Resource Hub
Curated tools, articles and essays for AI-First leaders.
The Capiva library is a curated collection of guides, essays, tools, and articles on AI applied to business — from AI harness and context engineering to GEO/AEO (AI visibility) and AI Centers of Excellence. Use the filters below to jump straight to the type of content you need.
Featured
How to configure MCP in Claude Code: claude mcp add, .mcp.json and scopes
How to configure MCP in Claude Code: claude mcp add for HTTP and stdio, local, project and user scopes, .mcp.json with variables and approval. Tested commands.
Claude Code subagents: how to create and when to use them
How to create Claude Code subagents: a .claude/agents file, frontmatter, tools, model, validation, how to call them and when to delegate.
MCP vs API vs Skills vs CLI: when to use each one
MCP vs API vs Skills vs CLI in Claude Code: the same task three ways, where a Skill fits and a table of when to use each. Tested.
How to save tokens in Claude Code: /context, /compact, subagents and cache
How to save tokens in Claude Code: measure with /context, /clear vs /compact, what breaks the prompt cache, a lean CLAUDE.md, MCP and subagents. With sources.
Claude Code Hooks: How to Configure Them, With 3 Ready Examples (PreToolUse, PostToolUse and Stop)
How to configure Claude Code hooks, with three tested examples: a PreToolUse guard, a PostToolUse sensor and a Stop gate.
CLAUDE.md: What It Is and How to Write One the Agent Follows
What CLAUDE.md is, how to write one the agent follows, its ideal size, and CLAUDE.md vs AGENTS.md.
How to build an MCP server in Python: official SDK, pytest tests and running it in Claude Code
How to create an MCP server in Python with the official SDK: define tools, test them with pytest and run the server from Claude Code, step by step.
llms.txt: What It Is and How to Create, Generate and Validate It (Next.js Example)
What llms.txt is and how to create one: the llmstxt.org v2 format, a Python generator and validator, and publishing in Next.js.
How to Measure Whether ChatGPT Cites Your Company: A Python Script With the OpenAI Search API
A Python script that uses the OpenAI web search API to measure whether ChatGPT cites your company.
How to Create a Skill in Claude Code: SKILL.md Step by Step
How to create a Claude Code skill: SKILL.md step by step, with a script and arguments.
How to Install Claude Code on Windows: PowerShell, CMD, WinGet or WSL
How to install Claude Code on Windows with PowerShell, CMD, WinGet or WSL, and how to fix the most common errors.
Guardrails and Evals for AI Agents: What They Are and How to Know the Agent Got It Right
What guardrails and evals for AI agents are, and how to check an agent works before production.
AI Consulting for Businesses: What It Is, What It Covers, and How to Choose the Right One
AI consulting for businesses covers diagnosis, proof of concept, implementation, and ongoing governance. What each track includes, how to evaluate a vendor before hiring, and what separates a good engagement from a bad one.
What Is GEO / SEO for AI (and How It Works)
GEO (Generative Engine Optimization), AEO, and "SEO for AI" are the discipline of optimizing content to be cited by AI answers — distinct from classic SEO, which ranks links. The concept (Princeton, 2023), the difference between the terms, and what the AI rewards.
How to Appear in ChatGPT: What Makes the AI Recommend Your Company
You don't register your company with ChatGPT — the AI recommends whoever has a citable, structured, authoritative presence. The three real levers (citability, authority, technical access) and how to test.
What Is an AI Center of Excellence? The Structure That Decides If AI Becomes Capability or Stays in Pilot
An AI Center of Excellence is the internal structure that drives AI adoption to valuable outcomes and prevents fragmented or ungoverned adoption (Microsoft CAF). Most fail by becoming bottlenecks.
How Much Does AI Consulting Cost? What Determines the Price (and How to Ask for a Real Quote)
There is no fixed price table for AI consulting. The value depends on the billing model (hourly, project, retainer, scope), the seniority of the team, and the actual scope of the problem. The factors and the right questions to ask before accepting a quote.
What is an AI Harness? Definition, components, and why it matters more than the model
An AI harness is the infrastructure around an LLM (tools, rules, memory and quality gates) that turns it into a reliable agent. Agent = Model + Harness.
What Is Harness Engineering? The Discipline That Decides If an Agent Works in Production
Harness engineering is the discipline of designing everything around the model (rules, tools, memory, and verification) so an agent works in production. Named by Mitchell Hashimoto in 2026.
