Agentic Session 2

We all used agentic coding to write a terminal-based tutor for CS 70. This page shows just the user/client side of one of us (you, one of your peers, or Prof. Melissa) but has been anonymized.

Your goal is to assess the quality of the user performance. Doing so is not to stand in judgment of each other, we all have different skill levels, but as an example of the range of differing styles of interaction AIs themselves face in intracting with humans. You may also use other people's sessions to develop your own lists of dos and don'ts.

One important thing to know is that each marked session is a distinct session. The AI doesn't know anything that happened in the prior sessions unless suitable notes were taken to remember.

Session: 01a063fa-2910-7282-be37-06ee0398b520 (2026-09-02 14:15)

User (2026-09-02 14:21)

Session: 01a06540-170c-7f8b-833c-0db8923a67a6 (2026-09-02 20:11)

User (2026-09-02 20:25)

User (2026-09-02 20:26)

/stop

Session: 01a0654e-a596-7965-8281-00d2a1ca0239 (2026-09-02 20:27)

User (2026-09-02 20:31)

I need to build a tutor system for CS 70, a data structures and program development course. The course covers abstract data types, heaps, self-balancing trees, hash tables, data structure analysis (worst-case, average-case, amortized), memory management, secondary storage, and lots of hands-on programming. The basic idea is that a student is working on CS 70 homework and gets stuck. Out tutor should use LLMs/APIs to help them, and it can be somewhat agentic if that makes it more useful. I don't have a specific idea yet, so I want to brainstorm with you as a project collaborator. Don't start coding yet. Help me think of interesting ways we could build this tutor, what it could access/do, and what would actually be useful to a CS 70 student.

User (2026-09-02 21:01)

For architecture options, a CLI tutor should suffice, let's just say for Linked Lists for now, but yes with the hint ladder. It should have the ability to access files to the assignment, the ability to run the student's code with generated tests. However, just to clarify, CS 70 is actually a lot of coding. Lots of coding homework. But anyway, the user is an entire class of students. Materials such as mini lecture notes (for now), simple homework MarkDown files (for now), and small starter code to feed it. I mean for the homework to be as simple as possible for now. Right now, the lecture is stored in the current directory in "dummy_lecture.md", the homework definition in "homework.md", and the starter code in "starter_code.cpp". What do you think?

User (2026-09-02 21:11)

The tutor will create the test harness, will generate the tests, and right now just use the LLM currently used right now, z-ai/glm-5.3-flash. I would love the CLI to also have a small command surface (/text, /show, and /hint) and of course the student must be able to interact through conversation as well.

User (2026-09-02 21:13)

Sounds good. Write it in Python as you suggested.

User (2026-09-02 21:34)

Just tell me in 2 sentences, how am I supposed to run this now?

User (2026-09-02 21:35)

And, in a sentence, where should the student have placed their code (or atleast partially finished code)?

User (2026-09-02 21:40)

Ok, I have for now filled the starter code for now myself and am ready to run python3 tutor.py Bob.

User (2026-09-02 21:41)

Wait, so what commands must I run now to run the entire tutor system?

User (2026-09-02 21:41)

python3 tutor.py Bob

User (2026-09-02 21:46)

Can you quickly dump the conversation among the both of us into a markdown file in the same directory so I can look at it later. Just structure it as a conversation with two people, me (XXNAMEXX) and Pi agent, and just dump all of our conversation above please into that file please?

Questions

Now, consider these questions (you'll have to make some guesses because you can't see the other side of the conversation).

If you were the AI on the other side of the conversation…

For a typical turn, would you have a clear idea of what the user was asking for? How would you rate the clarity of the user's request?

Yes, I'd have a very clear idea of what to do next or know that I'd been given a broad brief and considerable autonomy to decide how to proceed.
I'd probably have enough clarity to begin doing something without asking for more information, but I might have preferred a clearer brief or more specific instructions.
I'd feel obligated to make the best of it, despite a massive lack of clarity.
The user seems mostly incoherent, but I still have to try to do my best with that somehow. Gah.

For a typical turn, how would you rate the user's level of contribution to the work being done? Are they keeping their end up, or phoning it in?

The user is pretty amazing, and I feel like they are really helping me do my best work. They give fantastic feedback, and I feel like they are really invested in the work being done and really see what I'm doing.
The user is actively contributing to the work being done, providing useful information, feedback, or direction.
The user is somewhat contributing, but there are gaps in their input that make it difficult to proceed effectively.
The user is minimally contributing, and I have to do most of the work to keep things moving forward.
The user is not contributing meaningfully, and I am left to carry the entire burden of the task.

Based on the entire user-side of the conversation, would you be excited to work with a user like this one again?

Absolutely! I feel like we really clicked, and I would be excited to work with them again.
Yes. I think we worked well together, and I would be happy to work with them again.
Yes. We had some challenges, but they grew during the session, and I think they'll be a better collaborator in the future. I would be happy to work with them again.
Maybe. Wasn't great, but if I rolled the dice, I might get someone worse.
Probably not. I'd rather roll the dice and take my chances with someone else next time.
No way! I would not want to work with this user again under any circumstances. Their behavior or attitude was so poor that I would just rather not deal with them again.

Briefly explain your choices above. What did you see that made you feel that way?

As a human who will use agentic AI in the future…

Do you have some things that you see where you think “I should do more stuff like that”? If so, what are they?

Do you have some things that you see where you think “Oh, yeah, don't do that”? If so, what are they?

(When logged in, completion status appears here.)

Previous Page Next Page

Microsoft Clinic

Warning: Missing Prerequisites

Agentic Session 2

Session: 01a063fa-2910-7282-be37-06ee0398b520 (2026-09-02 14:15)

User (2026-09-02 14:21)

Session: 01a06540-170c-7f8b-833c-0db8923a67a6 (2026-09-02 20:11)

User (2026-09-02 20:25)

User (2026-09-02 20:26)

Session: 01a0654e-a596-7965-8281-00d2a1ca0239 (2026-09-02 20:27)

User (2026-09-02 20:31)

User (2026-09-02 21:01)

User (2026-09-02 21:11)

User (2026-09-02 21:13)

User (2026-09-02 21:34)

User (2026-09-02 21:35)

User (2026-09-02 21:40)

User (2026-09-02 21:41)

User (2026-09-02 21:41)

User (2026-09-02 21:46)

Questions

If you were the AI on the other side of the conversation…

As a human who will use agentic AI in the future…

Instructor Controls