TCEA Professional Development

Vibe-Coding
in the K–12 Classroom

A curriculum map of AI-powered student projects aligned to Texas TEKS — from Kindergarten through Grade 12.

Grades K–2 Grades 3–5 Grades 6–8 Grades 9–12 Texas TEKS–Aligned

What Is Vibe-Coding?

Vibe-coding means describing what you want in plain language and letting AI generate it — then iterating, evaluating, and improving the result. For students, it's not a shortcut. It's a thinking scaffold.

At each grade band, the complexity shifts: in K–2, the teacher holds the prompt and the class shapes the output together. By high school, students write specs, deploy working apps, and defend every AI-assisted decision publicly.

Every project below requires students to prompt → evaluate → revise. AI produces the first draft. Students are responsible for everything that ships.

Prompt

Students describe what they need in precise language — the first act of computational thinking.

Evaluate

AI output is never accepted at face value. Students fact-check, annotate, and identify errors.

Revise

Students improve the output using content-area knowledge — the real learning moment.

Publish

At every grade band, work is shared — with the class, a community partner, or the public.

Curriculum Map

How vibe-coding evolves from guided exploration to professional-grade production

K–2
Grades K–2
Guided Exploration
Teacher holds the prompt
Class shapes output together
Evaluate & illustrate
No student logins needed
3–5
Grades 3–5
Scaffolded Agency
Students type own prompts
Iterate on AI output
Fact-check & annotate
Data-first editorial
6–8
Grades 6–8
Code & Critique
Write & run real code
Debug AI-generated scripts
Build functional tools
Red-team AI outputs
9–12
Grades 9–12
Ship & Defend
Deploy public-facing apps
Real datasets & APIs
Portfolio-ready work
Present to real audiences
K–2

Grades K–2 — Guided Exploration

The teacher controls the prompt. The whole class shapes the output together. No student logins required — just a projected screen and curious minds.

📖 ELA / Reading

My Sight Word Story

Kids dictate a 3-sentence story using weekly sight words. AI generates it with illustrations. Students illustrate a favorite part by hand.

Book CreatorDiffit
TEKS: ELA K.6, 1.6 — high-frequency words in context

Rhyme Machine

Students say a word, ask AI to make a rhyming poem, then illustrate one stanza. Class compares which rhymes feel natural vs. forced.

ChatGPT (teacher-led)Adobe Express
TEKS: ELA K.2.A — phonological awareness, rhyme
➕ Math

Shape Town Builder

Kids describe a scene ("a house made of squares and a triangle roof") → AI or tool generates it. Students label each shape and its attributes.

Google SlidesCanva AI
TEKS: Math K.6.A, 1.6.A — 2D shapes and their attributes

My Number Book

Students dictate: "Show me 7 frogs." AI generates image + equation. Class builds a counting book, one number per page.

Book CreatorChatGPT + Slides
TEKS: Math K.2.B — counting sets, numerals
🔬 Science

Weather Reporter Bot

Kids tell AI what today's weather looks like; it writes a weather report they read aloud and record. Teacher uses a fill-in prompt template to scaffold.

Claude / ChatGPTFlip
TEKS: Sci K.8.A, 1.8.A — observing and describing weather

Life Cycle Slideshow

Students narrate each stage of a butterfly or frog life cycle → AI generates one sentence + image per slide. Students sequence and label.

Book Creator AICanva
TEKS: Sci 2.12.A — life cycles of organisms
🏘️ Social Studies

Community Helper Helper

Kids describe a job; AI writes what that person does and generates an image. Class builds a "Community Helpers" book together.

Book CreatorGoogle Slides
TEKS: SS K.12, 1.7 — roles in the community

Texas Symbols Museum

Each student picks a Texas symbol (bluebonnet, mockingbird, Lone Star), prompts AI for a "museum label" description, then designs the label.

CanvaChatGPT (teacher-led)
TEKS: SS 2.12.A — state symbols and their significance
💡 Non-Obvious Idea
💡

Fix My Robot's Mistake

Give students an AI-generated paragraph with one deliberate factual or grammar error. Their job: find it and fix it before the class "publishes" the work. Builds critical AI literacy from day one, aligns to ELA revision TEKS, and teaches kids that AI isn't always right — without a single lecture about it.

