I Trained Six Models for Fraud Detection, and the Best One Isn’t in Production
What a final-year project taught me about the gap between evaluation metrics and production decisions The post I Trained Six…
Category: General
Agentic AI Is Rewriting The Analytics Stack But There’s One Skill It Still Can’t Touch
As AI handles more of the execution, what work should belong to agents vs humans and why does that distinction…
How to Work with AI Coding Agents
A practical guide to getting better code, not just more code The post How to Work with AI Coding Agents…
Piloting the world’s first double-blind AI evaluations
Piloting the world’s first double-blind AI evaluations
The Operating Layer: Memory, Skills, Todos, Voice, Channels, and the Approval Boundary
The operating layer: human oversight over memory, skills, todos, voice, channels, and the approval boundary. Photo via Unsplash (Unsplash License).…
Intelligent transcription with Gemini 3.5 Transcribe
Now you can get more intelligent speech-to-text transcription with Gemini 3.5 Transcribe.
How Does a RAG Reranker Really Work?
Enterprise Document Intelligence [Vol.1 #2D] – What data scientists say when asked, what the model actually does under the hood,…
AI helps design new materials that work in the real world
Today, anyone with a large enough artificial intelligence model can generate millions of new material designs in minutes. Unfortunately, that…
Why Random Forest Needs to Be This Random
Bagging hits a wall no amount of trees can break — here’s the equation that explains why, and the experiment…
Is Agentic AI Just Automation?
Why most agents are just flowcharts in disguise, and what to build instead. The post Is Agentic AI Just Automation?…
How to Format Your TDS Draft: A New and Improved Guide
Everything you need to know about creating a draft on our Contributor Portal The post How to Format Your TDS…
A New Towards Data Science: A Faster Site and a Brand-New Contributor Portal
We’re excited to share some big news: We completely rebuilt the TDS website and our contributor portal. Whether you come…
I Deployed My Data Pipeline to AWS. Then Everything That Was “Local” Broke.
What moving a Dockerized pipeline off my laptop taught me about containers, networking, and hidden assumptions. The post I Deployed…
One Document Type, a Million Files: Structured Extraction into the SQL Table RAG Queries
Enterprise Document Intelligence [Vol.1 #14C] – One hour with two people, six to ten fields, and the two signals that…
From AI Experiments to AI Operations: Why I Stopped Playing with Agents and Started Building a System
From experiments to operations: a calm, organized workspace where AI becomes a real system. Photo via Unsplash (Unsplash License). Hermes…
Put Your Own Logic Inside the Codex Agentic Loop
Understanding Codex hooks The post Put Your Own Logic Inside the Codex Agentic Loop appeared first on Towards Data Science.
Generating scenarios for extreme events, without extreme data
Can a city’s seawall stand up to a blockbuster storm? Will a region’s power grid hold against record-breaking heat? And…
10 Positions for Enterprise RAG That Mainstream Tutorials Get Wrong
Enterprise Document Intelligence [Vol.1 #M3] – The ten positions the series argues from, and the map of every article that…
Speculative Decoding on CPUs: Nearly 4x Faster Token Generation with DFlash
Speculative decoding can turn underused CPU compute into faster token generation, without changing the model’s output. In our vLLM tests,…
AI Agents Don’t Need More Context — They Need Typed Context
AI agents don’t just have a context problem—they have a context typing problem. When instructions, memory, retrieved evidence, and tool…
Survival Analysis and the Cox Proportional Hazards Model: A Beginner-Friendly Guide
From Kaplan-Meier curves to hazard ratios with runnable Python Code throughout The post Survival Analysis and the Cox Proportional Hazards…
Parse the Folder, Not Just the PDFs: The Relational Tables RAG Needs on a Case File
Enterprise Document Intelligence [Vol.1 #14D] – The index lists what the case type demands before any folder is opened, and…
Bug Detection Blind Spots in AI Coding Harnesses (GStack and Beyond)
28 debugging experiments reveal that AI struggles less with complexity than with missing information. The post Bug Detection Blind Spots…
Building a Proper Backend for My LangGraph AI Agent
Turning a demo agent into something that can keep real booking data The post Building a Proper Backend for My…
Multi-Document RAG: A Folder of Unrelated PDFs Is One Long Document with a Nested Outline
