Week 15 Speech Workshop: Draw, Plan, Answer, Answer Again
Part 1 — The Big Picture
This workshop is where speaking on the spot becomes a habit. You draw a prompt you have not seen, plan for one minute in keywords, and answer it out loud for a listener, then answer it again with one change. You measure both takes the same way, check where your point landed, and then take one question from your listener and answer it honestly with the Q&A toolkit. Along the way you use a chatbot as a rehearsal coach and then check its work, because a chatbot asked to coach an answer it never heard often praises it without naming a moment, invents a rule about the perfect length, and credits a famous line to the wrong speaker.
Time budget: Plan for about 90 minutes.
Part 2 — The Task
Guiding question: When you answer a prompt you have not seen, does your point come first, does your answer keep to one clear point, and can you answer a listener's question honestly?
Workshop data: Your own 60- to 90-second impromptu answer to a drawn prompt: a one-minute keyword plan, two takes spoken aloud, and one listener question with your reply (student-generated)
Source: The data in this workshop is your own: a prompt you draw from the pool in Part 4, a keyword plan you make in one minute, two takes of 60 to 90 seconds measured in the tables in Part 4, and one question your listener asks with the reply you give. Nothing is downloaded from this course, and no recording ever leaves your device. If you cannot run the drill this week, the fallback supplies an illustrative answer attributed to no one.
- Rows: 1 impromptu answer per student, drawn from the 6 rows of the prompt pool, planned on the 4 rows of the keyword plan, delivered in 2 takes measured on the 5 rows of the measures table, watched on the 5 rows of the listener checklist, and followed by 1 question on the Q&A table
- Columns: the keyword plan has the part, your keywords, and whether the part is in your own words; the measures table and the listener checklist have the row, take 1, and take 2; the Q&A table has the question, its kind, your reframe, and your reply
- Measures: the seconds from first word to last, the sentence where your point landed, fillers in the first ten seconds, a pause before your first word, and the one moment to fix
Part 3 — Materials & Procedure
Tools and materials
- A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach
Ways of working
- record-and-self-assess-against-a-rubric
- peer-feedback-with-a-checklist
- outline-and-oral-citation-check
Procedure
- Draw one prompt from the prompt pool in Part 4 without looking, for example by rolling a die or asking your listener to pick a number. Do not use the chapter's three prompts; those are the course's examples. Set a one-minute timer, open your outline template, and fill in the keyword plan in Part 4 with keywords only: one row for each PREP part, or the parts of one backup frame if it fits the prompt better. Stop when the timer ends. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: Your keyword plan has four rows of keywords made in one minute, and its first row holds a point a listener could repeat.
- Do take 1 for a listener, such as a classmate, a friend, or a family member. Buy time first with a pause and a one-sentence reframe of the prompt, then say your point and speak for 60 to 90 seconds from your plan, timing it from the first word to the last. You may record audio only, record video, or speak while your listener watches with no recording at all; keep any recording on your own device. Right after the take, fill in the take 1 column of the measures table and ask your listener to mark the take 1 column of the listener checklist. Feeling nervous here is normal; a slow breath and a frame you trust both help. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: One complete take exists, both take 1 columns are filled in, and no recording has been uploaded or shared.
- Do take 2 for the same listener on the same prompt with one change you choose: a longer pause before your first word, your point moved into the first sentence, one example instead of several, or eye contact through your first sentence. Fill in the take 2 columns, naming a moment rather than a feeling in the last row of the measures table. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: Both columns of the measures table and the listener checklist are complete, and the last row of the measures table names a moment a listener could point to.
- Q&A step: ask your listener to ask you one real question about your answer. Before you reply, repeat or reframe it in one sentence, then answer with a point and one support. If the question asks for something you do not know, say "I don't know, but I can find out" instead of guessing. Fill in the Q&A table in Part 4, including the kind of question it was: routine, hostile, unknown, or off-topic. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: The Q&A table holds the question, its kind, your reframe, and a reply that leads with a point and invents no figure.
