February 2026

Agentic AI in Payments: Balancing Autonomy and Risk

⋅

Imagine: You are standing in the checkout line with your credit card in hand after buying groceries and the terminal flashes red and says “Card declined”. You try again and still the same result. You are embarrassed at this point, so you pull out another card. You know you have got plenty of money in your account, but an AI agent somewhere thinks otherwise. Or worse, it thinks you are doing fraud, so it didn’t approve any of […]

Ver mais

Liked Liked

Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimization

⋅

Active data acquisition is central to many learning and optimization tasks in deep neural networks, yet remains challenging because most approaches rely on predictive uncertainty estimates that are difficult to obtain reliably. To this end, we propose Goal-Oriented Influence- Maximizing Data Acquisition (GOIMDA), an active acquisition algorithm that avoids explicit posterior inference while remaining uncertainty-aware through inverse curvature. GOIMDA selects inputs by maximizing their expected influence on a user-specified goal functional, such as test loss, predictive entropy, or […]

Ver mais

Liked Liked

Red/green TDD

⋅

Agentic Engineering Patterns > “Use red/green TDD” is a pleasingly succinct way to get better results out of a coding agent. TDD stands for Test Driven Development. It’s a programming style where you ensure every piece of code you write is accompanied by automated tests that demonstrate the code works. The most disciplined form of TDD is test-first development. You write the automated tests first, confirm that they fail, then iterate on the implementation until the tests pass. […]

Ver mais

Liked Liked

The Sample Complexity of Replicable Realizable PAC Learning

⋅

In this paper, we consider the problem of replicable realizable PAC learning. We construct a particularly hard learning problem and show a sample complexity lower bound with a close to $(log|H|)^{3/2}$ dependence on the size of the hypothesis class $H$. Our proof uses several novel techniques and works by defining a particular Cayley graph associated with $H$ and analyzing a suitable random walk on this graph by examining the spectral properties of its adjacency matrix. Furthermore, we show […]

Ver mais

Liked Liked
I Built an AI That Fixes Pipeline Failures Before Platform or DevSecOps teams Gets the Slack…

I Built an AI That Fixes Pipeline Failures Before Platform or DevSecOps teams Gets the Slack…

⋅

🤖 I Built an AI That Fixes Pipeline Failures Before Platform or DevSecOps teams Gets the Slack Message 📉 The Slack Notification That’s Crushing Your Sprint Velocity “Hey, the pipeline failed again. Can you check?” Whether it’s 2 AM production calls or during business hours, your phone buzzes. You squint at Slack — another developer hasn’t even *looked* at the error logs. They just pinged you. Again. Meanwhile, your actual engineering tasks? Delayed. Your sprint commitments? Slipping. Sound familiar? If you’re on a […]

Ver mais

Liked Liked
Part 2 — How to Build Your Own AI Agent: (Cloud-Agnostic, Fully Automated, Enterprise-Ready)

Part 2 — How to Build Your Own AI Agent: (Cloud-Agnostic, Fully Automated, Enterprise-Ready)

⋅

From natural-language prompts → to Terraform module → to PR → to CI/CD → to validation Most AI content explains concepts.This guide helps you build something real — a fully functioning AI agent that: Understands natural-language infrastructure requests Generates complete Terraform modules (multi-file) Enforces strict enterprise standards Auto-fixes issues via LLM reasoning Creates a GitHub branch Commits all files Opens a pull request Triggers GitHub Actions Runs unit tests Runs Terraform init + validate + plan Works in any cloud (AWS, Azure, GCP, etc.) Works in any pipeline […]

Ver mais

Liked Liked
Explain Linear Regression to Me Like I am a 5-Year-Old

Explain Linear Regression to Me Like I am a 5-Year-Old

⋅

Source: Image generated by ChatGPT5.2 Hello everyone, this blog is part of a series of blogs I am preparing called “explain Machine learning Concept X to me like a 5 year old”. As I was once told “you don’t truly understand a concept until you can explain it simple enough a 5 year old can understand it”. This is my personal take to refresh on basic machine learning concepts in a general manner, and is meant in no […]

Ver mais

Liked Liked
Mastering the Machine: An Expert Guide to Prompt Engineering

Mastering the Machine: An Expert Guide to Prompt Engineering

⋅

In the high-stakes landscape of 2026, the competitive advantage of an organization no longer rests solely on its access to data, but on the precision of its communication with the intelligence systems processing that data. We have entered the era of the “Autonomous Frontier,” where AI has transitioned from a passive search tool to an active agent capable of executing complex business workflows. However, as AI gains agency, the margin for error narrows. A poorly structured instruction is […]

Ver mais

Liked Liked
Vectors, Embeddings, and Search: An Intuition-First Guide

Vectors, Embeddings, and Search: An Intuition-First Guide

⋅

https://nicolas.nz/blog/vectors-embeddings-and-search Vectors, embeddings, and search When we talk about AI, search, or LLMs, it often sounds like magic. You type words. Something understands them. It finds meaning, not just keywords. But under the hood, there’s no magic. There are vectors. Lots of them. Not symbols, not rules, not hidden dictionaries. Just numbers arranged in space. When I built my previous blog, I used vectors to power article recommendations (surfacing related content based on what you’d just read). I never really went […]

Ver mais

Liked Liked

How Does the Discount Factor γ Change the Optimal Policy?

⋅

In a simple gridworld example, everything stays the same except the discount factor γ. Reward for boundary/forbidden: -1 Reward for target: +1 Only γ changes Case 1: γ = 0.9 The agent is long-term oriented. Future rewards are discounted slowly: γ⁵ ≈ 0.59 So even if the agent takes a -1 penalty now (entering a forbidden area), the future reward is still valuable enough to justify it. Result: The optimal policy is willing to take short-term losses to […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2026