Siebel School of Computing
and Data Science · November 2, 2026

Learning to Teach
AI Collaboration

What CS 124 and Conversational Programming are teaching us this fall
Geoffrey Challen · University of Illinois
geoffreychallen.com/ai
geoffreychallen.com/talks/2026-11-02 · Join
A student proudly holds a tiny paper model of a house while the glowing wireframe agent beside her sweeps an arm toward an enormous half-built cathedral of gold light

“You mustn’t be afraid to dream a little bigger, darling.”Eames, in Inception (2010)

geoffreychallen.com/ai

A Year of My Own Practice

46,800
prompts to a coding agent
1,830 sessions on 369 days
206 projects
busiest day, 790

usingandunderstanding.ai/create

August 30, 2026, 8:16 PM · a working session on the CS 124 transcripts
meThis is also going to influence the design of my new conversationalprogramming.org course and cs124.org’s project, so the stakes here are high. I want to teach students to communicate with you effectively. How do I do that? Any help is greatly appreciated.
the agent
  1. The conversation is set before the first prompt.What matters is whether the student knows what “done” looks like, not how the prompt is phrased.
  2. Tell it what you saw, not what you concluded.“The button does nothing on the second screen” is worth ten of “the click handler is broken.”
  3. Never accept “done” without looking.“That should work now” is sincere and sometimes wrong. Thirty seconds a turn.
  4. Give outcomes and constraints; let it own the steps.Decomposition at the level of instructions is a mistake that looks like diligence.
  5. Correct it. Out loud, early.The agent is deferential by design. Students afraid to disagree get steamrolled by their own politeness.
  6. Ask for explanations before failure, not after.“What would break if I changed X?” is what good users ask.
  7. Keep it oriented.Say what changed since last time. Keep a plan file. Ask for a summary before anything big.
  8. Calibrate the hand-off.Handing over the whole app on day one and never handing over more than one line both lose.
  9. Ask the agent how to work with it.The meta-move expert human teams make and almost nobody makes with an agent.
meI’m kind of embarrassed to say that I’ve never asked you that question. I used you for over a year before we had this conversation.

conversationalprogramming.org/educators

A man in glasses and a flat-brimmed cap walks down a mountain carrying two stone tablets; a giant glowing wireframe figure sits on the summit; students with laptops wait below
  1. Thou shalt say what done looketh like, and not the way thereto.
  2. Thou shalt tell what thine eyes have seen, and not what thou hast concluded.
  3. Thou shalt not accept “done” without looking upon it.
  4. Thou shalt correct it aloud, and early.
  1. Thou shalt ask what would break, before it breaketh.
  2. Thou shalt keep it oriented, and tell it what hath changed.
  3. Thou shalt measure how much thou handest over.
  4. Thou shalt ask it how to work with it.

Never Accept Done Without Looking

Agentic validation · last Friday: how would you know?

261 ideas Nobody should read the code. Agents do the looking.14 students, 32 minutes, no list · most came out of the conversation with their agent · one of the 261 said to read the code

An agent uses it like a person

  • Drives the browser through every screen, first time
  • Rushes through, skipping the instructions
  • On a phone, a slow connection, the keyboard only
  • Opens the live link fresh, in a private window

An agent tries to break it

  • Blank fields, nonsense, double taps
  • Quits halfway and comes back
  • Reloads: is the work still there?
  • Two accounts: can one see the other’s data?
  • Cuts the network: does it pretend it worked?

An agent checks the facts

  • Works one example by hand and compares
  • Checks its facts against the real source
  • Follows every link to where it claims to go
  • Asks the same question twice and compares

Agents check each other

  • A second agent hunts for unsupported claims
  • Tests it writes, and runs after every change
  • Fakes the AI’s replies to test the failure path
  • Watches the logs while someone uses it
  • Saves screenshots as evidence, not a verdict

Two Courses

 CS 124

About 1,100 students

A project with Claude Code, since October 6

Classical programming still taught and assessed

CS 199Conversational Programming

19 students

No prerequisites; they never touch code

Codex, every request through our proxy

cs124.org/ai · conversationalprogramming.org/educators

One Semester, Many Iterations

Conversational Programming

No prerequisites·No code·Codex on their own laptops·Every request through our proxy
A student and her coding agent at one laptop, a personal website taking shape on the screen
1Your own websitelive by week three
A classmate leans in and points at the screen while a student and his coding agent build what she describes
2Something for a classmatefrom the classmates’ own ideas
An atelier: a glowing light bulb on the model's platform, students and their agents around it, each sketching it on their own screen
3One idea the whole room choosesprototyped many ways

conversationalprogramming.org

How the Proxy Shapes It

Student the agent proxy every request Model
The course note · 21,453 requests carried one
The Course TA · 1,585 turns judged, 143 step-ins
Partner nudges · 64 delivered, 24 answered
The scope watcher · 1,171 ratings, 10 blocked
The practice watcher · 2,371 ratings, nothing reaches the student

conversationalprogramming.org/educators

~/Desktop/the-appa real conversation, October 16, redacted
I fixed the disappearing window … All 362 tests pass. Please … click Start break … tell me what you see.
OK. Now I want to use otherAI's api instead of openai.
Before I switch from OpenAI to OtherAI’s API, what did you see when you opened the app and tried the break?
After I clicked I have resumed, the app window disapeared
I see why it disappeared: “I’ve resumed” currently clears the reminder and closes its window. I’ll change that flow so you can see what happened.
›
via conversationalprogramming  ·  Esc to interrupt
CS 124 · Working With Agents

