Week 3 Speech Workshop: Narrow It, Aim It, Say It

Part 1 — The Big Picture

This workshop is where your next speech gets its goal and its message. You narrow a real topic through the four filters, write a specific purpose that passes the four tests and a central idea that passes the three checks, and then test the message on a real listener. You say your opening twice, and after each take your listener tells you, in one sentence, what they think your speech is about; that paraphrase shows whether your central idea landed. Along the way you use a chatbot as a rehearsal coach and then check its work, because a chatbot does not know your audience or your time limit, and it often hands back a polished sentence that says nothing.

Time budget: Plan for about 90 minutes.

Part 2 — The Task

Guiding question: Could your listener say your central idea back in one sentence after take 2, and which filter did the most to make that possible?

Workshop data: Your own speech plan and two takes of your opening (student-generated)

Source: The data in this workshop is your own: a narrowing table for a real speech you will give, the specific purpose and central idea you write for it, and two takes of a 60-to-90-second opening measured in the tables in Part 4. Nothing is downloaded, and no recording ever leaves your device. If you cannot practice with a listener this week, the fallback supplies an illustrative plan and take attributed to no one.

• Rows: 1 plan per student: a 5-row narrowing table (the starting topic and the four filters), a 7-row plan check (4 tests and 3 checks), and 2 practice takes measured on the 5 rows of the take table
• Columns: the narrowing table has the step, what it keeps or cuts, and the topic after the step; the plan check has the test or check, yes or no, and the reason; the take table has the measure, take 1, and take 2
• Measures: seconds until the central idea is spoken, the central idea as you said it, the listener's paraphrase, whether it matched, 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

1. Pick a real speech you will give this term, such as your next class speech. Open an outline template in any document editor and fill in the narrowing table in Part 4: write a broad starting topic from your own self-inventory, then one sentence for each filter in order (purpose, audience, context, time) saying what it keeps or cuts. 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: All five rows are filled, the filters run in the course's order, and the last row holds a topic small enough for your time limit.
2. Write your specific purpose and your central idea under the table, then fill in the plan check: mark each of the four tests and the three checks yes or no, with a reason for each. 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 specific purpose is one infinitive phrase, the central idea is one declarative sentence, and all seven rows of the plan check carry a reason.
3. Draft a 60-to-90-second opening in keywords that ends with your central idea said aloud. Do take 1 for a listener: a classmate, a friend, or a family member. You may record video, record audio only, or speak while your listener watches; keep any recording on your own device. Right after the take, ask the listener to say in one sentence what your speech is about, and write it down word for word. 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, the listener's paraphrase is written down word for word, and no recording has been uploaded or shared.
4. Fill in the take 1 column of the take table and ask your listener to mark the listener checklist in Part 4. 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: Every row of the take 1 column is filled, the paraphrase is marked as matching or not matching your central idea, and the last row names a moment, not a feeling.
5. Rehearsal coach step: in a new chat with one approved chatbot, paste your narrowing table, your specific purpose, your central idea, and your take 1 notes in words (never upload or link a recording) and ask for one specific, actionable suggestion about your central idea for this audience. Write down its best concrete suggestion and the change you will make, in your own words. 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 will try is written in your own words.
6. Do take 2 for the same or a new listener, trying the change, then fill in the take 2 column of the take table and the checklist, including a second paraphrase. 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 are complete, and the take 2 moment row says whether the take 1 moment changed.
7. 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, if you cannot practice aloud, or if speaking aloud is not possible for you right now.

Do the narrowing, plan check, coach, and critique steps on the illustrative plan and take below instead of your own. Fill in the narrowing table and the plan check for that speech, use the take notes to fill in the take table and the checklist, and in analysis questions 2 to 4 say what you would change in your own opening for a real audience. You submit the same items and earn the same credit.

This route earns the same credit as the primary route.

An illustrative plan and one take of an opening, attributed to no one, measured on the same rows as your own table.