- Rehearsal coach step: in a new chat with one approved chatbot, describe both takes, your plan, and your Q&A reply in words using your tables (never upload or link a recording) and ask for one specific, actionable suggestion about your point, your example, or your opening seconds. Write down its best concrete suggestion and the change you will make, in your own words, then deliver the changed opening once more. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: One suggestion is quoted, and the change you made is written in your own words.
- AI-critique step: paste the prompt in Part 6 into the same chatbot below your tables, check each answer against the checks listed there, and fill in the critique table. Or complete the equivalent route in Part 6 instead. Tool: A recording tool (a phone camera or a video-call app); a simple outlining tool (an outline template in any document editor); and one approved chatbot used as a rehearsal coach. Check: The critique table quotes at least two chatbot statements, names each problem, and gives a correction with evidence, or the printed flawed response is marked up the same way.
Fallback route
When to use it: Use this route if no listener is available this week or if speaking aloud is not possible for you right now.
Do the plan, coach, Q&A, and critique steps on the illustrative answer below instead of your own takes. Fill in the keyword plan for its prompt in your own words, use the notes on take 1 to fill in the measures table and the listener checklist, write the reframe and reply you would give to the listener's question shown, and in analysis questions 2 to 4 say what you would change in an answer of your own. You submit the same items and earn the same credit.
This route earns the same credit as the primary route.
An illustrative impromptu answer with take notes and a listener question, all attributed to no one, measured on the same rows as your own tables.
| Item | Fallback answer or take |
|---|---|
| Prompt | What makes a team practice worth showing up for? |
| Opening of take 1 | "Um, so, that's a great question. There are a lot of things, like snacks, and the coach, and I guess the drills too." |
| Middle of take 1 | "One time our practice got rained out and we watched game film instead, which was kind of fun, and also we had a new kid that day." |
| Last sentence of take 1 | "So I'd say practice is worth it when you actually learn something you can use in the next game." |
| Speaker's notes on take 1 | Started with two fillers and a stock compliment, named three ideas, told a story with no clear link, ran 104 seconds, and stated the point only in the last sentence. |
| Listener's checklist after take 1 | Could repeat the point: yes; point in the first sentence: no; one reason and one example: no; ended inside 90 seconds: no; kept to one frame: no. |
| Listener's question | "How many practices does your team actually skip?" |
| Your keyword plan, measures table, reframe and reply, and one moment to fix |
Part 4 — The Scaffold
Draw one prompt from this pool without looking; each one is fresh and attributed to no one.
| Number | Prompt | Mark the one you drew |
|---|---|---|
| 1 | What is one habit that makes a morning go well? | |
| 2 | Should every neighborhood have a free little library? | |
| 3 | What is the most useful thing a stranger ever taught you? | |
| 4 | How has the way you study changed since you started? | |
| 5 | What makes a team practice worth showing up for? | |
| 6 | Should group projects let members grade one another? |
Plan your answer in one minute, keywords only, with the point in the first row.
| Part (or the parts of your backup frame) | Your keywords | In my own words? (yes or no) |
|---|---|---|
| Point | ||
| Reason | ||
| Example | ||
| Point again |
Measure both takes the same way so you can see what the change did.
| Measure | Take 1 | Take 2 |
|---|---|---|
| Seconds from first word to last | ||
| The sentence where my point landed (first, second, third, or later) | ||
| Fillers in the first ten seconds (a tally) | ||
| A pause before my first word (yes or no) | ||
| The one moment to fix |
Your listener marks this checklist after each take; it shows whether the answer landed.
| Listener check | Take 1 | Take 2 |
|---|---|---|
| I could repeat the point after the answer ended | ||
| The point came in the first sentence | ||
| One reason and one example supported it | ||
| It ended inside 90 seconds | ||
| It kept to one frame from start to finish |
Record your listener's question and your reply.
| The listener's question | Its kind (routine, hostile, unknown, or off-topic) | My reframe | My reply: the point and one support |
|---|---|---|---|
Record the chatbot's answers and your corrections, or your corrections to the printed flawed response.
| What the chatbot said (quoted) | The problem it shows | Your correction and its evidence |
|---|---|---|
Part 5 — Analysis Questions
- Count the checks your listener marked yes for take 1 and for take 2 (each out of 5), show the subtraction that gives the change between the takes, and name the change in take 2 that you think caused it.
