

intent-kit v0.7.0: Context That Works, DAGs That Scale
Stephen Collins
•
Aug 14, 2025
4 mins
With v0.7.0, intent-kit's context system is faster, clearer, and more reliable—and it runs on a DAG-based architecture that m...
Read More


intent-kit v0.5.0: Why I Hit Pause on Multi-Intent (and Why You Should Sometimes, Too)
Stephen Collins
•
Aug 4, 2025
3 mins
For intent-kit v0.5.0, I made a counterintuitive move: I removed multi-intent workflows—not forever, but for now. Here's why ...
Read More


Intent Graphs: Protocol-Driven Automation for the LLM Era
Stephen Collins
•
Jul 27, 2025
5 mins
Imperative code falls apart when you try to automate with LLMs. Intent graphs are the antidote—protocol-driven, inspectable, ...
Read More


intent-kit v0.4.0: Lessons in Reliable, Testable LLM Workflow Engineering
Stephen Collins
•
Jul 25, 2025
2 mins
The latest release of intent-kit is packed with practical engineering improvements—environment-based configuration, performan...
Read More


Why I Don't Like Imperative Code (And What I Prefer Instead, Especially with MCP)
Stephen Collins
•
Jul 25, 2025
5 mins
Imperative code isn't just a personal pain point—it's a roadblock in the era of LLM-powered automation. As the world shifts t...
Read More


Introducing intent-kit: Universal, Deterministic Intent Workflows for Python
Stephen Collins
•
Jul 9, 2025
2 mins
Building reliable LLM-powered automation shouldn't mean reinventing the wheel. intent-kit gives you a universal Python framew...
Read More


Introducing ts-validator: Static Analysis for Runtime Validation in TypeScript APIs with Rust
Stephen Collins
•
Apr 27, 2025
1 min
TypeScript types disappear at runtime, leaving APIs vulnerable to unvalidated external inputs. This post introduces `ts-valid...
Read More


Track UI Events and Network Activity in macOS Using Rust + SwiftUI
Stephen Collins
•
Apr 12, 2025
4 mins
Want to know exactly what a macOS app does when you click a button—and which network requests it triggers? This tutorial show...
Read More


Track UI Events and Network Activity in Windows Using Rust + C#
Stephen Collins
•
Apr 12, 2025
4 mins
Want to trace exactly what a desktop app is doing—when a button is clicked and what network request it triggers? This tutoria...
Read More


How sqlite-vec Works for Storing and Querying Vector Embeddings
Stephen Collins
•
Mar 31, 2025
5 mins
Most vector search systems require a dedicated service or cloud API—but what if you could run fast, KNN-based vector search d...
Read More


What Are Vector Embeddings? A Beginner's Guide to How LLMs Understand Language
Stephen Collins
•
Mar 25, 2025
4 mins
Vector embeddings are a foundational concept in AI and language models like GPT-4. They translate human language into numbers...
Read More


How to Use sqlite-vec to Store and Query Vector Embeddings
Stephen Collins
•
Mar 4, 2025
9 mins
SQLite has long been valued for its simplicity and efficiency, but with the introduction of `sqlite-vec`, it becomes a powerf...
Read More


I Wasted 2 Years and Thousands on an AI Product No One Wanted—Here's What I Wish I Knew
Stephen Collins
•
Feb 12, 2025
2 mins
Many AI founders assume that if they build a great product, customers will come. I made the same mistake. I spent 2 years and...
Read More


How to Create a Node.js Proxy Server for Hosting the DeepSeek-R1 7B Model
Stephen Collins
•
Jan 24, 2025
6 mins
Hosting large language models like DeepSeek-R1 7B locally can be a game-changer for AI applications. This post guides you thr...
Read More


How to Use PydanticAI with Multimodal LLMs
Stephen Collins
•
Dec 15, 2024
6 mins
Learn how to simplify multimodal workflows with PydanticAI and OpenAI's GPT-4o. This tutorial explores structured outputs, re...
Read More


How to Build Lightweight GraphRAG with SQLite
Stephen Collins
•
Oct 3, 2024
10 mins
Learn how to build a lightweight GraphRAG system using SQLite, offering a portable, serverless solution for document processi...
Read More


