic AI is a showroom: the demo that dazzled, the workflow that now runs itself. This article is the morgue. Because the most useful thing you can study before building an agentic system isn’t the success stories — it’s the autopsies. And there are a lot of bodies. The headline number is Gartner’s, from June 2025: over 40% of agentic AI projects will be cancelled by the end of 2027 — not scaled back, not pivoted, cancelled — citing escalating costs, unclear business value, and inadequate risk controls. It’s not a speculative warning; Gartner frames it… Go to Post
-
Free Booklet: Claude AI The Complete Guide
Anthropic ships major Claude updates almost weekly, which makes staying current with the platform a genuine full-time problem — even the best deep-dive guides go stale within weeks of publication. Claude AI: The Complete Guide solves that by treating currency as a feature: every pricing figure, benchmark, and model spec is timestamped, every correction from prior editions is called out explicitly rather than quietly fixed, and this August 2026 revision covers everything from the new Claude Opus 5 to the Fable 5/Mythos 5 export-control saga that briefly took two flagship models offline worldwide. Whether you’re writing your first API call… Go to Post
-
Multi-Agent Orchestration: From One Agent to Many (and When Not To)
You start with one coding assistant and it’s great. So you add a second agent to review the first. Then a planner. Then a tester. Each addition feels reasonable, and somewhere around the fourth one the system starts to wobble: the logs balloon, the agents make contradictory decisions, costs spike, and you’re back babysitting it at 2 a.m. wondering whether all this orchestration actually bought you anything. That tension — more power versus more pain — produced one of 2025’s sharpest engineering disagreements. On June 12, Cognition (the team behind Devin) published “Don’t Build Multi-Agents,” arguing that parallel subagents make… Go to Post
-
How Can AI Help My Business?
If you run a small business and you’ve been wondering whether this whole AI thing is for you, here’s the honest state of play in 2026: most of your peers have already started. Depending on which survey you read, somewhere between 82% and 89% of small businesses now use AI in some form — up from roughly a third just three years ago. The U.S. Chamber of Commerce found small firms adopting AI faster than large companies for the first time in the data’s history. But that headline hides the part that should reassure you. When researchers look at who’s… Go to Post
-
AI Slop & Review at Scale
Sonar’s 2026 State of Code Developer Survey put a hard figure on a feeling every engineer already had: 96% of developers don’t fully trust that AI-generated code is functionally correct. That’s the stat that made headlines. But the more revealing one sits right next to it: only 48% always verify AI code before committing. Sit with that gap. Nearly everyone distrusts the output, and barely half consistently check it. Sonar calls the space between those numbers the verification gap — and AWS CTO Werner Vogels gave the accumulating consequence a name at re:Invent in December 2025: verification debt. The pressure… Go to Post
-
The Senior Developer Bar in 2026
A lot of my posts are about how to build with AI — agents, orchestration, the Microsoft stack, the protocols. This series steps up a level and asks a harder question aimed squarely at senior and lead developers: in mid-2026, what actually makes you valuable? Because the answer has moved, and a lot of people haven’t noticed. The bar is no longer “I integrated an LLM” Two years ago, wiring an LLM into a product was a differentiator. You could stand up in a review, show a feature that called a model, and that was the value. In mid-2026 that’s… Go to Post
-
Free Mini-Course: FND-101 AI Foundations for Practitioners
Modern AI has its own concepts, vocabulary, and ways of working that are unfamiliar even to experienced engineers. This course is the technical front door to the catalogue: it gives practitioners the grounding they need before entering any of the intermediate and advanced tracks, so they are not learning fundamentals and specifics at the same time.Students build an accurate mental model of what today’s AI is, how language models behave, what the application landscape looks like, and how quality and responsibility are handled. The emphasis is on genuine understanding rather than hype or hand-waving.Labs are gentle, guided exercises that let… Go to Post
-
Context engineering as a software discipline
You ask your coding agent to add a new endpoint. It churns for a minute and produces beautiful, idiomatic code that compiles on the first try. You merge it. Then you deploy, and three services fall over. The agent ignored your authentication layer, bypassed the validation patterns every other handler uses, and pulled in a dependency that conflicts with your stack. None of that was in your prompt. You assumed the agent would just know — it’s been trained on millions of repositories, after all. But it had never seen your repository, your conventions, or your production constraints. The prompt… Go to Post