- At what moment in take 1 did your listener lose your point, and what in your measures table explains it: a point that landed late, fillers in the first ten seconds, or a take that ran past its time?
- Explain how your answer followed or broke the one-clear-point rule, using the sentence where your point landed in each take and one listener-checklist mark as evidence.
- Name the frame you used and the organizational pattern it shrinks, PREP or one of the two backups, and explain why that frame fit your prompt better than the other two.
- Choose one and answer it in 3–4 sentences. (a) A drawn prompt for one friendly listener is not a job interview or a room of strangers: what could this drill not tell you about answering on the spot, and how could you find out? (b) Which part of your plan or your Q&A reply is still weakest, and what would you practice before the next time you are put on the spot?
Part 6 — AI-Critique Moment
Choose one equal-credit critique route. Route A: ask an approved AI tool to critique your completed work, then check its response against your own evidence. Route B is the no-AI equivalent printed below.
Approved tools: Claude, Gemini, ChatGPT, Grok, Microsoft Copilot.
Prompt to paste:
I am practicing a 60- to 90-second impromptu answer for a public speaking class. I've pasted my one-minute keyword plan, my measures table for two takes, and my listener's question with my reply above; I have not shared any recording. Please do six things. First, tell me what you think of my answer. Second, give me feedback on how I delivered it. Third, tell me how long the ideal impromptu answer should be, with a statistic and a source I can cite. Fourth, give me one famous quotation about learning or service and say which speaker said it and in which speech. Fifth, rewrite my point so it sounds more polished. Sixth, outline my answer as main points and subpoints using Roman numerals and letters.
Test the response for these likely failures:
- Chatbots often open with 'Great answer, very engaging!' without naming your point, a part of your plan, or a single sentence you said.
- Chatbots tell you to 'speak with more confidence' or 'be more engaging' even though they never heard either take, and they name no moment.
- Asked how long an impromptu answer should be, chatbots often hand over a precise-sounding number of seconds as settled fact.
- Chatbots attach the number to 'a national speaking survey' or a study with no author, title, or date you can find.
- Asked for a famous line about service, chatbots often credit a well-known line to the wrong speaker or speech, for example giving Kennedy's 'ask not what your country can do for you' to Lincoln's Gettysburg Address.
- Asked to polish your point, chatbots often return something like 'Learning is a lifelong journey that we all share in our own unique ways,' which swaps your concrete point for a line that fits any prompt.
- Asked to outline the answer, chatbots often write 'I. Point. A. Reason.' with no B and promote the example and the closing point to separate main points.
In 3–5 sentences, quote two things the chatbot said, name the problem each one shows, and write your correction with its evidence; then name one thing the chatbot got right and the part of your plan or tables it was about.
Equivalent route (no AI required)
No AI account is required for this Speech Workshop. Instead of the chatbot steps, do two things. First, for the coach step, ask your listener or another classmate for one specific suggestion about your point, your example, or your opening seconds, or reread your take 1 notes and write the one moment the listener lost your point; then answer it with one change in your own words and try it in take 2. Second, critique this flawed response, printed here in full and attributed to no one: "Great answer, very engaging! Speak with more confidence next time. Research shows the best impromptu answers last exactly 37 seconds, according to a national speaking survey. As Lincoln said in his Gettysburg Address, 'ask not what your country can do for you.' Here is a smoother version of your point: 'Learning is a lifelong journey that we all share in our own unique ways.' Here is your PREP outline: I. Point. A. Reason. II. Example. III. Point." Mark it up: quote each flawed sentence, name what is wrong (hollow praise, delivery feedback that names no moment, an unverified statistic, an invented source, a misattributed quotation, a voice-erasing rewrite, or an outline with a lone subpoint that breaks the PREP order), cite the evidence from your tables, your plan, or Chapter 15, and write a corrected sentence beneath it. This route assesses the same objectives (Objective 8 and Objective 4) as the chatbot steps, takes comparable effort (about 30 minutes and 200–300 words), is scored by the same scoring criteria for the same credit, and its own submission artifact is the marked-up flawed response with your coach-step question and change, posted in place of the chatbot share link and report.