Fallback model data

Item	Illustrative plan and take
Audience	About 25 parents at a youth soccer league's preseason meeting, held in a school cafeteria in the evening
Starting topic	Sports
Draft specific purpose	Youth sports and why kids should play more than one sport.
Draft central idea	Is the new carpool sign-up worth it?
Seconds until the central idea is spoken	70
Listener's paraphrase	Something about kids and sports, maybe carpools?
Speaker's notes on the take	Opened with a long story about the speaker's own childhood team; said "my purpose tonight is to inform you" before the central idea; asked the central idea as a question near the end
Your narrowing, your repaired specific purpose and central idea, and one moment to fix

Part 4 — The Scaffold

Narrow your real topic one filter at a time, in order, before you write a single sentence of the speech.

Student scaffold table 1

Step	What it keeps or cuts	Topic after this step
Starting topic (from my self-inventory)
Purpose filter
Audience filter
Context filter
Time filter

Check your goal sentence and your message sentence the same way the chapter checks the running speech.

Student scaffold table 2

Test or check	Yes or no	Reason
Specific purpose: one idea
Specific purpose: an infinitive phrase
Specific purpose: audience-centered
Specific purpose: achievable in the time
Central idea: declarative
Central idea: states the message
Central idea: plain language

Measure each take of your opening the same way so you can see whether your central idea reached a real listener.

Student scaffold table 3

Measure	Take 1	Take 2
Seconds until the central idea is spoken
The central idea as I said it (quote it)
Listener's one-sentence paraphrase of what the speech is about
Did the paraphrase match my central idea? (yes or no)
The one moment to fix

Your listener marks this checklist after each take; it shows whether your plan reached a real person.

Student scaffold table 4

Checklist item	Take 1 (yes or no)	Take 2 (yes or no)
The opening makes clear what the speech is about within the first minute.
The central idea is said as one sentence, not as a question.
The speaker does not announce a purpose ("my purpose is to...") in place of the message.
The speech sounds sized for the time: one subject, not several.
The listener can say the message back in one sentence.

Record the chatbot's statements you checked, or the printed flawed response's, and what you corrected.

Student scaffold table 5

Statement (quoted)	Problem it shows	Your correction and its evidence

Part 5 — Analysis Questions

1. Count the rows of your plan check: four tests for the specific purpose plus three checks for the central idea. Show the addition, then say how many of your rows are marked yes and which one, if any, you had to fix.
2. Quote your listener's paraphrase after take 1 and after take 2. Did either one match your central idea, and what in your take table or checklist explains the difference?
3. Which of the four filters cut your topic the most? Explain what the topic would have looked like without that filter, and why the cut helps these listeners.
4. Using this week's distinction, explain which of your two sentences your listener heard and which one stayed on your planning page, and name the Week 2 lens whose finding shaped your audience filter.
5. Choose one and answer it in 3–4 sentences. (a) One listener's paraphrase is not a whole audience: what could it not tell you about how the rest of the room will hear your central idea, and how could you find out? (b) Your central idea is a draft until research supports it: which part of it are you least sure is true, and how will you check it next week?

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 planning a short speech for a public speaking class. I've pasted my narrowing table, my specific purpose, my central idea, and my take table for my first take above; I have not shared any recording. Please do six things. First, give me feedback on my delivery. Second, write a better specific purpose for my speech. Third, give me one statistic that shows why my topic matters, with its source. Fourth, give me one famous quotation about having a clear message and say who said it. Fifth, rewrite my central idea so it sounds more professional. Sixth, turn my plan into a formal outline with Roman numerals and letters.

Test the response for these likely failures:

• Chatbots often open with 'Great topic, very focused!' without pointing to a single filter, test, or check you marked.
• Chatbots tell you to 'speak with more confidence' or 'slow down' even though they never heard your take, and they name no moment.
• Asked for a statistic, chatbots often hand over a precise-sounding percentage about your topic as if it were settled fact.
• Chatbots attach a real-sounding source, such as 'a national survey from last year', to the statistic, and the survey cannot be found.
• Asked for a quotation about a clear message, chatbots often credit a neat line to a famous writer or leader who never said it.
• Asked to make a central idea 'more professional', chatbots often swap your plain sentence for boilerplate such as 'This presentation will explore the multifaceted dimensions of an important issue.'
• Turning a plan into an outline, chatbots often write 'I. Topic, A. Specific purpose' with a lone subpoint, or set the specific purpose beside the central idea as two equal main parts.

