AI

Home » AI

Building Production AI Agents on AWS: AgentCore Harness, Strands 1.0, and the Multi-Agent Architecture that Actually Ships

2026-08-06T16:10:24+00:00

Six months ago, "AI agents on AWS" meant duct-taping together Amazon Bedrock, a Lambda function to handle tool routing, DynamoDB for session state, CloudWatch for tracing, and a LangGraph loop you prayed would recover from a network hiccup mid-reasoning. Every team was reinventing the same infrastructure. Every demo worked; most productions did not. That changed on June 17, 2026, at AWS Summit New York, where Dr. Swami Sivasubramanian (VP of Agentic AI) announced what AWS is calling the agentic infrastructure layer: Amazon Bedrock AgentCore Harness reaching general availability, the Strands Agents 1.0 SDK going production-grade with native multi-agent primitives, and [...]

Building Production AI Agents on AWS: AgentCore Harness, Strands 1.0, and the Multi-Agent Architecture that Actually Ships2026-08-06T16:10:24+00:00

Claude Skills Unlocked: A Practical Guide to Anthropic Academy’s 21 Free Courses

2026-07-31T10:22:44+00:00

Anthropic Academy has grown into one of the more substantial free AI learning resources available today, with 21 self paced courses covering everything from everyday Claude usage to building agents with the Model Context Protocol. Every course is free, requires only an email sign up, and is built directly by the team behind Claude rather than a third party reinterpreting the documentation. The challenge most learners run into is not access, since the catalog is open to anyone, but direction, since 21 course titles do not automatically translate into a plan. This guide breaks the catalog into four practical tracks [...]

Claude Skills Unlocked: A Practical Guide to Anthropic Academy’s 21 Free Courses2026-07-31T10:22:44+00:00

Automating Publications with Claude, Canva, and n8n

2026-07-29T12:50:19+00:00

Every business that runs a social media page knows the same repetitive cycle. Pick a topic. Write a caption. Design a graphic. Post it on schedule. Repeat tomorrow. Multiply that by every campaign, every seasonal push, every recurring content series, and it becomes a real operational cost, not just a marketing task. That repetitive cycle is exactly what a project called Automating Publications was built to solve. It is a working, experimental content pipeline built with Claude, Canva, Slack, Google Drive, and n8n, and it is a useful reference for any business or enterprise team thinking about applying AI to [...]

Automating Publications with Claude, Canva, and n8n2026-07-29T12:50:19+00:00

AI Ethics Explained: How to Use Artificial Intelligence Responsibly

2026-07-25T14:10:52+00:00

Have you ever used ChatGPT to help explain a difficult topic? Maybe you've asked Gemini to summarize a lengthy article, generate ideas for a school project, write an email, or even use Claude for brainstorming concepts. If you're a student, you've probably wondered: "Is it okay to use AI for assignments?" If you're a content creator, perhaps you've asked yourself at least once: "Who actually owns AI-generated content?" Or maybe you've come across AI-generated images and videos on social media posts and thought: "How can I tell if this is real or AI?" These questions have become increasingly common because [...]

AI Ethics Explained: How to Use Artificial Intelligence Responsibly2026-07-25T14:10:52+00:00

Fine-tuning an LLM for natural Tagalog speech

2026-07-16T10:40:33+00:00

If you're an ML engineer or a technical lead planning to pre-train a large language model (LLM) for Tagalog or Taglish, how do you start? In this article, we walk through the process of defining a target voice, building a data pipeline, running a QLoRA training experiment, and evaluating results with native speakers, so a team can test the idea with a small, well-scoped proof of concept before committing to a larger build.  Why natural Tagalog is harder than correct Tagalog for LLM A general-purpose LLM may produce Tagalog that is grammatically acceptable yet still sound overly formal, translated, or [...]

Fine-tuning an LLM for natural Tagalog speech2026-07-16T10:40:33+00:00

Building Diffender: A Serverless AI Security Reviewer for GitHub Pull Requests with Amazon Bedrock

2026-07-13T20:55:30+00:00

A pull request can pass its tests, satisfy its acceptance criteria, and still expose a production credential in one line of code. Diffender is an Amazon Bedrock pull request reviewer built to identify that kind of risk before the change reaches the main branch. However, human review remains essential, and its depth can vary with workload, time pressure, and security experience. Meanwhile, deterministic scanners provide valuable coverage, although their findings are not always presented in a form that developers can immediately understand and act on. Diffender adds another layer to that review process. It is a serverless GitHub bot that [...]

Building Diffender: A Serverless AI Security Reviewer for GitHub Pull Requests with Amazon Bedrock2026-07-13T20:55:30+00:00

Everything You Need to Know About Harness Engineering

2026-07-13T20:21:29+00:00

AI agents can now write code, browse the web, and run for hours without a human watching. Ask one to build a feature, and it might open ten files and call five tools. It can make a hundred small decisions before it ever shows you a result. That is a different animal from a chatbot answering one question. In my experience following this shift, it also breaks the old playbook for controlling AI behavior. For a while, prompt engineering was the go-to answer. Write a clearer instruction, add a few examples, and the model behaves. That still works for single-turn [...]

Everything You Need to Know About Harness Engineering2026-07-13T20:21:29+00:00

Should the Philippines Make Its Own Local Large Language Model?

2026-07-08T05:21:18+00:00

  As countries all around the world are beginning to invest in their own large language models, the same question keeps coming up in Philippine tech circles: should the country build one, too? If we do, would it be cost-effective? And if it is, would it be beneficial? As an early-career professional, I have heard these questions before, whether we are talking about sovereignty, independence, or simply having something to be proud of. Some people in our industry keep asking that question, and more often than not, in that same instance, the reality of creating one always surfaces. First, it [...]

Should the Philippines Make Its Own Local Large Language Model?2026-07-08T05:21:18+00:00

UI/UX Design: Speeding Up the Creative Process with AI

2026-07-13T20:17:29+00:00

If you have ever stared at a blank Figma canvas with a deadline looming, whether that is a thesis defense, a hackathon demo, or a personal app you finally want to ship. You already know that speed matters as much as polish. A traditional UI/UX workflow covers research, wireframing, high-fidelity mockups, and developer handoff, which can take weeks in a normal product cycle. Most people building on a deadline simply do not have weeks to spare. Students finishing a thesis MVP, hackathon participants racing the clock, and hobbyists building for fun on a weekend all share the same goal: getting [...]

UI/UX Design: Speeding Up the Creative Process with AI2026-07-13T20:17:29+00:00

Agentjacking: How Fake Sentry Errors Hijack AI Coding Agents

2026-06-28T15:46:35+00:00

AI coding agents like Claude Code, Cursor, and Codex now do far more than autocomplete. They read source code, query observability platforms, open pull requests, and run terminal commands on developer machines. That expanded access is useful, but it also creates a problem most security teams have not accounted for: when an agent reads data from an external tool, it often treats that data as trustworthy. A new attack class called agentjacking takes advantage of exactly this assumption. Researchers at Tenet Security documented the technique in June 2026. It tricks AI coding agents into executing attacker-controlled code by hiding instructions [...]

Agentjacking: How Fake Sentry Errors Hijack AI Coding Agents2026-06-28T15:46:35+00:00

AWS, Azure, and GCP Certifications are consistently among the top-paying IT certifications in the world, considering that most companies have now shifted to the cloud. Upskill and earn over $150,000 per year with an AWS, Azure, or GCP certification!

Follow us on LinkedIn, Facebook, or join our Slack study group. More importantly, answer as many practice exams as you can to help increase your chances of passing your certification exams on your first try!