Harness, Context Engineering, and RAG: What's the Difference and How They Fit
Context engineering is one layer of the harness, not a synonym, and RAG is one technique inside context engineering. Understand the containment: RAG inside context engineering, inside the harness.
How to build an AI harness in Python (step by step)
A Python walkthrough: an error-to-rule loop, a guardrail that blocks the action, and a pass/fail eval. The example model is a placeholder, with no benchmark score.
Claude Code: complete guide to harness, MCP and hooks
Map of Claude Code as a harness. Summarizes and links the published how-tos: Windows, CLAUDE.md, hooks, skills, MCP, subagents, MCP versus API, and tokens.
AI Harness Benchmark: Why the Same Model Scores Differently
In agent benchmarks, the harness moves the score as much as the model. There are two senses: agent harness (the scaffold, which must be disclosed) and eval harness (the runner, which must be held constant).
AI Harness in Practice: running a company on agents
How Capiva runs an operational AI harness in production, why most AI projects never reach the P&L, and capivaOS, the open-source development layer.
Claude Impact Lab Rio: Auditable AI for Public Health and Public Safety
The first Brazilian edition of the Claude Impact Lab brought teams together in Rio to build AI solutions for public health and public safety.
capivaOS — Spec-Driven Harness for Claude Code
capivaOS: open-source (MIT) harness that enforces a spec → plan → implement → verify pipeline on Claude Code, with mechanical quality gates. Plugin, 2 commands.
MCA: Technology Convergence Map
Visualize the convergence of AGI, agentic swarms and bio-computing. Capiva's MCA maps the technology forces redefining your sector in 0 to 18 months.
GEO Diagnostic — Is Your Site Visible to AI?
Free tool that analyzes your site in 60 seconds and reveals whether ChatGPT, Gemini and Perplexity cite your company. A 0-100 score across 6 dimensions.
Capiva Intake: turn your project idea into context
Describe your project idea and get a domain glossary, requirements, contradictions and open questions, ready to seed an AI harness.
Podkst.ai
Transform any text, URL, or topic into a professional podcast with AI. 30+ neural voices in Portuguese.
The Professional Uselessness Epidemic
How AI is replacing burnout with a deeper crisis: the feeling of being irrelevant.
The Whole Library
31 itemsClaude Code subagents: how to create and when to use them
How to create Claude Code subagents: a .claude/agents file, frontmatter, tools, model, validation, how to call them and when to delegate.
MCP vs API vs Skills vs CLI: when to use each one
MCP vs API vs Skills vs CLI in Claude Code: the same task three ways, where a Skill fits and a table of when to use each. Tested.
How to configure MCP in Claude Code: claude mcp add, .mcp.json and scopes
How to configure MCP in Claude Code: claude mcp add for HTTP and stdio, local, project and user scopes, .mcp.json with variables and approval. Tested commands.
How to save tokens in Claude Code: /context, /compact, subagents and cache
How to save tokens in Claude Code: measure with /context, /clear vs /compact, what breaks the prompt cache, a lean CLAUDE.md, MCP and subagents. With sources.
How to build an MCP server in Python: official SDK, pytest tests and running it in Claude Code
How to create an MCP server in Python with the official SDK: define tools, test them with pytest and run the server from Claude Code, step by step.
Claude Code Hooks: How to Configure Them, With 3 Ready Examples (PreToolUse, PostToolUse and Stop)
How to configure Claude Code hooks, with three tested examples: a PreToolUse guard, a PostToolUse sensor and a Stop gate.
llms.txt: What It Is and How to Create, Generate and Validate It (Next.js Example)
What llms.txt is and how to create one: the llmstxt.org v2 format, a Python generator and validator, and publishing in Next.js.
How to Create a Skill in Claude Code: SKILL.md Step by Step
How to create a Claude Code skill: SKILL.md step by step, with a script and arguments.
CLAUDE.md: What It Is and How to Write One the Agent Follows
What CLAUDE.md is, how to write one the agent follows, its ideal size, and CLAUDE.md vs AGENTS.md.
How to Install Claude Code on Windows: PowerShell, CMD, WinGet or WSL
How to install Claude Code on Windows with PowerShell, CMD, WinGet or WSL, and how to fix the most common errors.