How to Scale GraphRAG with Neo4j for Efficient Document Querying
Stephen Collins
•
Sep 7, 2024
16 mins
Learn how to integrate Neo4j with GraphRAG to scale up document processing and query-focused summarization. In this tutorial,...
Read More


Introducing JSON Schemas for AI Data Integrity
Stephen Collins
•
Aug 11, 2024
5 mins
JSON Schemas provide a robust framework for enforcing data structure and integrity in AI-driven applications. This post intro...
Read More


How to Implement a Tree of Thoughts in Python
Stephen Collins
•
Jul 5, 2024
6 mins
Explore the concept of the Tree of Thoughts (ToT) and learn how to implement it in Python. This blog post demonstrates the sy...
Read More


Building a Reliable and Accurate LLM Application with Voting Systems
Stephen Collins
•
Jun 27, 2024
3 mins
Ensuring the reliability and accuracy of LLM-powered applications is crucial in AI development. This post introduces a voting...
Read More


Implementing GraphRAG for Query-Focused Summarization
Stephen Collins
•
May 16, 2024
8 mins
GraphRAG is a novel approach to query-focused summarization, designed to generate comprehensive and diverse answers to global...
Read More


How to Create LCEL Chains in LangChain
Stephen Collins
•
Mar 21, 2024
3 mins
Learn how to use the LangChain Expression Language (LCEL) and LangChain to create chains. This tutorial demonstrates an examp...
Read More


How to Perform OCR with Multi Modal LLMs
Stephen Collins
•
Mar 14, 2024
6 mins
Dive into the integration of multi modal Large Language Models (LLMs) like GPT-4 and Claude 3 with AWS Rekognition for extrac...
Read More


How to Enhance Content with Semantify
Stephen Collins
•
Mar 1, 2024
3 mins
Discover how Semantify, a cutting-edge CLI tool, can transform your MDX blog posts by leveraging Generative AI. This tutorial...
Read More


How to Use Promptfoo for LLM Testing
Stephen Collins
•
Feb 14, 2024
7 mins
Introducing Promptfoo, a new LLM testing CLI tool designed to streamline the process of evaluating and improving language mod...
Read More


Basic Security Practices for SQLite: Safeguarding Your Data
Stephen Collins
•
Feb 2, 2024
8 mins
Learn about essential security measures for SQLite databases, focusing on protecting sensitive data, including vector embeddi...
Read More


Harnessing Semantic Kernel for LLM Integration
Stephen Collins
•
Jan 20, 2024
5 mins
The Semantic Kernel is an open-source SDK that could revolutionize the integration of LLM functionalities into your applicati...
Read More


How to Automate Processes with CrewAI
Stephen Collins
•
Jan 13, 2024
4 mins
Learn how to leverage CrewAI for automating complex processes. This post guides you through the use of AI agents and tasks in...
Read More


How to use Milvus to Store and Query Vector Embeddings
Stephen Collins
•
Jan 6, 2024
3 mins
Dive into the world of vector databases with Milvus, and discover how to use it for advanced vector search in Python. This po...
Read More


Using LlamaIndex for Web Content Indexing and Querying
Stephen Collins
•
Jan 1, 2024
3 mins
Learn about LlamaIndex, a simple, flexible data framework for connecting custom data sources to large language models (LLMs),...
Read More


How to Supercharge Chatbots with Mixtral 8x7B and Vector Search
Stephen Collins
•
Dec 15, 2023
6 mins
Discover how to elevate chatbot intelligence by integrating Mistral AI's 'Mixtral 8x7B' model with vector search technology....
Read More


A Beginner's Guide to SQLite: The Lightweight Database Solution
Stephen Collins
•
Dec 13, 2023
4 mins
Dive into the world of SQLite, an efficient and lightweight database solution ideal for both beginners and experienced develo...
Read More


Empowering OpenAI Assistants with Shell Command Capabilities
Stephen Collins
•
Dec 7, 2023
1 min
Explore the cutting-edge approach of empowering OpenAI Assistants with shell command capabilities, using clipboard operations...
Read More