Enterprise Document Intelligence [Vol.1 #14B] – No shared fields means no index to build. One summary line per file plus…
Why We Fine-Tuned SigLip (And Why That’s Not Always the Right Call)
LoRA fine-tuning solved our under-labeling problem. Whether it makes sense for you depends on three questions. The post Why We…
Running Codex as a Headless Agent
Turning Codex from an interactive assistant into a programmable automation component The post Running Codex as a Headless Agent appeared…
Estimating from No Data: Deriving a Continuous Score from Categories
A walkthrough of and the maths behind using low-capacity networks to acquire fine-grained scoring when only categorical labelling is available…
The Types of Dimensions in a Star Schema, and How to Use Them
Dimensions are one of the two main object types in dimensional modelling. But what are the different types of dimensions?…
Bayesian Guardrails for AI Decisions: Measuring Uncertainty Before Automating Decisions
AI systems should not automate a decision simply because they can provide a prediction. A decision system should consider how…
How Benders Decomposition Works, Part II: Feasibility Cuts
Learning about Farkas’ lemma and how it can inform Benders decomposition to learn from infeasibility, applied to the capacitated facility…
From Atari to EVE Online: Building on 15 Years of AI Research in Games
Google DeepMind partners with game studios to prototype breakthrough AI gameplay.
Paving the way for greener ammonia production
Ammonia is one of the most important chemicals produced in the world, ranking second only to sulfuric acid in the…
How to Effectively Align Your Intent with Claude Code
Improve your proficiency with Claude Code. The post How to Effectively Align Your Intent with Claude Code appeared first on…
The LLM Judge That Kept Agreeing With Itself
What a production incident taught me about trusting a model to judge another model’s work The post The LLM Judge…
Three Kinds of RAG Corpus, and What It Costs to Build for the Wrong One
Enterprise Document Intelligence [Vol.1 #14A] – Three questions tell you which shape a document collection has, and each shape wants…
How to Fine-Tune an LLM: An End-to-End Guide
A hands-on guide to fine-tuning LLMs for the real world The post How to Fine-Tune an LLM: An End-to-End Guide…
Making the Knowledge Layer a Graph You Actually Traverse
Why retrieval quality should be a property of the system, not of the question’s wording? Rebuilding knowledge layer with graph…
How to Scale an Integration Pipeline Without Breaking Correctness
A production account of scaling an enterprise integration pipeline from 500 to 8,000 events per second, and the two correctness…
Kimi K3’s 1M Token Context Window vs. RAG: Cost, Latency and Answer Quality
A controlled comparison of a top-5 RAG pipeline and a full 127,000 token prompt on the same 12 questions, same…
Understanding Anti-AI Public Opinion
People can accept tradeoffs when they see value — but if they don’t, what happens? The post Understanding Anti-AI Public…
Jigsaw Jeeves: Building a Puzzle Assistant using Computer Vision
Conceptual overview and walkthrough of a solution approach in Python The post Jigsaw Jeeves: Building a Puzzle Assistant using Computer…
From Prototype to Production: The Architecture Behind Secure & Governed AI Agents
Building the Responsible AI, security, and governance layers required for enterprise-ready agents The post From Prototype to Production: The Architecture…
When AI art has no author: Study finds generated images often can’t be traced to training data
When an artificial intelligence image generator produces a portrait, whose work went into it? The question sits at the center…
Building Enterprise Agent Systems that People can Trust, Verify and Improve
5 principles that determine whether an agent system succeeds in production, explained through one I built for a $100M+ company. The…
Q&A: Rethinking how innovation happens
Innovation is a concept that has become mythologized in the modern era: what it is, how to manage it, how…
Ten Is Not a Hundred
The number that fooled every hallucination detector The post Ten Is Not a Hundred appeared first on Towards Data Science.
Q&A: Rethinking how innovation happens
Innovation is a concept that has become mythologized in the modern era: what it is, how to manage it, how…
Webwright: Why AI Web Agents Should Write Code, Not Click
For years, web agents have worked one click at a time—and often fallen apart on long tasks. Microsoft Research’s Webwright…