← Back to Home
šŸŽ„

31 Days of AI

This was a campaign run in December 2025 to test the ability to deploy an entire documentation workflow daily using only AI and without any manual intervention. See the final results here.

Day 22 of 31

Day 01

Automating the Editor

Introducing the article-spec-pack pipeline that powers this entire campaign.

Live
Day 02

Beyond the Hype

Swap the sci-fi shorthand for a working definition of AI you can actually use.

Live
Day 03

From Logic to Prediction

Why AI works differently than every other tool you use—and why that matters.

Live
Day 04

The Professional's Playbook

Four copy-paste AI prompts for developers, project managers, creatives, and learners.

Live
Day 05

Evaluating AI Outputs

AI doesn't know what it doesn't know. Learn to spot hallucinations, bias, and verify facts.

Live
Day 06

Managing Context

AI has no long-term memory—learn to manage context windows and keep the model on track.

Live
Day 07

The CRIT Framework

Structure your prompts with Context, Role, Instruction, and Task Format for professional outputs.

Live
Day 08

Advanced Patterns (CoT, RAG, ReAct)

Make the model think before it talks using CoT, RAG, and ReAct to handle complex work without hallucinations.

Live
Day 09

Choosing Your AI Tool

A practical framework to match models to the job across speed, depth, and cost tradeoffs.

Live
Day 10

From Bug to Breakthrough

Use AI as a critical thinking partner to falsify assumptions and debug faster.

Live
Day 11

The Professional's Compass

Durable principles for working with AI so you can adapt as models and tools change.

Live
Day 12

How the Machine Learned to Write

A three-stage view of pre-training, fine-tuning, and RLHF—and what each stage explains about hallucinations and overconfidence.

Live
Day 13

Beyond Words

Multimodal AI in real workflows: screenshots, diagrams, and evidence-first prompting.

Coming Soon
Day 14

Creative Iteration

How to turn a generic first draft into something specific using constraints and proof artifacts.

Coming Soon
Day 15

Proactive Prompt Design

Design prompts like interfaces: inputs, constraints, outputs, and verification.

Coming Soon
Day 16

AI for Strategists

Turn messy threads into briefs, compare options, and run pre-mortems that catch failure early.

Coming Soon
Day 17

AI Security & Ethics

Practical guardrails: prompt injection fences, tool contracts, and evidence-based answers.

Coming Soon
Day 18

The Wisdom of Restraint

A clear gate for when to use AI, when to keep humans in charge, and when to say no.

Coming Soon
Day 19

Agentic AI

How to design safe agents with scopes, receipts, and verification habits.

Coming Soon
Day 20

From Apprentice to Architect

How to make your AI workflows durable: interfaces, evals, and a ā€œplan, patch, proveā€ loop.

Coming Soon
Day 21

7 Quick Wins: Instant Upgrades for Your Prompts

Sometimes you just need a quick fix—fast levers to pull for immediate output upgrades.

Coming Soon
Day 22

The Developer's Primer: How AI Actually Works Under the Hood

A useful frame: math over mind-reading—a mental model that matches how the machine actually behaves.

Coming Soon
Day 23

Mixture of Experts (MoE): Why Some Models Are Fast, Weird, and Worth It

MoE is one of the most important scaling ideas in modern language models.

Coming Soon
Day 24

Long Context, Short Attention: How to Keep a Model on Track

Long context doesn't remove the need for structure—it increases it.

Coming Soon
Day 25

Inference Engineering: The Part of AI That Actually Hits Your Users

Most AI problems that feel like "model quality" are really systems problems.

Coming Soon
Day 26

Evals That Prevent Embarrassing Launches

You tested with three prompts, it looked great—then you shipped without evals.

Coming Soon
Day 27

RAG in Production: Why "Just Add Retrieval" Still Ships Wrong Answers

Retrieval doesn't make the model truthful—it gives it more plausible text to be wrong with.

Coming Soon
Day 28

When AI Can Call Tools: How to Keep "Helpful" From Becoming Dangerous

You give a model a tool—then one day it does the thing you did not mean.

Coming Soon
Day 29

AI for Incident Response: Make It a Calm Copilot, Not a Chaos Multiplier

In incident response, the goal is a sequence of safe, reversible steps that reduce uncertainty.

Coming Soon
Day 30

Documentation That Stays True: Using AI Without Shipping Lies

The goal is docs that behave like a product: versioned, reviewable, and tested against reality.

Coming Soon
Day 31

Day 31

Final reflection (manual release).

Coming Soon