-
CLI Agents vs AI-Native IDEs: The Token Economics
Here is the benchmark that’s been driving architecture decisions across the industry in 2026: a typical CLI command costs an agent around 200 tokens. The equivalent operation through an MCP server costs 32,000 to 82,000 tokens. That’s not a typo, and it’s not cherry-picked. Independent benchmarks from Scalekit, Apideck, and others keep landing in the same range — roughly a 35× overhead for MCP on identical tasks. When “MCP is dead. Long live the CLI” hit the top of Hacker News and Perplexity’s CTO publicly described moving away from MCP internally over context waste, they were all pointing at the… Go to Post
-
MCP vs A2A: Two Protocols, Two Different Problems
If you’ve built anything with AI agents recently, you’ve heard two acronyms thrown around constantly, often with wildly conflicting takes: “MCP is the USB-C of AI.” “A2A replaces MCP.” “You need both.” “Neither is production-ready.” Most of that noise comes from a single confusion. MCP and A2A solve completely different problems, and treating them as competitors — or worse, as interchangeable — is one of the most common and most expensive architecture mistakes in the space right now. Get the distinction wrong and your system fights you at every layer: you’ll find yourself wrapping databases as “agents,” building bespoke RPC… Go to Post
-
Agentic Engineering: From Vibe Coding to a Plan, Execute, Verify Discipline
For about a year, “vibe coding” was the most fun anyone had had with a keyboard. You describe what you want, an agent writes it, you skim the result, you ship. Andrej Karpathy’s original framing was almost gleeful: you “give in to the vibes” and barely read the diffs. Then teams tried to put vibe-coded software into production, and the bill came due. The failure mode now has a name — AI slop: code that looks reasonable on the surface but lacks error handling, quietly introduces security vulnerabilities, breaks something three modules over, or produces an architecture nobody can maintain.… Go to Post
-
Free Booklet: Monitoring And Auditing In AWS
Monitoring and Auditing in AWS is a practical guide designed to help developers, architects, and security professionals build robust visibility into their cloud environments. As organizations increasingly rely on AWS to power critical workloads, the ability to track activity, detect anomalies, and respond to potential threats becomes essential. This booklet explores the core services, patterns, and best practices that enable effective monitoring and auditing across AWS, providing a clear path to strengthening security posture, ensuring compliance, and maintaining operational resilience in modern cloud-native systems. Go to Post
-
Free Booklet: Build And Deploy Anywhere With GPT-5 Codex
This interactive booklet is intended as an expanded version of the previous post. Due to the nature of code generation, the actual output and workflow will be different for each case. The code examples in this booklet are mainly for illustrative purposes. Go to Post
-
Build and Deploy Anywhere with GPT-5.3-Codex
Software engineering has always evolved alongside its tools. Compilers turned human ideas into executable programs. Integrated development environments improved productivity and debugging. Version control systems enabled collaboration at scale. Continuous delivery pipelines made rapid and reliable deployment possible. In early 2026, another major step appeared: agentic coding systems capable of participating in the engineering process itself. One of the most advanced examples of this new class of tools is GPT-5.3-Codex, OpenAI’s latest coding-focused model designed to reason across repositories, plan multi-step changes, execute development tasks, and collaborate with engineers across the full software lifecycle. Unlike traditional autocomplete-style coding assistants, GPT-5.3-Codex… Go to Post
-
The Rise of “Vibe Coding” and Intuitive Software Development
The world of software development is being reshaped by a new, more intuitive approach: “vibe coding.” This method, fueled by advancements in artificial intelligence, is moving the focus from writing syntactically perfect code to expressing the desired outcome in natural language. This deep-dive article explores the essence of vibe coding, spotlights the pioneering tools enabling this shift, and provides a framework for its integration across the entire Software Development Life Cycle (SDLC). Deconstructing the “Vibe”: What is Vibe Coding? At its core, vibe coding is a development practice where a human developer collaborates with an AI-powered coding assistant to generate,… Go to Post
Professional Developer
by Rodrigo Silva
