Replit · October 27, 2026

Computing Education
in Human Language

A studio where nobody writes code, the agents that teach through it, and what a platform would need
Geoffrey Challen · University of Illinois
geoffreychallen.com/ai
geoffreychallen.com/talks/2026-10-27 · Join

“Anyone … can use this system with little training. Detailed computer coding is no longer necessary.”FLOW-MATIC, Grace Hopper’s team, 1958

Computing

“Anyone … can use this system with little training. Detailed computer coding is no longer necessary.”FLOW-MATIC, Grace Hopper’s team, 1958

Computing

“In a few more years millions of schoolchildren will have … a tutor as well-informed and responsive as Aristotle.”Patrick Suppes, Scientific American, 1966

Educators
the overlapComputing
Educators

How Long Reading Took

Adults who can read · percent
Our World in Data; van Zanden et al. (2014); UNESCO

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

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

One Semester, Many Iterations

A New Skill

People, weekly · approximate, from public announcements

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

Different Days, Different Shapes

Fresh EyesSep 9 · critique in pairs, four partners in a row
Round 1↻
Round 2↻
Round 3↻
Round 4↻
Built for UsSep 30 · four rounds by the clock, then the room votes
Round One
Round Two
Round Three
Round Four
Head to Head
How Would You Know?Oct 23 · independent, then the whole room, then independent
Brainstorm
Go Around↻
Build It
Feedback
ReadyOct 21 · pairs try it, build on it, new pairs, again
Get Ready
↻
Build On It
↻
Keep Building
whole roompairsindependentninety minutes across · ↻ repeats until the room moves on

conversationalprogramming.org/activities

Every Class So Far

Sep 4
Pair Prompting
Pairs trade the keyboard in rounds; notes on what they saw; the room compares.
Sep 9
Fresh Eyes
Critique each other’s sites: builder and critic, four partners in a row.
Sep 11
Going Live
Every site online by the end of the hour, then make it yours.
Sep 16 & 18
Show and Tell
Everyone presents; the whole room as one band, two days running.
Sep 25
Ask the Agent, Then Eight Sites
Ask your agent how to work with it; three rounds; then find eight sites worth learning from.
Sep 30
Built for Us, Then Head to Head
Four rounds by the clock writing ideas for each other, then head-to-head votes.
Oct 2
What's Out There
Pick an idea, research it in pairs, then go around the room.
Oct 7
What Done Looks Like
The standings; say what done looks like; partners back it up and weigh it.
Oct 9
What You Want to Happen
Build in pairs, twice, saying what should happen rather than how.
Oct 16
Say What You Saw
Build on your own, try a partner’s, report what you saw, build on it.
Oct 21
Ready
Get ready; partners try it; what they hit; build on it; new partners; try it again.
Oct 23
How Would You Know?
Brainstorm on your own, go around the room, then build it.
Oct 28
Ready to Ship
Get it ready; try it; build on it; try it again; last fixes.
Studio: buildingDesk crit: critique in pairsPin-up: critique by the roomeach card’s bar is the day’s minutes by mode; the edge is its main one

conversationalprogramming.org/activities

What is happening
~/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

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 (159)the TA stepped in (13)— partners
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
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

A Different Set of Educators

2023: computing teachers

“CompSci teachers panic as Replit pulls the plug on educational IDE”

The Register, November 21, 2023

“The extremely short notice has left many educators scrambling”

STACS, Scotland’s computing teachers, November 16, 2023

“The education market turned out to be small.”

The San Francisco Standard, January 7, 2026
Now: everyone else’s teachers
  • Teaching people who will never write code to builda studio of non-majors, this fall
  • In every discipline, for their own students34 instructors, 23 departments, one summer at Illinois
  • No legacy to migrate, no IDE to defendthe conversation is the classroom
Not a small market. Everyone.

What a Course Needs, and What Is Missing

A course needs to
Today
see the conversation
students manually share individual chats
affect the conversation
static instructions for the entire workspace
manage a studio classroom
one project at a time
assess the process
only the finished work

See the Conversation

A mock-up of a Replit workspace: a student's agent chat marked Live and shared with course staff under course consent; her app's preview in the middle; on the right, course notes pinned to turns of the conversation
What it could look like
A mock-up we drew, not a Replit feature
  • Live, shared under the course’s consent, not chat by chat
  • Watched as it happens by the partner and the instructor
  • Notes pinned to a turn, and the same stream open to a learning agent
Today: students manually share individual chats, and nothing a program can follow.

Affect the Conversation

A mock-up of a Course settings page in a Replit workspace: a semester note, today's session, per-student notes with a shown-to-student switch, step-in rules, and the disclosure every student chat showsA mock-up of the same student's chat: after the agent says fixed, it asks her to try the save again in the preview; she says it still closes; a staff-only card records the step-in rule that fired
What it could look like
A mock-up we drew, not a Replit feature
  • A semester note and today’s session, changed mid-class, applied on the next turn
  • Per-student notes, disclosed to the student
  • Step-in rules: a hook on each turn
  • The step-in, in the agent’s own voice: try it, what did you see?
  • Staff see the rule that fired; the student sees one agent
Today: instructions are workspace- or project-wide, set before the chat, and nothing can speak at a turn.

Manage a Studio Classroom

A mock-up of a room view: nineteen students' projects as cards with their state (building, stuck nine minutes, done unverified, silent seven days), activity buttons, and a staff-only room agent answering who needs me right now
What it could look like
A mock-up we drew, not a Replit feature
  • Every project in the room on one page, with its state
  • A room agent: who needs me right now?
  • Activities across the room, started from one button
Today: multiplayer lives inside one project; no roster, no view across projects, and Pro seats fifteen.

Assess the Process

A mock-up of a project review: the student's conversation across three weeks as a strip of who typed and what was accepted, one turn opened, how far she got from a shared starter, and a process rubric drafted by a review agent with a done the agent re-checked
What it could look like
A mock-up we drew, not a Replit feature
  • The conversation is the record: who typed, what was accepted, the step-ins
  • A rubric for the process, drafted by a review agent
  • A “done” you can doubt, re-run in a clean preview
  • Course data outlives the plan, with export
Today: assignments, submissions and review left with Teams for Education in 2024; nothing assesses the process.

Exercises Only a Platform Can Run

hot-potato prompting
same start, how far
fix the bug, how fast
you own the code and the conversation
The next billion technology creators
Replit · October 27, 2026

Thank you

Geoffrey Challen · University of Illinois
geoffreychallen.com/ai
geoffreychallen.com/talks/2026-10-27
conversationalprogramming.org/educators
Discussion