Claude / ChatGPT (teacher-generated)Google Docs
3–5

Grades 3–5 — Scaffolded Agency

Students type their own prompts with scaffolding, iterate on AI outputs, and evaluate results critically. The loop is always: Student → AI → Student. AI drafts; students publish.

📖 ELA / Reading & Writing

AI Writing Partner Showdown

Students write a paragraph first, give the same prompt to AI, compare outputs side by side, and revise their own draft — not the AI's version.

Claude / ChatGPTGoogle Docs
TEKS: ELA 3.11, 4.11, 5.11 — writing process, revision

Summarize This — But Make It Accurate

Students paste a nonfiction article, ask AI to summarize, then fact-check the summary against the original and mark every error they find.

Claude / ChatGPTDiffit
TEKS: ELA 3.8, 4.8, 5.8 — main idea, supporting details

Genre Transformer

Take one historical event or science concept and prompt AI to write it as a poem, then a news article, then a diary entry. Students analyze how genre changes meaning.

ChatGPT / ClaudeGoogle Docs
TEKS: ELA 3–5 — multiple text genres, author's craft
➕ Math

Build a Word Problem Factory

Students prompt AI to generate 5 problems at grade level, solve them, rate which were too easy/hard/just right, then write a better one themselves.

Claude / ChatGPTGoogle Forms
TEKS: Math 3.4, 4.4, 5.3 — operations, fractions

Data Story Generator

Students collect real classroom data, enter it, prompt AI to describe the trend, then build their own graph and write their own interpretation.

Google SheetsCanva / InfogramClaude
TEKS: Math 3.8, 4.9, 5.9 — data representation

Math Explainer Video Script

Students prompt AI to write a script explaining a concept (area vs. perimeter, equivalent fractions), then record themselves — correcting AI errors before filming.

Claude / ChatGPTFlip
TEKS: Math 3.6, 4.5, 5.4 — geometry, fractions
🔬 Science

Food Web Simulator Prompt

Students describe a Texas ecosystem, ask AI to generate a food web description, then diagram it manually and identify any missing or wrong connections.

Claude / ChatGPTCanva / Slides
TEKS: Sci 3.9, 4.9, 5.9 — ecosystems, food webs

Matter Matters Explainer

Students prompt AI to explain a states-of-matter scenario, then annotate the output — highlighting what's correct, incomplete, and what needs a diagram.

Claude / ChatGPTBook Creator
TEKS: Sci 3.5, 4.5, 5.5 — physical properties, changes

Design an Adaptation

Students invent a fictional animal for a specific Texas biome, prompt AI to elaborate on survival advantages, then create a field guide entry with illustrations.

ChatGPT / ClaudeCanva
TEKS: Sci 3.9.B, 4.9.B — adaptations and survival
🗺️ Social Studies

Texas History Podcast Script

Students research one Texas history figure, feed notes to AI with "turn these into a 90-second podcast script," then revise for accuracy before recording.

Claude / ChatGPTFlip / Audacity
TEKS: SS 4.2, 4.3 — Texas history figures and events

Economic Choices Simulator

Students describe a simple business scenario and ask AI to model three economic decisions. They evaluate trade-offs and justify their best option in writing.

Claude / ChatGPTGoogle Slides
TEKS: SS 3.9, 4.9 — scarcity, opportunity cost

U.S. Regions Travel Brochure

Students prompt AI to draft a travel brochure for an assigned region, fact-check it against a textbook or vetted source, then design the final version.

Claude / ChatGPTCanva
TEKS: SS 5.9 — U.S. geographic regions
💡 Non-Obvious Idea
💡

Prompt Grader

Flip the dynamic entirely. Give every student the same AI output and several different prompts that could have produced it. Their job: figure out which prompt generated that response and rank all prompts from weakest to strongest. No coding, no tool login — just analytical thinking about how language shapes AI output. It builds prompt literacy, inference skills, and argument writing simultaneously, in one class period with zero setup.

