Your First Agent: A Walkthrough of What It Does

Follow a real agent run step by step — from prompt to result — and see exactly what happens inside. No code yet, just the anatomy of a successful task.

32 min · Reviewed 2026

The task

We give Claude (via Claude Code) this goal: 'Find all images larger than 2MB in my Downloads folder and move them into a folder called BigImages.' A human would do it in about five minutes. Let's watch the agent.

The trace

STEP 1
Think:  I need to list files, check sizes, filter images, create a folder, move files.
Act:    list_files('~/Downloads')
See:    42 files returned, mixed types.

STEP 2
Think:  I should filter to images and check sizes. I'll use a shell command.
Act:    shell('find ~/Downloads -type f \( -iname "*.jpg" -o -iname "*.png" -o -iname "*.heic" \) -size +2M')
See:    7 files listed with paths.

STEP 3
Think:  Now create the destination folder. Check if it exists first.
Act:    shell('mkdir -p ~/Downloads/BigImages')
See:    Folder created (or already existed).

STEP 4
Think:  Move each file. I'll confirm before running if this is risky.
Ask:    'I'm about to move 7 files into BigImages. Proceed? (y/n)'
Human:  y

STEP 5
Act:    shell('mv [the 7 files] ~/Downloads/BigImages/')
See:    Exit code 0, no errors.

STEP 6
Think:  Verify the move worked.
Act:    list_files('~/Downloads/BigImages')
See:    7 images present.

STOP
Report: 'Done. Moved 7 files totaling 23.4 MB into ~/Downloads/BigImages.'A real-world agent trace, condensed. Each step: think, act, observe.

What you just saw

Decomposition — the agent broke the goal into sub-steps.
Tool choice — it picked the right command for each sub-step (find, mkdir, mv).
Human checkpoint — it paused before a destructive action and asked permission.
Verification — after acting, it confirmed the result instead of assuming.
Reporting — at the end, it summarized what changed.

What could go wrong

Imagine step 5 failed — 'permission denied.' A dumb agent would retry forever. A good agent would read the error, reason about it ('maybe a file is locked'), try a different approach, or stop and ask for help. Handling failure is what separates toy agents from useful ones.

In the next lesson, we look at what goes wrong when the trace doesn't go this cleanly — because most of the time, it doesn't.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-agentic-first-agent-walkthrough-builders

What is the core idea behind "Your First Agent: A Walkthrough of What It Does"?
1. Follow a real agent run step by step — from prompt to result — and see exactly what happens inside. No code yet, just the anatomy of a successful task.
2. tool-calls
3. loop detection
4. Learn what "chatbot" means and why it's important
Which term best describes a foundational idea in "Your First Agent: A Walkthrough of What It Does"?
1. decomposition
2. agent trace
3. verification
4. tool-calls
A learner studying Your First Agent: A Walkthrough of What It Does would need to understand which concept?
1. agent trace
2. verification
3. decomposition
4. tool-calls
Which of these is directly relevant to Your First Agent: A Walkthrough of What It Does?
1. agent trace
2. decomposition
3. tool-calls
4. verification
Which of the following is a key point about Your First Agent: A Walkthrough of What It Does?
1. Decomposition — the agent broke the goal into sub-steps.
2. Tool choice — it picked the right command for each sub-step (find, mkdir, mv).
3. Human checkpoint — it paused before a destructive action and asked permission.
4. Verification — after acting, it confirmed the result instead of assuming.
Which of these does NOT belong in a discussion of Your First Agent: A Walkthrough of What It Does?
1. Tool choice — it picked the right command for each sub-step (find, mkdir, mv).
2. Human checkpoint — it paused before a destructive action and asked permission.
3. tool-calls
4. Decomposition — the agent broke the goal into sub-steps.
What is the key warning about "Define the guardrails first" in the context of Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. Before an agent runs, spell out what it's allowed to read, write, and delete.
4. Learn what "chatbot" means and why it's important
What is the key insight about "Always read the trace" in the context of Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. Learn what "chatbot" means and why it's important
4. Most agent platforms (Claude Code, Devin, Replit Agent) show you the trace as it runs. Watch it.
Which statement accurately describes an aspect of Your First Agent: A Walkthrough of What It Does?
1. We give Claude (via Claude Code) this goal: 'Find all images larger than 2MB in my Downloads folder and move them into a folder called BigIm…
2. tool-calls
3. loop detection
4. Learn what "chatbot" means and why it's important
What does working with Your First Agent: A Walkthrough of What It Does typically involve?
1. tool-calls
2. Imagine step 5 failed — 'permission denied.' A dumb agent would retry forever.
3. loop detection
4. Learn what "chatbot" means and why it's important
Which of the following is true about Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. In the next lesson, we look at what goes wrong when the trace doesn't go this cleanly — because most of the time, it doesn't.
4. Learn what "chatbot" means and why it's important
Which best describes the scope of "Your First Agent: A Walkthrough of What It Does"?
1. It is unrelated to agentic workflows
2. It applies only to the opposite beginner tier
3. It was deprecated in 2024 and no longer relevant
4. It focuses on Follow a real agent run step by step — from prompt to result — and see exactly what happens inside.
Which section heading best belongs in a lesson about Your First Agent: A Walkthrough of What It Does?
1. The trace
2. tool-calls
3. loop detection
4. Learn what "chatbot" means and why it's important
Which section heading best belongs in a lesson about Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. What you just saw
3. loop detection
4. Learn what "chatbot" means and why it's important
Which section heading best belongs in a lesson about Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. What could go wrong
4. Learn what "chatbot" means and why it's important

← Back to interactive lesson

Tendril · Builders · Agentic AI

Your First Agent: A Walkthrough of What It Does

Follow a real agent run step by step — from prompt to result — and see exactly what happens inside. No code yet, just the anatomy of a successful task.

