This is a post about how to use AI to make yourself smarter - not dumber.

Tools: How AI Agents Get Real Work Done

Now that we’ve covered AI agents in general, and prompts and LLMs specifically, let’s move on to tools.

We spent three months testing two AI coding assistants across our team of six. So far we’ve learned that overdelegation backfires, well-scoped tasks help, and accelerating an individual ≠ accelerating a team.

Now that we’ve covered agents at a high level and prompts specifically, let’s move to the next component in our series: Large Language Models (LLMs), a key subset of generative AI. In an agentic framework, LLMs serve as the “brain” or …

AI agents have the ability to complete tasks autonomously, but without clear, well-structured prompts, they stumble. Prompt engineering helps bridge the gap between potential and performance.

While not always rational (or even helpful) our intuition fundamentally shapes how we think. In this post, summer intern Julie illustrates how she uses statistics to keep her analyses grounded, and how that translates to business value.

AI agents represent a significant opportunity for businesses, provided they’re designed for real business impact. This potential has become especially viable as cost-efficient reasoning models become increasingly accessible. While …

There’s no “best AI model for all use cases.” You have to do the science each time. If you’re new to experimental design for AI/ML, here’s a quick and dirty intro to the Model Selection Triple methodology.

While the internet is an endless source of free data, everyone is training on the same tired datasets, and they’ve likely got more years of practice. Building a novel dataset tailored to your problem can be a game-changer (if done right).

AI is rapidly transforming the workplace, but don’t be fooled into thinking it’s as simple as replacing workers. If you want to stay ahead of the curve, try a human-centered approach.

Data scientists often struggle to deliver impact in production because they work in notebooks, outside the application stack. Could GenAI tools for UI creation help solve the low ROI problem in data science?

Workplace AI adoption can be hindered by unexpected human factors, including employee shame. In this post, an AI expert recounts real-world examples of overcoming these barriers to unlock a virtuous cycle of human-centered innovation.