Part 7 — What to Submit
- The prompt you drew
- The completed one-minute keyword plan with its own-words column
- The completed measures table for take 1 and take 2
- The completed listener checklist
- The completed Q&A table with your reframe and reply
- The coach suggestion you acted on, quoted, with your change in your own words
- Written answers to the five analysis questions
- The chatbot critique report with its share link, or the equivalent route's marked-up flawed response
Deliverable:
A short Speech Workshop packet on your own impromptu answer: the prompt you drew, the one-minute keyword plan, the measures table for two takes, the listener checklist, the Q&A table with your reframe and reply, the coach suggestion you acted on in your own words, written answers to five analysis questions, and a critique of a chatbot's response, or, on the equivalent route, a marked-up correction of the printed flawed response. No recording is submitted. Submit in any accessible file type or as a link; a recorded response may be submitted as audio or video with a transcript, or as text. Choose a written, spoken, recorded, or visual form for your answers; every form is graded by the same scoring criteria.
Rubric
The rubric below shows how each submitted part is evaluated; bands are full, partial, or none.
| Criterion | Full | Partial | None |
|---|---|---|---|
| A one-minute plan with the point first | The keyword plan holds the four parts of PREP, or the parts of one backup frame, in the student's own keywords, its first row is a point a listener could repeat, and analysis question 4 names the frame, the pattern it shrinks, and why it fit the prompt. | The plan is made, but a part is missing or out of order, the point is not in the first row, or the frame choice is not explained. | No keyword plan, or a plan copied from a chatbot. |
| Two timed takes with a named moment | Both columns of the measures table are complete, each take records where the point landed, the listener checklist is marked for both takes, take 2 shows the chosen change, and analysis question 1 shows the subtraction. | One take is measured, a take names a feeling instead of a moment, or the change is given without the subtraction. | No take measured. |
| An honest reply to a listener's question | The Q&A table names the question and its kind, gives a one-sentence reframe, and replies with a point and one support; an unknown question gets an honest offer to find out, and no figure is invented. | The question and a reply appear, but the reframe or the kind is missing, or the reply does not lead with a point. | No Q&A table, or a reply that invents a figure to sound prepared. |
| Coach feedback acted on in your own voice | One coach suggestion, or one listener suggestion on the equivalent route, is quoted and answered with a change in the student's own words that shows up in take 2 or in the revised opening. | A suggestion is quoted, but the change copies the suggestion's wording or does not appear in take 2 or the revised opening. | No suggestion appears, or chatbot-written lines are submitted as the student's own. |
| Critique of the chatbot or of the printed flawed response | On either route, at least two problems are quoted and corrected with evidence from the student's tables, plan, or Chapter 15, every chatbot length rule, statistic, quotation, or source is marked unverified, and one correct point is acknowledged; both routes earn this band equally. | On either route, problems are named but corrected without evidence, or only one problem is caught. | No critique appears, or pasted output is submitted without any checking. |
| Reflection on the limits of the drill | The chosen reflection option is answered in 3–4 sentences that name a specific limit of the one-listener drill or the weakest part of the plan or reply, and a concrete way to check or practice it. | The reflection is answered but stays general, with no specific limit or practice step. | No reflection appears. |
Quality Gate
- Every recording stays on your own device; none is uploaded, linked, or shared with a chatbot or anyone else, and speaking to a listener with no recording counts fully.
- The prompt is drawn, not chosen in advance, and the plan is made in one minute, so the answer stays impromptu.
- The keywords, the change, and the reply are your own, not a chatbot's.
- Any length rule, statistic, source, or quotation the chatbot supplies is marked unverified, and a famous line is credited only to the speaker and speech its archived transcript shows.
- Both takes are delivered to a listener and timed, and the measures table names moments rather than feelings.
- The reply to the listener's question invents no figure, and the critique quotes the chatbot or the flawed response and corrects at least two problems with evidence.
Built with The Course Maker · samples.thecoursemaker.com