DEV Community: Charlene

Your AI Agent’s Playbook

Charlene — Mon, 19 Oct 2026 15:33:39 +0000

The Markdown files that help your coding agent work smarter: A Data Drills Challenge

If you use AI agents or large language models (LLMs) daily, or are still experimenting with them, you'll probably have noticed that getting good, consistent results can be hit and miss.

One way to improve consistency is to create agent specifications: documented instructions that tell an AI agent how to work.

Instead of repeatedly explaining your project, the rules it should follow, and how to perform particular tasks, you can put that information into reusable files.

Welcome to the world of agent specifications and reusable AI instructions.

From Simple Prompts to Agent Specifications

You've probably heard of prompt engineering: the practice of writing clear instructions for AI.

You may also have come across context engineering, which is about making sure an AI system has the right information available to complete a task.

Agent specification files build on both ideas. They let us document important project information and create reusable rules and workflows.

Think of it as onboarding a new colleague. Instead of explaining everything from scratch every morning, you give them a project brief, a handbook, and instructions for common tasks. These reusable files help your agent understand its working environment, the project's context, and the processes it should follow.

For this challenge, we'll explore three useful Markdown files.

Three Flavours of Markdown

`AGENTS.md` — The Project Handbook

This file contains project-level instructions. It defines how an AI coding agent should work within a project, including its objectives, tools, conventions, and rules.

For example, it might describe:

The project's purpose and repository structure
Coding conventions and preferred tools
How to run tests
Important constraints and things the agent must not do

AGENTS.md is an open format for communicating project-specific instructions to AI coding agents. Think of it as a README for your agent.

`SKILL.md` — The Specialist's Instructions

A SKILL.md file provides reusable instructions, workflows, and domain-specific knowledge for a particular task.

A skill might explain how to clean a dataset, evaluate a machine learning model, or analyse financial statements using relevant accounting principles.

Under the Agent Skills specification, a skill is typically stored in its own folder with a SKILL.md file, including YAML frontmatter, and may have supporting resources.

The project can change, but the skill can remain the same.

`DESIGN.md` — The Design Brief

What should your project look and feel like?

A DESIGN.md file can define the visual identity of a project, including colours, typography, layouts, chart styling, and design principles. It helps AI agents create consistent interfaces and visual outputs.

Google's Stitch has published a specification for its DESIGN.md approach.

An important distinction: AGENTS.md and Agent Skills (SKILL.md) have published open specifications. DESIGN.md is not a universal, cross-tool standard in the same way. For this challenge, we're using it as a practical design brief.

Today's Data Drills Challenge

You're a data analyst at a subscription business. Customer churn is climbing. The executive team wants answers by Friday.

You have an AI assistant, a messy customer dataset, and a choice: prompt it as usual, or give it a playbook.

In this drill, you'll give an LLM or AI agent a data analytics task and compare two approaches:

Baseline: Use a simple prompt and assess the answer.
Playbook: Use the same prompt with agent specification files and assess whether the results improve.

Observe the differences, score both outputs, and take notes.

One prompt. Two approaches. How different are the results?

Step 1 — Get Your Data

You'll work with a fictional subscription dataset of approximately 2,000 customers, including signup dates, plan tiers, monthly usage, support tickets, and cancellation flags.

The dataset is deliberately imperfect. It includes missing churn statuses, impossible signup dates, duplicated customer IDs, and inconsistent spellings of the "Basic" plan tier.

Don't clean it yet!

In the Resources section, you'll find a Python script to generate the dataset. These data-quality problems are intentional: a basic prompt may overlook them and produce misleading churn calculations.

For example, if a churn status is missing, silently dropping that customer from the calculation could change the reported churn rate. A more careful analysis should identify and report unknown statuses separately, then explain which records are included in the calculation and why.

Spoiler alert: A well-written SKILL.md should encourage the agent to look before it calculates.

That's the point of the challenge. The messy data is the trap; your playbook should help the agent spot it.

Step 2 — Establish Your Baseline

Open a fresh conversation with your AI tool of choice. Provide the dataset and paste this prompt verbatim:

Analyse this customer dataset, identify any data-quality issues, investigate customer churn and recommend three visualisations that would help the business understand its customers.