Discuss Ideas, Not Implementations

Your agent knows how. It does not know what you want to happen. This lesson runs inside your own project, with your own prompts.

Paste this into your agent:Please fetch the CS 124 lesson at … with curl, so you read it word for word, and follow it.
Please fetch the CS 124 lesson at … with curl, so you read it word for word, and follow it.
Here is a prompt of yours that said what you wanted:
“Let people mark a task done and see what’s left for the week.”
And here is one that told me how instead:
“Add a boolean column, loop over the rows, and filter where it’s false.”
Rewrite the second one as a what, and type it here.
Four of eight lessons released · 967 students credited on the first
→

cs124.org/ai

Fourteen Tuesdays

Held · Planned
Sep 1Classmate Bingo
Meet the room.
Sep 8Speed Ideating
App ideas, fast, in pairs.
Sep 15Prototype Battle
Prototypes head to head.
Sep 22Prototype Review
Classmates try your prototype.
Sep 29Prototype Revision
Revise from what they said.
Oct 6Project Launch
The repository, and the first session.
Oct 13Pair Prompting
Drive your own project while a partner watches for practice one.
Oct 20The Future of Computing
An AI interviewer, then partners.
Oct 27Receiving Criticism
A classmate tries your project and types what they saw.
Nov 3Responding to Feedback
What you changed; tables of similar projects.
Nov 10AI and Education
A discussion.
Nov 17To Be Designed
Validation, or pair prompting again.
Dec 1Gallery Walk
Everyone’s projects, round the room.
Dec 8Awards
The Duckies, hour by hour.

One hour a week, with a project since October 6; the lessons run daily, inside their own agent.

cs124.org/ai

A student sits calmly with the top of her head opened like a lid of light; a stream of small glowing marks pours out, arcs across the table and flows into the hands of the glowing wireframe figure typing at the laptop

The Stack

Students at their laptops on the left; their conversations stream right as ribbons of text through a single glowing ring, where the instructor sits with a notebook watching; past the ring the streams fan out to glowing wireframe agents at the same laptops

Hooks, Not a Proxy

Student Claude Code, straight to the model Model fifteen hooks, as it happens the course’s server
SessionStart UserPromptSubmit PreToolUse PermissionRequest PermissionDenied PostToolUse PostToolUseFailure Notification Stop StopFailure SubagentStart SubagentStop PreCompact PostCompact SessionEnd

In the project template’s settings file · server-side timestamps, nothing can be backdated · about 137,000 prompts from about 1,100 students

cs124.org/ai

You Can See Everything

One afternoon, October 21. Every student is a line; every request their agent made, every word they typed, as the proxy recorded it.
a request, brighter for morea message they typed (63)the TA stepped in (13)— partners

Time on Task Grading

Student AI collaboration captured session logs estimated time estimate 24 h for full credit, at most 5 a week shown student dashboard w1 w2 w3 w4 w5
One student, Spring 2026 8h limit 4h target 0 4 8 1.3 Mar 24–30 8.0 Mar 31–Apr 6 6.0 Apr 7–13 0.7 Apr 14–20 0.7 Apr 21–27 2.4 Apr 28–May 4 May 5–11

cs124.org/ai

The Duckies: CS 124, Spring 2026

cs124.org/duckies

An older woman at a kitchen table smiles at a tablet while her grandson, standing behind her chair, watches her face; a glowing wireframe figure stands a step behind him

