Latest writings
Notes on AI agents, Salesforce, automation, micro-SaaS, and engineering.
Building Robust RAG Pipelines: A Deep Dive into LangChain Document Loaders
RAG systems live or die by the quality of their data ingestion. This guide covers how to architect a robust document loading pipeline using LangChain to handle PDFs, CSVs, and Web data effectively.
What Is LangChain? When to Use It and When to Write Your Own Code
What LangChain 1.x actually gives you today (create_agent, middleware, a standard model interface) and a plain framework for deciding between it and your own orchestration code.
Building Your First LLM Chain: A Developer's Guide to Sequential Logic
LLMs are powerful, but they are stateless. To build real applications, you need to connect outputs to inputs. Here is a practical, code-first guide to building your first chain using Python and LCEL.
From Chatbot to Agent: The Engineer's Guide to LLM Memory Systems
Stateless LLMs are just goldfish. To build true agents, you need persistence. We break down memory architectures, implementation patterns, and the hidden pitfalls of context poisoning.
LangChain vs. LlamaIndex vs. Vanilla: The Builder's Stack Selection Matrix
Stop agonizing over the perfect LLM framework. A pragmatic guide comparing LangChain, LlamaIndex, and Vanilla implementations with decision charts and folder structures for shipping production AI apps.
Building a Deep Research Agent: An End-to-End Walkthrough
LLMs are terrible researchers out of the box. In this technical walkthrough, I break down how to build an autonomous research agent that searches the web, verifies sources, and generates structured briefs without hallucinating.
The Engineer’s Guide to Debugging AI Agents: From Hallucinations to Reliable Systems
AI agents are non-deterministic by nature, making traditional debugging useless. Here is my systematic framework for logging, tracing, and fixing agent failures in production.
SalesforceBeyond Einstein: Building a Custom AI Sales Agent in Salesforce
Salesforce's native AI is powerful, but expensive. Here is a technical blueprint for building your own Opportunity Enrichment Agent using Apex, Flow, and external LLMs to automate pre-meeting research.
Building an AI Agent That Writes to Notion: Schema Design & API Logic
Stop pasting LLM outputs manually. Learn how to architect a Notion database schema and build a Python-based agent that autonomously writes, formats, and updates status fields via the Notion API.
Stop Overthinking Vector Databases: A Builder’s Decision Framework
Pinecone, Weaviate, Chroma, pgvector? The options are paralyzing. Here is the pragmatic 3-question framework I use to choose the right Vector DB, complete with a setup guide and cost analysis.
Building Your First RAG Pipeline: A Developer’s Guide to Context-Aware AI
LLMs hallucinate. RAG fixes that. This guide walks through building a retrieval pipeline from scratch, covering ingestion, chunking strategies, and how to evaluate your system.
Create Your First AI Planning Agent in 10 Minutes (n8n Tutorial)
Build a functional AI planning agent that breaks down complex goals into actionable steps using n8n. This step-by-step tutorial includes exact prompts, workflow configuration, and a ready-to-use template.
Building AI Agents from Scratch: A Practical Guide
Build an AI agent in plain Python: a tool-calling loop on the Claude API, a custom tool, memory, guardrails, and when LangChain, LangGraph or n8n is the better choice.
How to Build an AI Agent in 10 Minutes (Node.js + Claude)
Build a small AI agent in Node.js with the Claude API: conversation memory, a tool-use loop and proper error handling, matching a runnable GitHub repo.