Save the output. Don't correct the AI or ask follow-up questions. This is your baseline.

Make a note of the following:

What churn rate did it calculate? What did it assume "churned" meant?
Did it identify the intended data-quality issues? Did it find any others?
Which three visualisations did it recommend? Would they help the business make decisions?

Step 3 — Build Your Playbook

Now write three files. You'll find starter templates in the Resources section.

AGENTS.md — Define the project and its rules.

At minimum, include the business objective, the tools the agent should use, and one non-negotiable rule. For example:

Never modify the source CSV. Always state analytical assumptions explicitly.

SKILL.md — Define a reusable churn-analysis workflow.

This is the heart of the challenge. Write a skill that could work with any subscription business, not just this dataset.

Decide:

What counts as a churned customer, and what doesn't?
How should the churn rate be calculated consistently? What period and denominator are appropriate?
How should missing, duplicate, or contradictory records be handled?
How should the agent distinguish correlation from causation when discussing possible churn drivers?
Which customer segments are worth comparing, and which comparisons could be misleading?

Remember: a skill can contain domain-specific knowledge and a repeatable process.

DESIGN.md — Define how the findings should look.

Choose a colour palette, decide how churned and retained customers should be visually distinguished, and set rules for chart titles, legends, labels, and accessibility.

Be specific enough that two people following your brief would produce reasonably consistent charts.

Step 4 — Test Your Playbook

Start a fresh conversation using the same AI model.

Provide the same dataset and the same baseline prompt, plus your three files. Add this instruction:

Follow AGENTS.md for project context and rules. Apply SKILL.md for the churn analysis. Follow DESIGN.md for any visualisations.

Run the analysis and save the answer.

Tip: If you're working in a chat interface rather than an agent-enabled coding environment, attach or paste the file contents. A plain chat may not automatically discover AGENTS.md or a skill folder.

Step 5 — Score Both Answers

Now compare the response from the basic prompt with the response produced using your playbook.

Score both outputs using the criteria in the image below:

Reflection questions

Where did the playbook meaningfully improve the output?
Where did it fail or produce worse results?
How would you improve each file after reviewing the results?

Remember that agent specifications can improve consistency, but they don't guarantee correctness. Always verify the calculations and conclusions yourself.

Resources

Dataset

Generate the dummy customer dataset in Google Colab

Starter templates

Specifications and references

These are starter files, not finished solutions. You'll get more value by using your judgement and domain knowledge to adapt them.

Creating an initial set of instructions takes time, but the files can be reused and improved across projects.

A Quick Note on YAML and Markdown

Markdown (.md) is a plain-text format that's easy to read and write. It's useful for describing an AI agent's role, goals, behaviour, and instructions. Think of it as an instruction manual.

YAML (.yaml or .yml) is a structured text format often used for configuration: models, tools, settings, and metadata. Configuration only has an effect if the software reading it understands those settings.

For this Data Drills challenge, the main content of your files will be written in Markdown. If you use the Agent Skills standard, however, the SKILL.md file also includes a small YAML frontmatter section for metadata such as the skill's name and description.

You don't need to build an agent platform to complete the challenge. Focus on writing clear instructions, testing them, and evaluating what actually improves.

Vibe Coding With AI Agents -LOL

Charlene — Tue, 01 Apr 2025 16:02:12 +0000

What Are AI Agents

“AI agents are software systems that use artificial intelligence to pursue goals and complete tasks on behalf of users, often by making decisions and taking actions autonomously” - Google AI Search Slop

Ok, technically, the above definition is ‘correct.’ However, the term ‘AI agent’ is used differently among the cool kids.

Since the emergence of ChatGPT, an entirely new linguistic landscape has emerged. The field has introduced novel terminology including prompt engineers, AI agents, and vibe coding(Coding with an AI agent). To better understand these concepts, let's examine some of the most prominent 'AI agents' in use today.

Replit AI

Use natural language and chat to the agent to make apps and sites. No-coding required.

Tell Replit Agent your app or website idea, and it will build it for you automatically. It’s like having an entire team of software engineers on demand, ready to build what you need — all through a simple chat.