Claude / ChatGPT (teacher-generated)Google Docs
6–8

Grades 6–8 — Code & Critique

Students write and run actual AI-generated code, build functional tools, and work with real data. The standard: if it isn't run, it hasn't been tested. One working script they debugged beats ten AI outputs they passively accepted.

📖 ELA / Reading & Writing

Bias Detector

Students find two articles covering the same event from different outlets. They prompt AI to analyze both for loaded language, then write their own comparison arguing which source is more reliable — with specific evidence.

ClaudePerplexityGoogle Docs
TEKS: ELA 6.10, 7.10, 8.10 — author's purpose, point of view

AI-Assisted Research, Human-Controlled Argument

Students use AI to generate a counterargument to their own thesis, then write a rebuttal. Forces them to steelman the opposition before finalizing their essay.

Claude / ChatGPTGoogle Docs
TEKS: ELA 6.11, 7.11, 8.11 — argumentative writing, counterclaim

Literary Analysis Chatbot

Students vibe-code a simple Q&A bot "trained" on a class novel's plot and themes via system prompt. They test it and document where it fails — and why.

Claude ProjectsReplit
TEKS: ELA 6–8 — literary elements, theme, character analysis
➕ Math

Ratio & Proportion Calculator App

Students describe a real-world ratio problem, ask AI to generate a working Python or JavaScript calculator, run it, find edge cases where it breaks, and fix one thing themselves.

ReplitGoogle ColabClaude
TEKS: Math 6.4, 7.4 — ratios, rates, proportional relationships

Data Dashboard Builder

Students import a real dataset, prompt AI to generate a visualization script, run it, and present findings with a written interpretation they authored themselves.

Google ColabFlourishClaude
TEKS: Math 6.12, 7.12, 8.11 — statistical representations

Equation Explainer Bot

Students prompt AI to solve a multi-step equation and explain every step. Then they swap problems with a partner and verify whether the AI's reasoning is correct or flawed.

Claude / ChatGPTDesmos
TEKS: Math 7.10, 8.8 — equations, algebraic reasoning

Geometry Proof Checker

Students write their own geometric proof, then prompt AI to check their reasoning. They annotate where AI agrees, disagrees, or introduces an error of its own.

ClaudeGeoGebra
TEKS: Math 8.10 — geometric reasoning, transformations
🔬 Science

Cell City Simulator

Students describe a city where buildings represent organelles. AI generates the narrative. Students code a labeled HTML diagram — then test whether every label is biologically accurate.

Claude / ChatGPTReplit (HTML)
TEKS: Sci 7.5 — cell structure and function

Ecosystem Impact Modeler

Students describe a change to a Texas ecosystem and prompt AI to model ripple effects through a food web. They evaluate the response against a scientific source and flag inaccuracies.

Claude / PerplexityCanva / Slides
TEKS: Sci 7.10 — ecosystems and environmental change

Punnett Square Generator

Students describe a genetic cross in plain language, ask AI to generate a Punnett square and predict phenotype ratios, then verify manually. Advanced: prompt AI to generate a Python script that does it automatically.

Claude / ChatGPTReplit (Python)
TEKS: Sci 7.6 — heredity and genetics

Chemical Reaction Predictor

Students describe two substances combining, ask AI to predict the reaction type, cross-check with a simulation tool, and write a lab-style report on whether AI was right.

Claude / ChatGPTPhET Simulations
TEKS: Sci 8.5 — physical and chemical properties
🗺️ Social Studies

Primary Source Interrogator

Students paste a primary source and prompt AI with historical thinking questions: Who wrote this? Who benefits? What's missing? They write a sourcing analysis using AI output as a starting point only.

Claude / NotebookLMGoogle Docs
TEKS: SS 8.29 — historical thinking, primary/secondary sources

World Geography Data Story

Students pick two countries, pull real data (population density, GDP, climate), prompt AI for a comparative analysis, fact-check three claims, then build a corrected infographic.

Perplexity / ClaudeCanva
TEKS: SS 6.9, 6.21 — human-environment interaction

Propaganda vs. Persuasion Analyzer

Students feed AI examples of WWII-era propaganda and modern advertising, ask it to identify persuasion techniques, then write an argument about where persuasion ends and manipulation begins.

