DEV Community

Fernando Rodriguez profile picture

Fernando Rodriguez

CTO at KeepCoding. I write tools for AI agents and blog about what breaks when you let them code.

Location Madrid Joined Joined on  Personal website https://www.frr.dev
From /simplify to the Jedi Council: How I Built a Code Review with Kent Beck, Martin Fowler, and Mike Acton

From /simplify to the Jedi Council: How I Built a Code Review with Kent Beck, Martin Fowler, and Mike Acton

Comments
8 min read
RustyClaw: I'm rewriting an AI agent in Rust (because the meme demands it)

RustyClaw: I'm rewriting an AI agent in Rust (because the meme demands it)

Comments
7 min read
Why 99% of What You Send to Claude Is Already Cached

Why 99% of What You Send to Claude Is Already Cached

Comments
7 min read
OpenAI scales PostgreSQL for 800 million users with a single writer (no sharding)

OpenAI scales PostgreSQL for 800 million users with a single writer (no sharding)

Comments
6 min read
Madness Driven Design: Don Quixote, Sancho Panza, and Your AI Copilot

Madness Driven Design: Don Quixote, Sancho Panza, and Your AI Copilot

Comments
8 min read
My AI Read a JSON File from Disk 900 Times in a Loop (And Why No Linter Can Save You)

My AI Read a JSON File from Disk 900 Times in a Loop (And Why No Linter Can Save You)

Comments
6 min read
Linear Agent Isn’t What You Need. Your Agent Was Already in the Terminal

Linear Agent Isn’t What You Need. Your Agent Was Already in the Terminal

Comments
6 min read
Five Nonexistent Experts Review Your Startup Before You Build It

Five Nonexistent Experts Review Your Startup Before You Build It

Comments
8 min read
Git Worktrees: How to Have Multiple AI Agents Working Simultaneously Without Conflicts

Git Worktrees: How to Have Multiple AI Agents Working Simultaneously Without Conflicts

Comments
5 min read
I'm paying $15 per million tokens to write 'fix: typo'

I'm paying $15 per million tokens to write 'fix: typo'

Comments
7 min read
diy-codex-automations-claude-code-systemd

diy-codex-automations-claude-code-systemd

Comments
4 min read
In Codex, a Skill Is Not a /Command (but in Claude Code, It Almost Is)

In Codex, a Skill Is Not a /Command (but in Claude Code, It Almost Is)

Comments
5 min read
Why My CLI Output Isn't XML (And How I Ended Up Reinventing TOON Without Knowing It)

Why My CLI Output Isn't XML (And How I Ended Up Reinventing TOON Without Knowing It)

Comments
6 min read
10 GB VM for a chatbot: What the hell is Claude doing on your Mac

10 GB VM for a chatbot: What the hell is Claude doing on your Mac

Comments
5 min read
Claude Code Native Build: 100MB Binary to Ditch Node for Good

Claude Code Native Build: 100MB Binary to Ditch Node for Good

Comments
6 min read
My Setup: Claude Code + Ghostty + Worktrees on a Mac

My Setup: Claude Code + Ghostty + Worktrees on a Mac

Comments
8 min read
The Week When Boring Discipline Beat Magic

The Week When Boring Discipline Beat Magic

Comments
6 min read
Beads Is Dead. Long Live the Linear CLI

Beads Is Dead. Long Live the Linear CLI

Comments
4 min read
Apple's On-Device Model is Terrible for Chat But Surprisingly Good at Structured Output and Tool Calling

Apple's On-Device Model is Terrible for Chat But Surprisingly Good at Structured Output and Tool Calling

Comments
4 min read
Your Mac Has a Free LLM and You're Not Using It

Your Mac Has a Free LLM and You're Not Using It

Comments
5 min read
Agentic Experience: 1,324 calls to my CLI, 15.9% error rate

Agentic Experience: 1,324 calls to my CLI, 15.9% error rate

Comments
7 min read
When Your AI Becomes Your Worst Enemy

When Your AI Becomes Your Worst Enemy

Comments
8 min read
Linear, Beads and Tasks: Three Memory Layers for Claude Code

Linear, Beads and Tasks: Three Memory Layers for Claude Code

Comments
5 min read
150 Lines of Apologies Removed

150 Lines of Apologies Removed

Comments
6 min read
The Best Thing That's Happened to Python in Decades Is Written in Rust

The Best Thing That's Happened to Python in Decades Is Written in Rust

Comments
8 min read
MEMORY.md: the field notebook your AI writes itself

MEMORY.md: the field notebook your AI writes itself

Comments
6 min read
Linear and Beads: How to Prevent Your AI from Getting Alzheimer's

Linear and Beads: How to Prevent Your AI from Getting Alzheimer's

Comments
4 min read
The Half-Life of Your Skills Is 2 Years (And Dropping)

The Half-Life of Your Skills Is 2 Years (And Dropping)

Comments
5 min read
I've Declared Email Bankruptcy (Again), but This Time I Have a Plan

I've Declared Email Bankruptcy (Again), but This Time I Have a Plan

Comments
6 min read
Codex CLI asks for permission to breathe (and gets fixed with two flags)

Codex CLI asks for permission to breathe (and gets fixed with two flags)

Comments
5 min read
Claude Code Skills: Teaching New Tricks to an Old Dog

Claude Code Skills: Teaching New Tricks to an Old Dog

Comments
8 min read
Bun: The Runtime That Wants to Retire Node (and Now Has the Cash to Do It)

Bun: The Runtime That Wants to Retire Node (and Now Has the Cash to Do It)

Comments
6 min read
When Security Asks Permission So Often You Stop Reading

When Security Asks Permission So Often You Stop Reading

Comments
6 min read
Your AI coding agent is a while loop with delusions of grandeur

Your AI coding agent is a while loop with delusions of grandeur

Comments
8 min read
Your Terminal is Burning Battery Like It's Mining Bitcoin

Your Terminal is Burning Battery Like It's Mining Bitcoin

Comments
4 min read
NLTagger and Sentiment Analysis: Why Apple Thinks Your Code is Depressing

NLTagger and Sentiment Analysis: Why Apple Thinks Your Code is Depressing

Comments
5 min read
39 Million Secrets Leaked on GitHub. Yours Could Be Next.

39 Million Secrets Leaked on GitHub. Yours Could Be Next.

Comments
5 min read
Anatomy of Claude Code's Remote Control: The Hidden API You Can't Use Yet

Anatomy of Claude Code's Remote Control: The Hidden API You Can't Use Yet

Comments
5 min read
Apple installed 84GB of jellyfish on my Mac. Duplicated.

Apple installed 84GB of jellyfish on my Mac. Duplicated.

Comments
4 min read
Adversarial Programming: When Your AI Copilot Invents APIs

Adversarial Programming: When Your AI Copilot Invents APIs

Comments
7 min read
33,000 lines of XML to tell you heavyWork() is slow: how I tamed xctrace for LLMs

33,000 lines of XML to tell you heavyWork() is slow: how I tamed xctrace for LLMs

Comments
5 min read
loading...