Take a look. It's impressive

Bolt AI

Prompt, run, edit, and deploy full-stack web and mobile apps using natural language.

Using a simple, chat-based environment you can prompt the AI agent to build whatever you want.

Bolt supports many of the most popular web languages and frameworks, as well as integration with Netlify for deployment and hosting; Supabase for database, auth, and file storage.

Using plain English…everyday language you can build a website or app. Just like that. Take a look.

Cursor

Cursor is an AI code editor with a built in agent. Once again, you can chat with the agent and get it to complete tasks for you. “Install Tailwind CSS.” Done. “Create a For Loop that loops over this array.” Sorted.

Curious? Take a look

You describe it and the AI agent will build it. What’s not to love.

Now I’m no luddite, but there is a huge caveat to all this. We need to address the🐘in the room.

The hype behind these AI agents has been alarming. We have people with no coding experience, vibe coding their way to building their first app. Building without tests and building without structure or thought. Just chatting with the AI agent and hoping something materialises.

There will be websites and apps released and out in the wild for unsuspecting people to buy and use.

Lots of people are claiming that learning to code is now a waste of time and money. Some are even saying that it’s only a matter of time before most web developers and software engineers are all made redundant.

There was a lot of gleeful chatter at the prospect of highly paid software engineers losing their jobs to someone with a £20 AI agent subscription.

However, LOL. This is wrong. You still need to know how to code. These agents are a tool, and you get the most out of them, if you know how to code.

Computational thinking, learning to code are still very profitable and valuable skills worth acquiring.

Here are a few Vibe Coders finding out the hard way, what happens when you try and cut corners.

What Can Go Wrong

Quiz Time
A vibe coder posted this in a user forum, asking for help. Hands up if you can see what’s wrong here🙋🏿‍♂️🙋🏾‍♀️🙋🏽🙋🏼‍♂️🙋🏻‍♀️🙋 There are two things that made me scream. Can you see them?

Post in the comments what are your thoughts about this vibe coder. What advise(be nice) would you give them?

The future is very bright for those who are pursuing careers in programming or data. So keep coding

Learn Python- Thank Me Later

Charlene — Wed, 19 Mar 2025 12:15:48 +0000

Python consistently ranks as the #1 language to learn if you are interested in the growing field of data analytics, data science, Machine Learning & AI. Even outside of these fields, Python is always among the top three most-used languages.

Why is Python So Popular

1. Versatility Across Industries

Python is used in web development, data science, machine learning, automation, cybersecurity, finance, and more. This makes it attractive to job seekers since they can apply it in multiple fields.

2. Simplicity & Readability

Python's syntax is beginner-friendly and resembles natural language.

Its readability makes it easy to learn and use, even for non-programmers (e.g., business analysts, researchers).

3. Strong Demand in Data Science & AI

Python dominates data science, machine learning, and AI, fields with huge job opportunities.

Libraries like Pandas, NumPy, Scikit-learn, TensorFlow, and PyTorch make it the preferred language in this space.

4. Huge Ecosystem & Libraries

Python has an extensive library ecosystem, covering web development (Django, Flask), automation (Selenium), scientific computing, networking, and more.

This reduces development time, making it attractive to companies.

5. High Salaries & Career Growth

Python developers are in high demand, leading to competitive salaries.

As AI, automation, and data science continue growing, Python skills remain a long-term investment.

6. Strong Community & Open Source Support

Python has a massive community, meaning plenty of learning resources, tutorials, and open-source contributions.

New learners can easily find help via forums, GitHub, Stack Overflow, and YouTube tutorials.

7. Automation & Scripting

Python is widely used for task automation, making it valuable for system administrators, DevOps engineers, and business analysts.

8. Cloud & Backend Development

Python powers many backend systems and cloud applications (AWS Lambda, Google Cloud Functions).

FastAPI and Flask are lightweight frameworks for microservices, making Python essential for modern web applications.

Because this is my first post, and I think we are all going to become firm friends💖. Here is a collection of Python cheatsheets. Learn it, then master Python. No, seriously. Trust me, learn Python.