Claude / ChatGPTGoogle Docs
TEKS: SS 7.28, 8.29 — media literacy, citizenship

Build a Constitution Simulator

Students vibe-code a decision-tree app: users answer questions about rights → app outputs which constitutional amendment applies. Students write the logic; AI generates the code.

Replit (Python or JS)Claude
TEKS: SS 8.16, 8.17 — U.S. Constitution, Bill of Rights
💡 Non-Obvious Idea
💡

Red-Team the Chatbot

Students are assigned to break an AI tool using their content-area knowledge. Their job: find three prompts that get the AI to produce a confident but factually wrong answer on a topic they've studied. They document each failure, explain why the AI was wrong using evidence, and present it to the class. This requires genuine subject-matter knowledge to execute well — expertise beats the tool. No rubric needed. Proving AI wrong is the assessment.

Claude / ChatGPT (sandboxed)Google Docs (documentation)
9–12

Grades 9–12 — Ship & Defend

Students build deployable tools, work with real APIs and datasets, and produce portfolio-ready work. The bar: public and defensible. If it isn't deployed, published, or presented to a real audience, it hasn't cleared the standard.

📖 ELA / Research & Writing

Synthesize or Plagiarize? The Source Audit

Students write a research paper using AI assistance throughout, then conduct a documented audit of every AI contribution: what was used, changed, rejected, and why. The audit is a second deliverable.

Claude / ChatGPTGoogle Docs (version history)
TEKS: ELA I–IV research strand — synthesis, source evaluation

Technical Writing for a Real Audience

Students identify a genuine problem in their school or community, vibe-code a one-page technical brief, and present it to an actual decision-maker — principal, city council member, or nonprofit director.

ClaudeCanva / Google Docs
TEKS: ELA III/IV — technical writing, purpose and audience

AI-Generated Text Forensics

Students receive five anonymous text samples — human-written, AI-generated, and hybrid. Using close reading only (no detection tools), they argue in writing which is which and why.

Claude (teacher-generated samples)Google Docs
TEKS: ELA 9–12 — author's craft, style, rhetorical analysis
➕ Math

Predictive Model Builder

Students select a real dataset (Texas climate, local property taxes, sports stats), write a plain-language spec for a regression model, prompt AI to generate the code, run it, and present findings with appropriate statistical caveats.

Google Colabpandas / matplotlib / scikit-learnClaude
TEKS: Algebra II / Statistics — regression, correlation (A2.4, Stats 3)

Function Behavior Explorer App

Students describe a family of functions, prompt AI to build an interactive Streamlit app with adjustable parameters, and write a mathematical commentary explaining each behavior.

Replit / StreamlitClaudeDesmos
TEKS: Precalculus / Algebra II — function families (PC.2, A2.2)

Personal Finance Simulator

Students vibe-code a compound interest/loan amortization calculator with their own inputs, run three real financial scenarios, and present a recommendation report to a "financial advisor" panel.

Replit (Python or JS)ClaudeGoogle Slides
TEKS: Financial Math FM.1, FM.2 — compound interest, debt

Statistics Lie Detector

Students find three real published statistics used in news or advertising, prompt AI to explain how each could mislead, then write a mathematical rebuttal. Final product: a public-facing fact-check post.

PerplexityClaudeCanva
TEKS: Statistics — sampling, bias, misleading representations (Stats 1, 4)
🔬 Science

Gene Expression Literature Review Bot

Students load three to five peer-reviewed abstracts into a Claude Project, query it systematically, identify gaps and contradictions across sources, then write a synthesis that goes beyond any single article.

Claude ProjectsGoogle ScholarGoogle Docs
TEKS: Biology — gene expression, DNA, biotechnology (Bio.6, Bio.7)

Climate Data Dashboard

Students pull real NOAA or NASA climate data, prompt AI to generate a Python visualization pipeline, and build a public-facing dashboard showing one specific trend. They write the interpretive narrative themselves.

Google Colab / ObservableStreamlit / GitHub PagesClaude
TEKS: Environmental Systems — climate, human impact (ES.2, ES.10)

Stoichiometry Checker App

Students describe a chemical reaction in plain English, prompt AI to generate a stoichiometry calculator, test it with known reactions, and document the chemistry behind each failure it produces.

