Engineering · AI Systems · Technical Leadership

Luis Mori Guerra

Full Stack Developer & Technical Lead in Lima, Peru

Building scalable data platforms, AI applications, and developer tools. 10+ years of full-stack engineering at the Linux Foundation and beyond.

Read the latest About me

Linux Foundation 10+ years building Lima, Peru

Articles published

175

Topics covered

10+

Years building

Latest

Featured writing

AI Coding Workflows AI Agents Prompt Engineering Coding Agents

When Is a Prompt Enough, and When Do AI Agents Need More?

A research-backed guide for engineers and PMs on what is now redundant with stronger coding agents, when a good prompt is sufficient, and when prompts need scaffolding, tools, evals, and workflow design.

Jun 3, 2026 17 min read Read article

Recent essays & deep dives

Practical writing on AI engineering, data platforms, and developer workflows.

AI Agents Claude Code

Skills vs Default Agents: Do Coding Skills Really Improve Claude Code and Cursor?

A practical research audit for engineers and PMs: when agent skills improve coding agents, when default agents plus repo context are enough, and how to evaluate the tradeoff.

Jun 2, 2026 12 min read

AI Engineering

How AI Helps Engineers Evolve and Scale Modern Apps

AI can help teams move faster, but the real unlock is designing agents, skills, evals, traces, and self-correction loops around your app.

Jun 1, 2026 15 min read

Software Architecture System Design

The Pieces of Modern, Effective Software Design

A practical ladder for growing a software system from one app and one database into observable, event-driven, permission-aware, AI-ready architecture.

Jun 1, 2026 18 min read

AI Engineering

Blueprint Over Bytes: How Modern Engineering Shifted From Writing Code to Designing Systems

AI is changing the center of gravity in software engineering: less manual typing, more specification, validation, system design, and human judgment.

May 27, 2026 9 min read

AI Evaluation

From Intuition to Metrics: How to Know You're Using AI Correctly

Most AI programs start with intuition and optimism, then hit a harder question: can anyone prove the system is creating value? This guide turns AI adoption into a measurement problem, using baselines, outcome metrics, evals, and learning loops.

Updated May 27, 2026 15 min read

AI LLM

Claude Sonnet 4.6 1M vs Composer 2.5 Fast: A Practical LLM Comparison

A friendly, evidence-based comparison of Claude Sonnet 4.6 1M and Cursor Composer 2.5 Fast across speed, intelligence, coding, agents, cost, and product fit.

Updated May 27, 2026 14 min read

Explore

Browse by topic

All topics

AI Agents 37 AI 21 Claude Code 13 Agno 12 LLM 11 MCP 11 Cursor 10 Spec Kit 8

Browse everything

View all articles

AI LLM AI Engineering Context Engineering

Part 2: Alternatives to Claude Opus 4.7 1M for Engineers in 2026

A practical engineering comparison of Claude Opus 4.7 1M alternatives: GPT-5.5, DeepSeek V4 Pro, DeepSeek V4 Flash, Gemini 3.1 Pro, Gemini 3.5 Flash, and Kimi K2.6.

Updated May 22, 2026 20 min read

AI LLM Context Engineering RAG

1M vs 200K Context Windows: What Actually Changes for LLM Apps

A practical comparison of 1M-token and 200K-token LLM context windows: what gets easier, what still breaks, and how Engineers and PMs should choose an architecture.

Updated May 21, 2026 18 min read

Auth0 CIMD MCP AI Agents

Auth0 CIMD for Modern Apps, MCP, and Agent Workflows

A practical guide to Auth0 Client ID Metadata Documents, Auth for MCP, on-behalf-of token exchange, and secure agent access patterns for modern web apps.

Updated May 8, 2026 18 min read

OpenFGA Authorization MCP AI Agents

OpenFGA for Granular Permissions in Modern Apps, MCP, and Agent Workflows

A practical guide to using OpenFGA for fine-grained authorization in SaaS apps, MCP servers, workflow agents, and agent orchestrators.

Updated May 8, 2026 32 min read

Engineering Workflow Requirements Planning AI Coding

Correct Planning for Engineering Development: From Prompts to Spec Kit

A source-backed research guide for turning vague engineering ideas into approved requirements, analysis, tasks, implementation, and tests, first with manual prompts and then with GitHub Spec Kit.

Updated Apr 29, 2026 18 min read

Software Engineering Computer Science Compilers Security

Self-Modifying Software: From Fixed Points to Hot Patches

Self-modifying software is not science fiction. It sits on deep computability theory and shows up today in JIT compilers, livepatching, dynamic updates, malware, and AI-assisted code loops.

Apr 29, 2026 13 min read

Agno LangWatch Scenario Evaluation

Agno Evals vs LangWatch Scenario: Native Agent Metrics or Simulated Agent Tests?

A source-backed comparison of Agno's latest native eval docs and LangWatch Scenario's simulation-based testing model, with practical guidance on when to use each and how to combine them.

Updated Apr 28, 2026 15 min read

AI Security AI Agents Databases Authorization

Preparing Databases for Secure AI Agents

AI agents feel like they can touch every system. The practical answer is not more trust in the model, but database roles, row-level policies, semantic layers, tool scopes, approval gates, and audit trails.

Updated Apr 28, 2026 16 min read

AI Security AI Agents Secure Coding DevSecOps

A Secure Agentic Coding Process Is Not Just a Bigger LLM

The current evidence does not support trusting model size alone for secure code generation. Secure agentic coding needs threat modeling, constrained tools, scanners, evals, and human approval gates.

Updated Apr 28, 2026 20 min read

AI Engineering Research Learning

How to Read Dense Engineering Articles With AI: From 90-Second Skims to Source-Grounded Deep Dives

A practical workflow for engineers who want to digest long, technical articles without drowning in detail. Start with quick-view prompts, then move into grounded notes, multi-pass summaries, and long-context research workflows.

