Blog

AI & LLMs

Articles on AI agents, LLM engineering, and applied machine learning — prompt design, RAG, evaluation, and building production AI features.

29 articles

July 20269 min read

Building a Streaming Chatbot with Groq and Next.js

Ship a fast streaming chatbot with the Groq API and Next.js route handlers, covering system prompts, rate limiting, and cost control.

July 202610 min read

Document Data Extraction with Multimodal LLMs

How to turn invoices, contracts, and scanned forms into reliable structured data using multimodal LLMs, from prompt design to human-in-the-loop review.

July 20269 min read

Semantic Caching for LLMs: Cut Cost on Repeat Questions

Most chatbot traffic is the same handful of questions worded differently. Semantic caching catches those near-duplicates and skips the model call entirely.

July 202611 min read

Building Agents with the Claude Agent SDK

A practitioner's walkthrough of the Claude Agent SDK: the agent loop, tool definitions, subagents, permission modes, and what it actually takes to ship a production coding or ops agent.

July 202610 min read

LLM Evals in CI: Testing Prompts Like Code

A prompt change that looks harmless in a chat playground can quietly break a production feature. Here is how to build an evaluation harness that catches that regression before it merges.

July 20269 min read

LLM Structured Output: JSON Schema That Actually Validates

Prompting an LLM to return JSON is not the same as guaranteeing it. Here is how JSON Schema constraints, tool-based calling, and Zod validation turn probabilistic output into something you can trust in production.

June 202611 min read

Claude Fable 5: What Developers Need to Know

Claude Fable 5 is Anthropic's new Mythos-class model. Here is the pricing math, the API migration gotchas, and who should actually use it over Opus.

May 202610 min read

AI Agents in Production: Lessons from a Year of Agentic Workflows

Tool design, guardrails, and eval loops: the unglamorous lessons from running AI agents in production and using agentic coding tools every day.

April 20269 min read

MCP Explained: What the Model Context Protocol Actually Solves

MCP is the USB-C of AI integrations: one protocol between models and your systems. What servers and clients are, and when building one makes sense.

April 20267 min read

How I Combine Opus 4.7 and Sonnet 4.6 in Claude Code

My practical workflow: use Opus 4.7 for critical planning and Sonnet 4.6 for cost-efficient execution loops.

April 20269 min read

LLM Prompt Caching: The Cheapest Cost Optimization You Are Not Using

Prompt caching cuts LLM input costs by up to 90 percent. How caching economics differ across Anthropic, OpenAI, and Gemini, and how to architect prompts for it.

May 202612 min read

Hermes AI Agent by Nous Research: Architecture, Self-Learning Loop, and Getting Started

A deep dive into Hermes — the open-source AI agent framework with a closed self-learning loop, persistent memory, 40+ tools, and multi-platform deployment via a single gateway.

May 202611 min read

MCP Authorization with Cerbos: Policy-as-Code for AI Agents

How to use Cerbos's open-source policy engine to control which tools your MCP server exposes per user role — without hard-coding ACLs.

March 202510 min read

How I Cut My LLM API Bill by 60% Without Touching Model Quality

Practical strategies for reducing LLM API costs in production — from prompt caching to model routing — with real numbers from my AI Gymbro project.

June 202511 min read

AI Agent Workflow Automation in 2025: What Actually Works

A practical guide to building reliable AI agent workflows — the patterns that work in production and the pitfalls that will waste your time.

August 202512 min read

RAG Pipeline Production Lessons: What Nobody Tells You

Hard-won lessons from building production RAG systems — indexing strategy, chunking failures, retrieval quality, and the metrics that actually matter.

October 202510 min read

Claude API Tool Use in Production: A Real-World Guide

Everything I learned shipping Claude's tool use (function calling) in production — schema design, error handling, streaming, and cost management.

December 202511 min read

OpenAI vs Anthropic vs Google Gemini: A Developer's Honest Comparison (2025)

A practical comparison of the three major LLM APIs from a developer who has used all three in production — pricing, DX, reliability, and when to use each.

January 202610 min read

LangChain vs Building Your Own LLM Orchestration: When to Use Each

An honest assessment of LangChain in 2025 — when it saves time, when it gets in the way, and how to decide if you need it at all.

February 20269 min read

AI-Powered Code Review with GitHub Actions: My Setup

How to add AI code review to your GitHub PR workflow — tool choices, prompt engineering, cost management, and what AI actually catches vs. misses.

March 202611 min read

pgvector vs Pinecone vs Qdrant: Choosing Your Vector Database in 2025

A practical comparison of the top vector database options — performance benchmarks, pricing, and which one to choose for your specific use case.

April 202610 min read

Prompt Engineering for Production: Beyond the Basics

Production prompt engineering is different from tutorial prompt engineering — version control, testing, regression prevention, and the patterns that actually improve reliability.

May 20269 min read

AI Content Generation Quality Control: What I Learned the Hard Way

Using AI to generate content at scale without sacrificing quality — the review workflows, quality signals, and failure modes you need to know about.

March 202510 min read

Prompt Injection Defense: How I Harden AI Systems Against Manipulation

Real prompt injection attack patterns, OWASP LLM Top 10 defenses, and practical controls I implement when building AI-powered APIs and agents.

June 202511 min read

Building an MCP Server from Scratch: A Practical Developer Guide

Step-by-step guide to building a Model Context Protocol server with real tools, authentication, and production deployment — using the official TypeScript SDK.

August 202510 min read

AI Agent Memory Persistence Patterns: From Volatile to Long-Term

How to implement memory for AI agents — covering in-context, external vector store, and structured database patterns with real trade-offs from production deployments.

November 202510 min read

Running Local LLMs with Ollama in Production: What I Learned

A practical guide to deploying Ollama for production local LLM inference — covering model selection, hardware requirements, API integration, and when local beats cloud.

January 202611 min read

AI Observability: How to Log, Trace, and Monitor LLM Applications

Production LLM observability with Langfuse, token cost tracking, latency monitoring, and anomaly detection — lessons from running AI-powered ERP integrations.

March 202610 min read

Function Calling Patterns: OpenAI vs Anthropic Tool Use in Production

Compare OpenAI function calling and Anthropic tool use APIs — with real patterns for parallel calls, error handling, retry logic, and structured output extraction.

Back to all posts