Latest writings
Notes on AI agents, Salesforce, automation, micro-SaaS, and engineering.

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.

Engineering a Personal Prompt System: Library, Versioning, and Automated Tests
Stop guessing with your prompts. Learn how to build a centralized prompt library, version control your system instructions, and write a simple Python test harness to evaluate output quality scientifically.

The De-Scoping Algorithm: How to Define an MVP That Actually Ships
Most developer side projects die in the 'graveyard of localhost' because the scope is too big. Here is the 'Power of One' framework I use to strip products down to the bare metal: 1 User, 1 Pain, 1 KPI.

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.

Refactoring My Reality: The Engineer's Guide to Daily Systems
Stop relying on motivation. Learn how to architect a '2-Hour Deep Work Loop' and implement a daily logging protocol that treats your energy like a finite system resource.

Your Code is Good, But Your Repo Looks Abandoned: A Guide to GitHub Hygiene
Code functionality is only half the battle. This guide covers how to structure your GitHub repositories to serve as high-converting assets for your personal brand.

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.

The Developer’s Guide to Landing Page Teardowns: Debugging Your Conversion Rate
You built a complex system, but your landing page is leaking users. Here is a systematic, builder-first framework to tear down, refactor, and optimize your copy for clarity and conversion.

Pricing 101 for Solo Founders: Stop Undervaluing Your Code
Engineers are great at logic but terrible at pricing. Learn how to structure pricing tiers, define value metrics, and use psychological anchoring to charge what your Micro-SaaS is actually worth.

Building an Automated AI Daily Brief: My Morning Workflow
Stop checking five different apps to start your day. Here’s how I built a Python-based system that fetches tasks, prioritizes them with GPT-4, and emails me a strategic briefing every morning at 7 AM. We cover API integration, prompt engineering for planning, and robust scheduling.

The Feedback Loop: Turning Community Questions into Engineering Assets
A practical system for developers who build in public: collect the questions people ask, sort them, answer each once in a permanent place, and let the patterns steer what you build.

The Infinite Content Engine: How to Turn 1 Technical Blog Post into 10 Assets
Stop letting your technical writing die in the archives. Here is the engineering approach to content ops: a systematic repurposing map to turn one article into a month's worth of content across X, LinkedIn, and YouTube.

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.

The Pragmatic Automation Stack: When to Pay vs. When to Self-Host
Subscription fatigue is real, but so is maintenance hell. Here is my decision framework for building an AI automation stack, comparing n8n vs. Zapier, Supabase vs. Airtable, and the exact tools I use to run my systems.

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 I Passed JLPT N5 Alongside Client Work (and Now Study for N4)
The study system I used to pass JLPT N5 while doing freelance Salesforce and automation work: textbooks, Anki, short daily sessions, and a little automation.

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.

n8n Automation Guide: Build a Telegram Translation Workflow with OpenAI
A practical introduction to n8n: the core concepts, a step-by-step Telegram translation workflow with OpenAI, the gotchas to watch for, and how n8n compares to Zapier and Make.
10 Micro-SaaS Ideas Using AI Automation
Practical micro-SaaS business ideas you can build in a weekend using AI APIs, n8n, and modern frameworks. Each idea includes a revenue model.
Salesforce Developer Interview Questions: Apex, SOQL and LWC Answered
Salesforce developer interview prep: Apex triggers and async processing, efficient and secure SOQL, the LWC lifecycle, order of execution, and how to prepare.
LWCHow to Build a Simple CSV Parser with Lightning Web Components
Upload a CSV file in Salesforce and preview it in a lightning-datatable with one Lightning Web Component, plain JavaScript and no Apex. Updated for API 67.0.