32 min · Reviewed 2026

The task

The trace

STEP 1
Think:  I need to list files, check sizes, filter images, create a folder, move files.
Act:    list_files('~/Downloads')
See:    42 files returned, mixed types.

STEP 2
Think:  I should filter to images and check sizes. I'll use a shell command.
Act:    shell('find ~/Downloads -type f \( -iname "*.jpg" -o -iname "*.png" -o -iname "*.heic" \) -size +2M')
See:    7 files listed with paths.

STEP 3
Think:  Now create the destination folder. Check if it exists first.
Act:    shell('mkdir -p ~/Downloads/BigImages')
See:    Folder created (or already existed).

STEP 4
Think:  Move each file. I'll confirm before running if this is risky.
Ask:    'I'm about to move 7 files into BigImages. Proceed? (y/n)'
Human:  y

STEP 5
Act:    shell('mv [the 7 files] ~/Downloads/BigImages/')
See:    Exit code 0, no errors.

STEP 6
Think:  Verify the move worked.
Act:    list_files('~/Downloads/BigImages')
See:    7 images present.

STOP
Report: 'Done. Moved 7 files totaling 23.4 MB into ~/Downloads/BigImages.'A real-world agent trace, condensed. Each step: think, act, observe.

What you just saw

Decomposition — the agent broke the goal into sub-steps.
Tool choice — it picked the right command for each sub-step (find, mkdir, mv).
Human checkpoint — it paused before a destructive action and asked permission.
Verification — after acting, it confirmed the result instead of assuming.
Reporting — at the end, it summarized what changed.

What could go wrong

In the next lesson, we look at what goes wrong when the trace doesn't go this cleanly — because most of the time, it doesn't.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-agentic-first-agent-walkthrough-builders

What is the core idea behind "Your First Agent: A Walkthrough of What It Does"?
1. Follow a real agent run step by step — from prompt to result — and see exactly what happens inside. No code yet, just the anatomy of a successful task.
2. tool-calls
3. loop detection
4. Learn what "chatbot" means and why it's important
Which term best describes a foundational idea in "Your First Agent: A Walkthrough of What It Does"?
1. decomposition
2. agent trace
3. verification
4. tool-calls
A learner studying Your First Agent: A Walkthrough of What It Does would need to understand which concept?
1. agent trace
2. verification
3. decomposition
4. tool-calls
Which of these is directly relevant to Your First Agent: A Walkthrough of What It Does?
1. agent trace
2. decomposition
3. tool-calls
4. verification
Which of the following is a key point about Your First Agent: A Walkthrough of What It Does?
1. Decomposition — the agent broke the goal into sub-steps.
2. Tool choice — it picked the right command for each sub-step (find, mkdir, mv).
3. Human checkpoint — it paused before a destructive action and asked permission.
4. Verification — after acting, it confirmed the result instead of assuming.
Which of these does NOT belong in a discussion of Your First Agent: A Walkthrough of What It Does?
1. Tool choice — it picked the right command for each sub-step (find, mkdir, mv).
2. Human checkpoint — it paused before a destructive action and asked permission.
3. tool-calls
4. Decomposition — the agent broke the goal into sub-steps.
What is the key warning about "Define the guardrails first" in the context of Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. Before an agent runs, spell out what it's allowed to read, write, and delete.
4. Learn what "chatbot" means and why it's important
What is the key insight about "Always read the trace" in the context of Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. Learn what "chatbot" means and why it's important
4. Most agent platforms (Claude Code, Devin, Replit Agent) show you the trace as it runs. Watch it.
Which statement accurately describes an aspect of Your First Agent: A Walkthrough of What It Does?
1. We give Claude (via Claude Code) this goal: 'Find all images larger than 2MB in my Downloads folder and move them into a folder called BigIm…
2. tool-calls
3. loop detection
4. Learn what "chatbot" means and why it's important
What does working with Your First Agent: A Walkthrough of What It Does typically involve?
1. tool-calls
2. Imagine step 5 failed — 'permission denied.' A dumb agent would retry forever.
3. loop detection
4. Learn what "chatbot" means and why it's important
Which of the following is true about Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. In the next lesson, we look at what goes wrong when the trace doesn't go this cleanly — because most of the time, it doesn't.
4. Learn what "chatbot" means and why it's important
Which best describes the scope of "Your First Agent: A Walkthrough of What It Does"?
1. It is unrelated to agentic workflows
2. It applies only to the opposite beginner tier
3. It was deprecated in 2024 and no longer relevant
4. It focuses on Follow a real agent run step by step — from prompt to result — and see exactly what happens inside.
Which section heading best belongs in a lesson about Your First Agent: A Walkthrough of What It Does?
1. The trace
2. tool-calls
3. loop detection
4. Learn what "chatbot" means and why it's important
Which section heading best belongs in a lesson about Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. What you just saw
3. loop detection
4. Learn what "chatbot" means and why it's important
Which section heading best belongs in a lesson about Your First Agent: A Walkthrough of What It Does?
1. tool-calls
2. loop detection
3. What could go wrong
4. Learn what "chatbot" means and why it's important

← Back to interactive lesson