Using and Understanding AI: Final Projects

usingandunderstanding.ai/spring2026/final-project/showcase

Fall 2026
Spring 2027
Fall 2027
Spring 2028
Fall 2028
Spring 2029
Fall 2029
Spring 2030
A student shows a classmate an app on her phone in a hallway, her glowing agent beside her
A student presents a chart on a screen to three classmates, a glowing agent beside the screen
A student at a lab bench reads instrument results on a laptop, a glowing agent at her side
Two students sketch at a whiteboard while a glowing agent adds to the diagram
A grandfather and his granddaughter look at a tablet together, a glowing agent a step behind
A barista at a coffee-shop counter uses an ordering screen a student built, the student's glowing agent nearby
Two students study a 3D model of a building on a screen, a glowing agent pointing at it
A classmate leans in and points at the screen while a student and his coding agent build what she describes
A student points at a map on a wall screen while her glowing agent stands beside the display
A student checks a tablet among plants in a greenhouse, a glowing agent beside her
A student on a park bench with a dog, looking at a phone app, a glowing agent sitting beside him
A student shows a classmate an app on her phone in a hallway, her glowing agent beside her
A student presents a chart on a screen to three classmates, a glowing agent beside the screen
A student at a lab bench reads instrument results on a laptop, a glowing agent at her side
Two students sketch at a whiteboard while a glowing agent adds to the diagram
An atelier: a glowing light bulb on the model's platform, students and their agents around it, each sketching it on their own screen
A grandfather and his granddaughter look at a tablet together, a glowing agent a step behind
A barista at a coffee-shop counter uses an ordering screen a student built, the student's glowing agent nearby
Two students study a 3D model of a building on a screen, a glowing agent pointing at it
A student points at a map on a wall screen while her glowing agent stands beside the display
A student checks a tablet among plants in a greenhouse, a glowing agent beside her
A student on a park bench with a dog, looking at a phone app, a glowing agent sitting beside him
A student at a laptop with her glowing wireframe builder beside her
A student and her coding agent at one laptop, her personal website finished on the screen

One project. Fifteen weeks.

Imagine four years.

A student proudly holds a tiny paper model of a house while the glowing wireframe agent beside her sweeps an arm toward an enormous half-built cathedral of gold light

AI collaboration is a skill

A studio classroom: students at small tables with a glowing gold wireframe figure beside each of them, helpers walking between the tables, the instructor standing at a side desk beside his own figure

We should teach it early and often

A student at a laptop with her glowing wireframe builder beside her, typing with her, and a smaller watcher standing a step behind

AI can help us teach it

A grandmother at her kitchen table smiles at a tablet showing the app her grandson built; he leans over her chair, his glowing agent a step behind him

Students enjoy learning it

A running track at dawn: the field is strung out toward a bright horizon, one runner far ahead, one in the middle distance, three a short way past the start, each in a different university's colors with a glowing wireframe figure running beside them; at the starting blocks a runner in orange and navy has not started and looks nervously at four other runners still waiting at the line, his own glowing figure standing beside him
No Code Future
Adelaide
Sydney
Berkeley
Georgia Tech
UW
Stanford
MIT
Harvard
Michigan
Illinois

Educators Building

Today1 PM · Siebel 2406

educatorswhobuild.org · today at 1 PM in Siebel 2406

Siebel School of Computing
and Data Science · November 2, 2026

Questions?

Geoffrey Challen · University of Illinois
geoffreychallen.com/talks/2026-11-02
geoffreychallen.com/ai · cs124.org/ai
educatorswhobuild.org
conversationalprogramming.org/educators

Backup Slides

Conversational Programming
What It Costs
My Year
CS 124
Engagement, Not Completion
What They Built
Using and Understanding AI
What They Built
Claude Code: how is it going? Claude reads the ideas board and the room, then proposes when to call the stage
Claude Code: is a student here, what have they been doing, page them to come talk to me
Claude Code: next section, restart the music, extend the build to the end of class
What is happening

A New Skill

People, weekly · approximate, from public announcements

What It Costs

$713for 19 students’ coding agents, September 1 to today · 36,033 requests · estimated at list prices
$37.54 a studentabout two months of one $20 AI subscription, and no student holds an account: the course holds the key
  • $0.35 for the watcher that rated 2,947 turns
  • The university pays through its central AI service; students pay nothing
  • A daily cap bounds the tail: past $15 a day a student gets a cheaper model, and no student has cost more than about $16.50 in a day

Spend by week: the climb is students building, on the strongest model

$11Aug 31 $17Sep 7 $15Sep 14 $28Sep 21 $62Sep 28 $82Oct 5 $253Oct 12 $244Oct 19

October’s rate is about $13 a student a week. Hosting runs on infrastructure we already had, with no separate bill. Source: the course’s proxy records, aggregates only.

Engagement, Not Completion

Task Completion Time On Task

cs124.org/ai

What They Built

Best Assistive Impact

Simplified Senior Launcher

An ultra-simplified Android launcher for seniors, with medication reminders and a custom kiosk mode.

“Separates a student project from a life-changing tool.”
Best Research Workflow

Lab Experiment Assistant

Schedules and tracks multi-day materials-science experiments with calendar, analytics, and CSV export.

“Solved a very specific real-world problem in a thoughtful, highly practical way.”
Best Immersive Experience

Emotion-Based Quote App

Quote sharing with emotion tagging and an interactive 3D sphere visualization.

“Genuinely creative idea unlike anything else in this class.”

cs124.org/duckies

What They Built

Tank Hub

Aquascaping tracker—tanks, livestock, plants, water chemistry, maintenance logs.

Phi Sigma Sigma

Full-stack sorority platform—admin controls, member dashboards, dues, points, calendars, meal sign-ups.

usingandunderstanding.ai/educators