All Posts

For CTOs and tech leads, the best framework for building AI agents might not be a SaaS product—it might be a state machine your team builds in-house.

Understand the crucial differences between client-side and server-side tool integration for Large Language Models. This guide explains how to leverage these patterns effectively, often achieving results superior to complex agentic frameworks.

Proactive chatbots set the stage for success. They reveal their capabilities upfront, guiding users towards successful outcomes, and are essential for effective chatbot design.

Cut through the LLM hype! Learn the 4 practical ways to use AI in chatbots: extraction, classification, transformation, and generation. Understand their strengths and risks for building better conversational apps.

Function calls are the unsung hero of LLM UI manipulations. While OpenAI has made great strides leveraging function calls to manipulate the UI in their demos, the rest of industry is yet to take its first meaningful steps. But what do those steps look like?

Facing the tough ‘build vs buy’ choice for your chatbot platform? This post breaks down when custom development is a strategic advantage versus when buying a solution saves time and resources.

From full creative freedom to strict fact matching, organizations can design chatbots that meet their specific risk tolerance and communication needs. The key is choosing an approach that serves the user while protecting the brand.

Ensuring proper communication is critical — don’t let a chatbot fail to chat! Bots must strike a balance between confirming user information and proceeding with a reasonable assumption of correctness. Explicit and implicit confirmations are the primary tools to achieve this balance.

Like any software project, building a chatbot requires careful planning. While all software projects fall along the Waterfall-Agile spectrum. I believe chatbot projects should lean closer to the Agile end, emphasizing rapid prototyping and iteration over extensive upfront planning. This post draws on my experience with numerous chatbot projects and outlines what successful teams have done at the start.

Most chatbots stick to one modality—either text or voice. But as someone who uses subtitles for everything, I wonder why voice bots don’t also include text for accessibility. Is it a limitation in the voice tech stack? Does text clutter the UI? To find out, I decided to build my own streaming-first chatbot interface with both text and voice.

Think developers are the key to chatbot success? Think again! This guide breaks down the essential entire team you need, from execs to QA, for a winning project.

You never get a second chance to make a first impression. Chatbots are no different, and the first interaction with users sets the tone for the entire user experience. When crafting this initial message, I recommend to keep the 3 C’s in mind.

Ever heard NixOS has a steep learning curve? Follow my painful (but funny) 9-attempt saga installing it, battling complex configs, Nvidia drivers, partitioning woes, and my own mistakes to finally reach Hyprland.

Think chatbots replace all web UIs? Not so fast. Explore the strengths of buttons, forms & tables in e-commerce (Apple, Taylor Stitch examples) vs chatbots and see where each truly fits.

Worried about AI lies? Build trust in your AI! This post explores how to measure truthfulness using ‘Correctness’ vs. ‘Faithfulness’ metrics, turning abstract trust into concrete data.

What’s the best way to take notes at an AI conference? Making memes, obviously! A humorous look at key takeaways from the AI Engineer Summit 2023 on LLMs, agents, evals, RAG, and conference life.

The Tiny Retriever vs OpenAI RAG showdown! Did the fine-tuned underdog beat the champ? See the nDCG results, the tech stack (GPL, SBERT), and why losing isn’t the end.

While my model is training, let’s take a moment to pause and reflect on the process so far, its thorns and roses, and make a few more Bert puns while we’re at it!

What makes a good retriever for RAG? Join me on a journey from classic BM25 to the world of BERT, DistilBERT, fine-tuning tricks like GPL, and why these ‘smaller’ models still punch above their weight.

Why use giant LLMs for RAG? This post kicks off a mission to build a tiny, specialized information retriever using BERT, aiming for better performance on niche/non-English data, faster speeds, and no GPU required!

Taylor v0.1 is live! Check out the first release of this AI junior developer agent on Github. Learn about the struggles (Github auth, APIs, TS/ESLint) and triumphs (Langchain agents, prompts) of this project.

Inspired by Minecraft’s Voyager, this post lays out the vision for ‘Taylor’ - an autonomous AI junior developer. Explore the goals, constraints, tech stack, and process ideas for automating dev tasks with Langchain.

NVIDIA’s Voyager agent showed impressive long-horizon planning in Minecraft. This post breaks down its six key components, GPT-4 powered action loop, and analyzes whether its parts are truly ‘agents’ or just ‘chains’.

Curious about AI agents automating software development? This post explains what they are, how they differ from chatbots, and lists popular open-source projects like GPT Engineer, AIder, and Webapp Factory you can explore.