Replit (Python)ClaudePhET
TEKS: Chemistry — stoichiometry, limiting reagents (Chem.8)

Physics Simulation Builder

Students write a spec for a projectile motion or wave interference simulation, prompt AI to generate it as a web app, test it against known physics outcomes, and annotate every discrepancy from reality.

Replit (p5.js)ClaudePhET
TEKS: Physics — motion, forces, wave behavior (Phys.4, Phys.7)

Medical Case Study Analyzer

Students receive a fictional patient case, prompt AI for a differential diagnosis, then evaluate it against anatomy/physiology knowledge — identifying where AI reasoning is sound vs. where it would harm a real patient.

Claude / ChatGPTGoogle Docs
TEKS: Anatomy & Physiology — body systems, homeostasis (A&P 1–4)
🗺️ Social Studies

Policy Brief Generator + Critic

Students pick a current Texas legislative issue (TRAIGA, school vouchers, water rights), prompt AI to draft a brief from one stakeholder's perspective, then write a rebuttal from an opposing stakeholder using real legislative language.

Claude / PerplexityGoogle Docs
TEKS: Government — legislative process, civic participation (Gov.18, Gov.22)

Historical Turning Point Simulator

Students pick a historical decision point, prompt AI to model three alternate outcomes based on changed variables, then argue in writing which alternate history is most plausible and why.

ClaudeGoogle Docs
TEKS: WH.29, USH.29 — causation, historical thinking

Economic Inequality Data Story

Students pull real Census or FRED economic data, prompt AI to build a visualization and narrative, fact-check three claims, then publish a corrected data story as a public blog post or infographic.

FRED / Census dataGoogle Colab / FlourishCanva
TEKS: Economics — income distribution, policy tradeoffs (Econ.4, Econ.9)

Geopolitical Risk Briefing

Students prompt AI to generate an intelligence-style briefing for an assigned world region, cross-check every factual claim against two vetted sources, and publish a corrected, sourced version.

Perplexity / ClaudeCanva
TEKS: World Geography — political systems, global issues (WG.18, WG.20)
💻 Computer Science / CTE

Vibe-Code a Real MVP

Students write a one-page product spec for a tool solving a real school or community problem, use AI to generate the full codebase, deploy it publicly, and pitch it — including what they changed from the AI's first output and why.

Cursor / ReplitClaude / GitHub CopilotVercel / GitHub Pages
TEKS: CS I/II — program development, deployment (CS.4, CS.6)

Prompt Injection Red Team

Students attempt to manipulate an AI system into producing outputs it's designed to refuse — using only text. They document every successful exploit, explain the mechanism, and propose one mitigation strategy. Ethical guardrails defined by teacher upfront.

Claude / ChatGPT (sandboxed)Google Docs
TEKS: CS — cybersecurity, ethics, system vulnerabilities (CS.7, CS.8)

Train a Text Classifier

Students collect 50 labeled examples in a content area, prompt AI to generate a Python classification model, run it on new examples, and report accuracy with a confusion matrix.

Google Colab + scikit-learnClaude (code scaffolding)
TEKS: CS II — algorithms, ML concepts, data classification (CS.5)

Automate Something Real

Students identify a repetitive task a teacher or administrator actually does and build a working automation. Deliverable: working tool + one-page implementation guide written for a non-technical user.

Python / Clauden8n / Google Apps Script
TEKS: CS I/II — problem-solving, implementation, documentation (CS.4, CS.6)
💡 Non-Obvious Idea
💡

The AI Consultant Engagement

Students are hired (fictionally) as AI consultants by a real local organization — a school district, small business, city department, or nonprofit. Their deliverable is a professional recommendations report: what AI tools the organization should adopt, which tasks AI should not handle, what the risks are, and what staff training would be required. They present to an actual representative of that organization when possible.

This is the only project that integrates every content area simultaneously — research, writing, data, ethics, economics, and communication — and produces something with genuine external value. It also directly mirrors what many of these students will be asked to do in their first professional job within five years.

Claude / Perplexity Canva (report design) Google Slides (presentation)