How to Integrate Neo4j with OpenAI's GPT Assistants
Stephen Collins
•
Dec 1, 2023
3 mins
Learn the step-by-step process of integrating Neo4j graph databases with OpenAI's GPT Assistants to enable GPT Assistants to ...
Read More


How to Build a System of Experts with LLMs
Stephen Collins
•
Nov 21, 2023
6 mins
Step into the world of AI-driven microservices with my tutorial on building a System of Experts powered by OpenAI's GPT-4 as ...
Read More


Enhancing GPT Assistants with Vector Search Tools
Stephen Collins
•
Nov 10, 2023
12 mins
Explaining how to integrate custom vector search tools with GPT Assistants, enabling the AI to deliver contextually nuanced r...
Read More


Enhancing MySQL Searches with Vector Embeddings
Stephen Collins
•
Nov 6, 2023
5 mins
Discover how the `mysql_vss` plugin, integrated with the Annoy library, revolutionizes MySQL search capabilities, enabling yo...
Read More


How to use Weaviate to store and query vector embeddings
Stephen Collins
•
Oct 13, 2023
7 mins
Learn how to use Weaviate, a vector database, with a custom vector embedding model, enabling nuanced semantic searches throug...
Read More


SQLite vs. Chroma: A Comparative Analysis for Managing Vector Embeddings
Stephen Collins
•
Oct 6, 2023
3 mins
Explore and compare SQLite, augmented with the `sqlite-vss` extension, and Chroma, a dedicated vector database, as tools for ...
Read More


How to use Chroma to store and query vector embeddings
Stephen Collins
•
Sep 30, 2023
4 mins
Discover the capabilities of Chroma in managing vector embeddings effectively. This article delivers a comprehensive tutorial...
Read More


Comparing GTE, USE, and Ada Text Embeddings
Stephen Collins
•
Sep 27, 2023
3 mins
Dive deep into the world of text embeddings with a comprehensive comparison of three groundbreaking models: GTE, Universal Se...
Read More


How to use PostgreSQL to store and query vector embeddings
Stephen Collins
•
Sep 24, 2023
11 mins
Uncover the potential of PostgreSQL in handling vector embeddings efficiently. This article provides a step-by-step tutorial ...
Read More


Building a Web Component-Based Chatbot with GPT-3.5-turbo
Stephen Collins
•
Sep 2, 2023
3 mins
Explains how to leverage OpenAI's GPT-3.5-turbo in a custom chatbot interface using web components. Get insights into modular...
Read More


Code Search with Vector Embeddings: A Transformer's Approach
Stephen Collins
•
Aug 25, 2023
6 mins
Discover how vector embeddings can power code search in never before seen ways. This article introduces you to the transforma...
Read More


How to use SQLite to store and query vector embeddings
Stephen Collins
•
Aug 17, 2023
8 mins
Guiding you into the process of creating and storing vector embeddings within a SQLite database using the `sqlite-vss` extens...
Read More


Introduction to Vector Search and Embeddings
Stephen Collins
•
Aug 11, 2023
5 mins
Explore the world of vector search and embeddings through a comprehensive guide. This blog post unveils the underlying princi...
Read More


Crafting Prompt Templates for Code Generation
Stephen Collins
•
Aug 3, 2023
8 mins
Unlock the potential of Large Language Models (LLM) like GPT-4 in generating code through well-crafted prompt templates. Dive...
Read More


How Reactivity works in Solid
Stephen Collins
•
Jul 27, 2023
5 mins
Dive deep into Solid's reactivity model and discover the magic behind the createSignal function. Learn how it differentiates ...
Read More


How to center content with CSS Flexbox and CSS Grid
Stephen Collins
•
Mar 11, 2023
5 mins
Centering content with CSS can be frustrating for developers. With the advent of modern CSS layout models such as CSS Flexbox...
Read More


How to setup a layout with CSS Grid
Stephen Collins
•
Mar 5, 2023
6 mins
In this blog post, we are going to explain how to setup a simple, responsive web layout with CSS Grid and minimal layout CSS....
Read More