Steven Gonsalvez

Software Engineer

Blog

24 articles on AI, productivity, and software engineering

Series

"Use Claude Code for FREE" is a Trap

Why free AI coding via Nvidia NIM and OpenRouter is a trap. The Cheap-Intelligent-Fast trilemma, 40 RPM rate limits, Opus 4.7 vs GPT-5.5 vs MiniMax M2.7 benchmarks, and why your first AI coding experience should not be the free one.

claude code free nvidia nimai coding agent comparison 2026opus 4.7 vs gpt 5.5free ai coding toolsnvidia nim rate limit 429ai model trilemma cheap intelligent fastminimax m2.7 reviewcoding agent benchmarks agentic

Your Coding Agent's Best Feature Isn't the Code

Why Claude Code beats Codex, Copilot, and every other coding agent in 2026. The developer experience of terminal AI coding agents matters more than the model. Statusline, /insights, hooks, and the features that make the 8th hour feel like the 1st.

claude codeai coding agentdeveloper experiencecodexcopilotterminal coding agentdevxai coding tools 2026

Browser Tools for AI Agents Part 1: Playwright, Puppeteer, and Why Your Agent Picked Playwright

Playwright for AI agents explained 2026. Why Playwright beat Puppeteer for browser automation, how accessibility trees slash token costs, dev-browser for coding agents, Patchright and Scrapling for anti-bot bypass.

playwright ai agentsbrowser automation aiplaywright vs puppeteerai browser toolsdev-browserpatchright stealthscrapling anti-botaccessibility tree ai 2026

Browser Tools for AI Agents Part 2: The Framework Wars (browser-use, Stagehand, Skyvern)

AI browser frameworks compared 2026. browser-use vs Stagehand vs Skyvern: DOM-first vs vision-first architecture, LLM token costs per step, caching strategies, and the expect testing tool for coding agent validation loops.

browser-use aistagehand browserskyvern automationai browser framework comparisondom vs vision aiai agent browser toolsexpect testingllm browser automation 2026

Browser Tools for AI Agents Part 3: Managed Infrastructure and When DIY Stops Making Sense

Managed browser infrastructure for AI agents 2026. Firecrawl vs Browserbase vs Steel vs Bright Data vs Browserless pricing and features compared. Self-hosted vs managed cost analysis and when DIY stops making sense.

firecrawl aibrowserbasesteel browserbright data scrapingbrowserless pricingmanaged browser infrastructureai web scraping saasheadless chrome cloud 2026

Browser Tools for AI Agents Part 4: Skip the Browser, Save 80% on Tokens

Save 80% on LLM tokens with content extraction 2026. markdown.new, Jina Reader, Trafilatura compared. Why feeding raw HTML to AI agents wastes tokens and how HTML-to-markdown conversion fixes your context window budget.

llm token optimizationmarkdown.new cloudflarejina reader aitrafilatura extractionhtml to markdownai content extractionreduce token costsweb scraping for llm 2026

2-2 Factor for AI Agents: Multi-Agent Reliability

Human reliability maths applied to AI agents. Consensus protocols, identity checks, and why your agent swarm needs the same safeguards humans built centuries ago.

aiagentssecurityarchitecturereliability

MCP Security Risks: Tool Poisoning, Shadowing Attacks and How AI Gets Exploited

MCP security vulnerabilities explained 2025. Hands-on demos of tool poisoning, cross-server shadowing attacks, token theft, and data exfiltration via Model Context Protocol. Practical defences and security best practices for AI agents.

mcp securitymodel context protocol vulnerabilitiesai agent security riskstool poisoning attackmcp shadowingai data exfiltrationmcp best practicesai cybersecurity 2025

2025s Best AI Coding Tools: Real Cost, Geeky Value & Honest Comparison

2025 AI coding tools pricing compared. Gemini 2.5 Pro free tier, GitHub Copilot, Cursor, Claude Code, Aider, Roocode, Cline costs and value. Honest review with comparison table for developers on a budget.

ai coding tools pricing 2025github copilot costcursor pricingclaude code reviewgemini ai freeaider cliroocodecline vs copilotai developer tools comparison

Build Your Own MCP Prompt Server: A Dev-Centric Registry with STDIO

Build your own MCP prompt server tutorial 2025. Step-by-step TypeScript guide to a layered prompt registry with STDIO transport, Zod validation, file-based storage. Works with Claude Desktop, Cursor, and any MCP client.

mcp prompt serverbuild mcp server tutorialmodel context protocol typescriptmcp stdio transportzod validationprompt managementclaude desktop mcpcursor mcp server 2025

MCP Architecture Explained: STDIO, SSE Transport and What Makes It Tick

MCP architecture deep dive 2025. How Model Context Protocol works under the hood: function calling, JSON-RPC, STDIO vs SSE transport, streamable HTTP, OAuth 2.1 auth, and the enterprise security gaps nobody talks about.

mcp architecturemodel context protocol transportmcp stdio vs ssemcp oauthjson-rpc aimcp function callingstreamable http mcpmcp enterprise security 2025

Introduction to Model Context Protocol (MCP): The USB-C of AI Integrations

Model Context Protocol (MCP) explained for developers 2025. How Anthropic MCP standardises AI tool integrations, replaces LangChain connector chaos with M+N simplicity. MCP servers, clients, and the USB-C analogy.

model context protocolmcp servermcp explainedanthropic mcpai tool integrationmcp vs langchainai standards 2025mcp architecture

Finding the Best AI Coding Assistant: From Pure Vibe to Practical Power

Best AI coding assistant comparison 2025. GitHub Copilot vs Cursor vs Claude vs ChatGPT for developers. Performance benchmarks, pricing, and how to pick the right AI pair programmer for your workflow.

ai coding assistantgithub copilotcursor aiclaude codechatgpt codingai pair programmingbest ai tools for developers 2025

Beyond the Hype: What Truly Makes an AI a Great Coding Partner?

What makes an AI coding assistant actually good in 2025. Beyond HumanEval benchmarks to real-world capabilities: architecture understanding, debugging, security awareness, code generation vs code comprehension.

ai coding benchmarksai code generationai debugging toolshumanevalswebenchai architecture understandingllm coding capabilities 2025

Tyranny of Small Decisions: AI Agents and Codebase Drift

Alfred Kahn warned that rational small decisions aggregate into irrational outcomes. Now AI agents make thousands of those decisions daily in your codebase.

aiagentsarchitectureengineering-cultureeconomics

War Heroes vs The Meticulous Engineer

Why orgs promote firefighters and ignore the people who prevent fires. Time preference, effort paradox, and the cultural rot that follows.

leadershipengineering-cultureorganisationsmanagement

GitHub Actions OIDC with Terraform and Azure

Set up passwordless GitHub Actions using OIDC federated credentials with Terraform on Azure. Full working example with GitOps vending machine.

azuregithubterraformtutorial