How to Measure Whether ChatGPT Cites Your Company: A Python Script With the OpenAI Search API
A Python script that uses the OpenAI web search API to measure whether ChatGPT cites your company.
Guardrails and Evals for AI Agents: What They Are and How to Know the Agent Got It Right
What guardrails and evals for AI agents are, and how to check an agent works before production.
AI Consulting for Businesses: What It Is, What It Covers, and How to Choose the Right One
AI consulting for businesses covers diagnosis, proof of concept, implementation, and ongoing governance. What each track includes, how to evaluate a vendor before hiring, and what separates a good engagement from a bad one.
How Much Does AI Consulting Cost? What Determines the Price (and How to Ask for a Real Quote)
There is no fixed price table for AI consulting. The value depends on the billing model (hourly, project, retainer, scope), the seniority of the team, and the actual scope of the problem. The factors and the right questions to ask before accepting a quote.
How to Appear in ChatGPT: What Makes the AI Recommend Your Company
You don't register your company with ChatGPT — the AI recommends whoever has a citable, structured, authoritative presence. The three real levers (citability, authority, technical access) and how to test.
What Is GEO / SEO for AI (and How It Works)
GEO (Generative Engine Optimization), AEO, and "SEO for AI" are the discipline of optimizing content to be cited by AI answers — distinct from classic SEO, which ranks links. The concept (Princeton, 2023), the difference between the terms, and what the AI rewards.
What Is an AI Center of Excellence? The Structure That Decides If AI Becomes Capability or Stays in Pilot
An AI Center of Excellence is the internal structure that drives AI adoption to valuable outcomes and prevents fragmented or ungoverned adoption (Microsoft CAF). Most fail by becoming bottlenecks.
Claude Code: complete guide to harness, MCP and hooks
Map of Claude Code as a harness. Summarizes and links the published how-tos: Windows, CLAUDE.md, hooks, skills, MCP, subagents, MCP versus API, and tokens.
How to build an AI harness in Python (step by step)
A Python walkthrough: an error-to-rule loop, a guardrail that blocks the action, and a pass/fail eval. The example model is a placeholder, with no benchmark score.
What Is Harness Engineering? The Discipline That Decides If an Agent Works in Production
Harness engineering is the discipline of designing everything around the model (rules, tools, memory, and verification) so an agent works in production. Named by Mitchell Hashimoto in 2026.
AI Harness Benchmark: Why the Same Model Scores Differently
In agent benchmarks, the harness moves the score as much as the model. There are two senses: agent harness (the scaffold, which must be disclosed) and eval harness (the runner, which must be held constant).
Harness, Context Engineering, and RAG: What's the Difference and How They Fit
Context engineering is one layer of the harness, not a synonym, and RAG is one technique inside context engineering. Understand the containment: RAG inside context engineering, inside the harness.
What is an AI Harness? Definition, components, and why it matters more than the model
An AI harness is the infrastructure around an LLM (tools, rules, memory and quality gates) that turns it into a reliable agent. Agent = Model + Harness.
capivaOS — Spec-Driven Harness for Claude Code
capivaOS: open-source (MIT) harness that enforces a spec → plan → implement → verify pipeline on Claude Code, with mechanical quality gates. Plugin, 2 commands.
Claude Impact Lab Rio: Auditable AI for Public Health and Public Safety
The first Brazilian edition of the Claude Impact Lab brought teams together in Rio to build AI solutions for public health and public safety.
GEO Diagnostic — Is Your Site Visible to AI?
Free tool that analyzes your site in 60 seconds and reveals whether ChatGPT, Gemini and Perplexity cite your company. A 0-100 score across 6 dimensions.
AI Harness in Practice: running a company on agents
How Capiva runs an operational AI harness in production, why most AI projects never reach the P&L, and capivaOS, the open-source development layer.
Podkst.ai
Transform any text, URL, or topic into a professional podcast with AI. 30+ neural voices in Portuguese.
Capiva Intake: turn your project idea into context
Describe your project idea and get a domain glossary, requirements, contradictions and open questions, ready to seed an AI harness.
MCA: Technology Convergence Map
Visualize the convergence of AGI, agentic swarms and bio-computing. Capiva's MCA maps the technology forces redefining your sector in 0 to 18 months.
The Professional Uselessness Epidemic
How AI is replacing burnout with a deeper crisis: the feeling of being irrelevant.