AI Tools & Frameworks Directory

These ares seven unconventional uses of LLMs that go far beyond usual chat interface and conversations.

The idea of building your own AI agent used to feel like something only big tech companies could pull off.

Turning free-to-use data into a hypothesis-ready dataset The post Using Causal Inference to Estimate the Impact of Tube Strikes on Cycling Usage in London appeared first on Towards Data Science.

How I turned LLM persona interviews into a repeatable customer research workflow The post From Ad Hoc Prompting to Repeatable AI Workflows with Claude Code Skills appeared first on Towards Data Science.

Design has traditionally required multiple roles working in sequence: a strategist to define the problem, a designer to shape the solution, and a developer to build it. This means coordinating timelines, aligning opinions, and going through rounds of iteration before anything tangible is created. Cl...

Learn faster, build smarter, and unlock the full power of Claude Code through real examples, reusable templates, prompts, workflows, subagents, and system design.

FastAPI has become one of the most popular ways to serve machine learning models because it is lightweight, fast, and easy to use.

How you can build your own Thompson Sampling Algorithm object in Python and apply it to a hypothetical yet real-life example The post DIY AI & ML: Solving The Multi-Armed Bandit Problem with Thompson Sampling appeared first on Towards Data Science.

A stateless AI agent has no memory of previous calls.

As memory grows in RAG systems, accuracy quietly drops while confidence rises — creating a failure that most monitoring systems never detect. This article walks through a reproducible experiment showing why this happens and how a simple memory architecture fix restores reliability. The post Your RAG...

Conceptual overview and practical guidance The post Context Payload Optimization for ICL-Based Tabular Foundation Models appeared first on Towards Data Science.

Merge LLMs easily with Unsloth Studio's no-code GUI and combine models without retraining.

Why it tickles your brain to use an LLM, and what that means for the AI industry The post The LLM Gamble appeared first on Towards Data Science.

AI voice generation has a major problem. It works like a robot, reading a script phrase by phrase, with no feelings or emotions. It might be clever, but it matters less if there is no human feeling attached to it. The way the AI generates its voice makes it hard to feel like you’re having […] The po...

Explore five beginner-friendly platforms that let you host Python apps for free, compare their limits, and pick the right one.

Open source. 5-minute setup. Vector RAG done right—try it yourself. The post Proxy-Pointer RAG: Structure Meets Scale at 100% Accuracy with Smarter Retrieval appeared first on Towards Data Science.

Explore the end-to-end pipeline of TurboQuant, a novel KV cache quantization framework. This overview breaks down how multi-stage compression achieves near-lossless storage through PolarQuant and QJL residuals, enabling massive context windows with minimal memory overhead The post KV Cache Is Eating...

Git worktrees, parallel agentic coding sessions, and the setup tax you should be aware of The post AI Agents Need Their Own Desk, and Git Worktrees Give Them One appeared first on Towards Data Science.

How I turned my eight-year weekly visualization habit into a reusable AI workflow The post Beyond Prompting: Using Agent Skills in Data Science appeared first on Towards Data Science.

What if an unsupervised model could become a strong classifier with only a handful of labels? The post You Don’t Need Many Labels to Learn appeared first on Towards Data Science.

Build an AI customer sentiment analyzer for call recordings using Whisper, BERTopic & Streamlit with this open-source step-by-step guide with code.

Artificial intelligence is rapidly developing. The minute we become accustomed to one breakthrough, another comes to shift our expectations. The new model, Claude Opus 4.7, that Anthropic introduced recently, is one such shift. The release tends to go beyond mere AI chatbots and makes AI a trusted, ...

The question around AI, and I mean the pinnacle of AI, not your regular “write me an email”, is shifting. What used to be “what can it do for me?” has now become “who gets to use it?” We saw this recently with Anthropic’s Claude Mythos Preview – a supposed epitome of AI models that […] The post Open...

The upstream decision no model, or LLM can fix once you get it wrong The post Your Chunks Failed Your RAG in Production appeared first on Towards Data Science.