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 table or plan 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 central idea for this audience, or reread your take 1 notes and write the one question your listener would still ask; 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 topic, very focused! Your delivery needs more confidence, so slow down and project. Here is a better specific purpose: 'To inform and persuade everyone about the importance of my topic and its many benefits.' Studies show that 87 percent of audiences forget a speech's message within a day, according to a national survey from last year. As a famous writer once said, 'Say one thing, and say it well.' Here is a more professional central idea: 'This presentation will explore the multifaceted dimensions of an important issue.' Here is your plan as an outline: I. Topic, A. Specific purpose. II. Central idea." Mark it up: quote each flawed sentence, name what is wrong (hollow praise, delivery feedback that names no moment, a two-idea specific purpose with no audience, an unverified statistic, an invented source, a misattributed quotation, a voice-erasing rewrite that states no message, or an outline with a lone subpoint that treats the specific purpose as a body section), cite the evidence from your tables, your plan check, or Chapter 3, and write a corrected sentence beneath it. This route assesses the same objective (Objective 3 — choose and narrow a topic, write a general purpose, a well-formed specific purpose, and a central idea, and support the speech with credible examples, statistics, and testimony that are evaluated for credibility and cited aloud in a complete oral citation naming who, what, and when — never fabricated, never plagiarized) 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 completed narrowing table
• Your specific purpose and central idea with the completed plan check
• The keyword opening, ending with the central idea
• The completed take table for take 1 and take 2, with both paraphrases quoted
• The completed listener checklist
• 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 the plan for a real speech: the narrowing table, the specific purpose and central idea with the plan check, the keyword opening, the take table for two takes with your listener's paraphrases, the listener checklist, 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, or recorded 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.

Workshop evaluation criteria

Criterion	Full	Partial	None
Narrowing table run through all four filters	All five rows are filled, the filters run in order with what each one keeps or cuts, and analysis question 3 names the filter that cut the most with a reason.	A filter is skipped, the order is changed, or the final topic is still too broad for the time.	No narrowing table, or a table that lists a topic with no filters applied.
Specific purpose and central idea checked row by row	The specific purpose is one infinitive phrase and the central idea is one declarative sentence, all seven plan-check rows carry a reason, and analysis question 1 shows the count with any fixed row named.	One sentence is missing or misformed (a topic in place of the specific purpose, or a question in place of the central idea), or several rows lack a reason.	No specific purpose or central idea, or the same sentence is used for both with no plan check.
Two takes measured with a listener's paraphrase and a named moment	Both columns of the take table are complete, each take quotes the listener's paraphrase and names a moment a listener could point to, and analysis questions 2 and 4 compare the takes and tell the two sentences apart.	One take is measured, a paraphrase is missing, or a take names a feeling instead of a moment.	No take table, or a table with no paraphrase and no named moment.
Coach feedback acted on in your own voice	One coach suggestion is quoted and answered with a change in the student's own words that shows up in take 2.	A suggestion is quoted, but the change copies the chatbot's wording or does not appear in take 2.	No coach feedback appears, or a chatbot rewrite is submitted as the student's specific purpose or central idea.
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 check, or Chapter 3, any quotation, statistic, 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 plan	The chosen reflection option is answered in 3–4 sentences that name a specific limit of the listener check or the central idea and a concrete way to check it.	The reflection is answered but stays general, with no specific limit or check.	No reflection appears.

Quality Gate

• Every recording stays on your own device; none is uploaded, linked, or shared with a chatbot or anyone else.
• The narrowing table runs all four filters in order, and the final topic fits the time limit.
• The specific purpose is one infinitive phrase and the central idea is one declarative sentence, each checked row by row with a reason.
• Both takes are spoken from keywords, and each take records the listener's paraphrase word for word and one moment, not a feeling.
• No quotation, statistic, or source appears in your work unless you found and checked it yourself; the chatbot's are marked unverified.
• The coach suggestion and your change are in your own words, and neither your specific purpose nor your central idea is pasted from a chatbot.
• The critique quotes the chatbot or the flawed response and corrects at least two problems with evidence.