Tendril — AI Lessons for Real Life

Tendril

Final Boss: Build the Pet Namer

You have met prompts, tokens, temperature, bias, and hallucination. Now you put it all together. Your mission: build a prompt that names pets better than any random person on the internet. Let's go. 🐶

Decide what the AI needs to know (animal, color, vibe)

Write a role + task prompt

Pick a temperature (hint: go high for creativity)

Test it with three different pets

Refine based on which names feel right

Evaluate like a pro

Are the names actually different from each other?

Would a kid say them out loud and smile?

Any names that feel stereotyped? Push back on those.

Would you use any of these in real life?

The big idea: you just used role, task, format, temperature, and bias-checking all at once. You didn't just learn about AI. You used it like a builder. That's the whole Tendril move.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-game-ai-pet-namer-capstone-builders

What is the main idea of "AI Pet Namer Capstone"?

Use everything you've learned to design the ultimate pet-naming AI.
Use AI as the final authority for the whole decision
Avoid checking the answer once it sounds polished
Focus only on speed instead of judgment

Which concept is most central to "AI Pet Namer Capstone"?

temperature
prompt engineering
evaluation
iteration

Which use of AI fits this topic best?

Let the AI decide what matters without your review
Use the answer before checking whether it fits the situation
Decide what the AI needs to know (animal, color, vibe)
Use the first answer without checking it

What should a careful learner remember about "Build your mental model"?

Use AI to draft or organize ideas about prompt engineering, then verify before acting.
Skip the context so the tool can guess faster
Treat the output as private even after sharing it online
Use the answer without checking the source

You want to use AI after this lesson. What is the safest next step?

Act immediately because the AI answer is written clearly
Use the AI answer as a draft, then check it against a reliable source.
Hide uncertainty so the final answer looks cleaner
Use private or sensitive details before checking permission

How should AI output about prompt engineering be treated?

As proof that no other source is needed
As a replacement for context, consent, or expert review
As a draft or helper output that still needs human judgment and verification
As something that becomes correct when it sounds confident

Name one way to verify an AI answer about prompt engineering.

Which action would help you apply "AI Pet Namer Capstone" responsibly?

Use the tool to avoid thinking through the tradeoff
Keep going even if the output conflicts with a trusted source
Use the first answer without checking it
Write a role + task prompt

Final Boss: Build the Pet Namer

Decide what the AI needs to know (animal, color, vibe)

Write a role + task prompt

Pick a temperature (hint: go high for creativity)

Test it with three different pets

Refine based on which names feel right

Evaluate like a pro

Are the names actually different from each other?

Would a kid say them out loud and smile?

Any names that feel stereotyped? Push back on those.

Would you use any of these in real life?

The big idea: you just used role, task, format, temperature, and bias-checking all at once. You didn't just learn about AI. You used it like a builder. That's the whole Tendril move.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-game-ai-pet-namer-capstone-builders

What is the main idea of "AI Pet Namer Capstone"?

Use everything you've learned to design the ultimate pet-naming AI.
Use AI as the final authority for the whole decision
Avoid checking the answer once it sounds polished
Focus only on speed instead of judgment

Which concept is most central to "AI Pet Namer Capstone"?

temperature
prompt engineering
evaluation
iteration

Which use of AI fits this topic best?

Let the AI decide what matters without your review
Use the answer before checking whether it fits the situation
Decide what the AI needs to know (animal, color, vibe)
Use the first answer without checking it

What should a careful learner remember about "Build your mental model"?

Use AI to draft or organize ideas about prompt engineering, then verify before acting.
Skip the context so the tool can guess faster
Treat the output as private even after sharing it online
Use the answer without checking the source

You want to use AI after this lesson. What is the safest next step?

Act immediately because the AI answer is written clearly
Use the AI answer as a draft, then check it against a reliable source.
Hide uncertainty so the final answer looks cleaner
Use private or sensitive details before checking permission

How should AI output about prompt engineering be treated?

As proof that no other source is needed
As a replacement for context, consent, or expert review
As a draft or helper output that still needs human judgment and verification
As something that becomes correct when it sounds confident

Name one way to verify an AI answer about prompt engineering.

Which action would help you apply "AI Pet Namer Capstone" responsibly?

Use the tool to avoid thinking through the tradeoff
Keep going even if the output conflicts with a trusted source
Use the first answer without checking it
Write a role + task prompt