Updated Apr 27, 2026 17 min read

AI Language Communication Culture

Why We All Suddenly Talk Like AI People

From context and hallucinations to hardening and vibe coding, AI didn't invent all these words, but it definitely gave them a promotion.

Apr 27, 2026 7 min read

AI Agents Prompt Engineering LLM Software Architecture

How to Write Robust System Prompts for AI Agents Across LLMs

There is no truly bulletproof system prompt. But there is a practical engineering standard for making prompts far more robust across Sonnet, Haiku, GPT, and reasoning-style models.

Updated Apr 22, 2026 20 min read

AI Engineering Management Scrum Agile

When Code Gets Cheap, Complexity Moves: Rethinking Estimation in the AI Era

AI makes first-draft code cheaper, but it does not erase ambiguity, integration, verification, coordination, or production risk. That means engineering complexity has to be discussed differently, especially in Scrum planning.

Apr 22, 2026 16 min read

AI Agents Web Standards MCP Cloudflare

Agent-Ready Infrastructure: How to Make Your Website Work With AI Agents

AI agents are the new crawlers. Learn how to signal discoverability, serve machine-readable content, control bot access, and expose capabilities through MCP — with practical code examples.

Apr 21, 2026 13 min read

Spec Kit Cursor Claude Code Spec-Driven Development

GitHub Spec Kit: How to Get Started with Cursor or Claude Code

A simple, source-backed guide for engineers and PMs to start with GitHub Spec Kit, understand the main commands, and use the workflow cleanly in Cursor or Claude Code.

Updated Apr 15, 2026 20 min read

Code Review AI Agents LLM Software Engineering

How to Build a Good Agentic Code Reviewer

Most AI code review bots fail for a simple reason: they optimize for visible comments instead of reviewer trust. This guide pulls together current benchmarks, practitioner reports, product limitations, and design patterns for building a code review agent that is fast, quieter, less biased, and less hallucination-prone.

Apr 15, 2026 23 min read

AI Future of Work Productivity Burnout

AI Work Paradoxes: Why Faster Tools Are Making Professional Life Feel Heavier

The emerging AI-era problem is not just automation or job loss. It is possibility overload, expectation creep, verification fatigue, boundary collapse, and work that expands faster than human attention.

Apr 14, 2026 12 min read

Spec Kit Legacy Modernization Spec-Driven Development Brownfield

Before You Copy Legacy Code: A Spec-to-Spec Migration Workflow for Modernizing One Feature

An exploratory, source-backed article on reverse-engineering one feature into current-state specs in the old repo, then using those artifacts to drive a safer implementation in a new repo and a new stack.

Updated Apr 14, 2026 18 min read

Spec Kit Cursor Gemini GPT-5.4

A Phase-by-Phase Model Strategy for GitHub Spec Kit in 2026

A source-backed follow-up on routing GitHub Spec Kit phases across fast drafting models, deeper planning models, and stronger implementation models without treating all steps as the same kind of work.

Updated Apr 14, 2026 19 min read

Spec Kit Cursor Spec-Driven Development Brownfield

How to Reverse-Engineer an Existing Feature into GitHub Spec Kit Artifacts

A practical brownfield workflow for reconstructing one existing feature into spec.md, plan.md, tasks.md, and supporting Spec Kit artifacts without pretending you are starting from scratch.

Updated Apr 13, 2026 16 min read

Luis Mori Guerra

Recent Articles

Topics

Luis Mori Guerra

Featured writing

When Is a Prompt Enough, and When Do AI Agents Need More?

Recent essays & deep dives

Skills vs Default Agents: Do Coding Skills Really Improve Claude Code and Cursor?

How AI Helps Engineers Evolve and Scale Modern Apps

The Pieces of Modern, Effective Software Design

Blueprint Over Bytes: How Modern Engineering Shifted From Writing Code to Designing Systems

From Intuition to Metrics: How to Know You're Using AI Correctly

Claude Sonnet 4.6 1M vs Composer 2.5 Fast: A Practical LLM Comparison

Browse by topic

Browse everything

Part 2: Alternatives to Claude Opus 4.7 1M for Engineers in 2026

1M vs 200K Context Windows: What Actually Changes for LLM Apps

Auth0 CIMD for Modern Apps, MCP, and Agent Workflows

OpenFGA for Granular Permissions in Modern Apps, MCP, and Agent Workflows

Correct Planning for Engineering Development: From Prompts to Spec Kit

Self-Modifying Software: From Fixed Points to Hot Patches

Agno Evals vs LangWatch Scenario: Native Agent Metrics or Simulated Agent Tests?

Preparing Databases for Secure AI Agents

A Secure Agentic Coding Process Is Not Just a Bigger LLM

How to Read Dense Engineering Articles With AI: From 90-Second Skims to Source-Grounded Deep Dives

Why We All Suddenly Talk Like AI People

How to Write Robust System Prompts for AI Agents Across LLMs

When Code Gets Cheap, Complexity Moves: Rethinking Estimation in the AI Era

Agent-Ready Infrastructure: How to Make Your Website Work With AI Agents

GitHub Spec Kit: How to Get Started with Cursor or Claude Code

How to Build a Good Agentic Code Reviewer

AI Work Paradoxes: Why Faster Tools Are Making Professional Life Feel Heavier

Before You Copy Legacy Code: A Spec-to-Spec Migration Workflow for Modernizing One Feature

A Phase-by-Phase Model Strategy for GitHub Spec Kit in 2026

How to Reverse-Engineer an Existing Feature into GitHub Spec Kit Artifacts

Search the blog