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

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

What is the main idea of "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.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Your First Agent: A Walkthrough of What It Does"?
1. reasoning
2. agent trace
3. tool calls
4. observation
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Decomposition — the agent broke the goal into sub-steps.
4. Use the first answer without checking it
What should a careful learner remember about "Define the guardrails first"?
1. Before an agent runs, spell out what it's allowed to read, write, and delete. Unscoped agents can do unexpected things fast.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use the AI answer as a draft, then check it against a reliable source.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about agent trace be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about agent trace.
Which action would help you apply "Your First Agent: A Walkthrough of What It Does" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Use the first answer without checking it
4. Tool choice — it picked the right command for each sub-step (find, mkdir, mv).

← 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

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

What is the main idea of "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.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Your First Agent: A Walkthrough of What It Does"?
1. reasoning
2. agent trace
3. tool calls
4. observation
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Decomposition — the agent broke the goal into sub-steps.
4. Use the first answer without checking it
What should a careful learner remember about "Define the guardrails first"?
1. Before an agent runs, spell out what it's allowed to read, write, and delete. Unscoped agents can do unexpected things fast.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use the AI answer as a draft, then check it against a reliable source.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about agent trace be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about agent trace.
Which action would help you apply "Your First Agent: A Walkthrough of What It Does" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Use the first answer without checking it
4. Tool choice — it picked the right command for each sub-step (find, mkdir, mv).

← Back to interactive lesson