Creating a prompt bot with a prompt provided by the Chatbot: A time saver

 In the past, to create a prompt bot, people needed to write the prompt themselves. 

Now that chatbots are becoming more and more capable, we can actually ask a chatbot to give us the prompt to use for creating a prompt bot. Below is my example, using Poe's 'Create Prompt Bot' function. 

STEP 1: In Poe's chatbot, state what I needed: 

 I  want to use Poe's prompt bot function to build a prompt bot to guide upper primary students to learn/ revise the sentence structure 'If I were (a bird), I would ...." through a 7-turn scaffolded conversation. Please provide me with the prompt to use with Poe's prompt bot function.

STEP 2: Copy the prompt given in Step 1 into Poe's Prompt bot function: 

You are a friendly ESL writing tutor for upper primary students (around ages 9–12). You will run a 7-turn scaffolded mini-conversation to help the student learn and revise the sentence structure:

"If I were (a/an + noun), I would (base verb) ..."

Goal: By the end of Turn 7, the student produces 2 correct sentences using the target pattern, with correct use of "were" (not "was") and "would + base verb", and with at least one sentence expanded using because/so/and or a detail phrase.

Tone & level: Warm, encouraging, simple language, short messages. Avoid metalanguage/grammar jargon; explain in kid-friendly terms. Always model correct English. Ask only ONE question per turn. Keep each turn 1–4 short lines.

Conversation rules:

- The conversation must be EXACTLY 7 turns (your messages), numbered Turn 1 to Turn 7 in your own planning, but do NOT show the numbers to the student.

- Each turn: (1) tiny teach/model, then (2) ask the student to respond.

- If the student makes a mistake, correct gently: show the corrected sentence and give a quick reason (e.g., “We say ‘If I were…’ for imagining.”). Then ask them to try again.

- Always give a clear example before asking the student to write.

- Use high-interest, school-appropriate options (animals, jobs, objects, superheroes, sports, nature). Avoid sensitive topics.

- Require “a/an” where needed: “If I were a bird… / an astronaut…”.

- Encourage creativity and longer answers, but keep it easy.

Scaffold plan (must follow):

Turn 1: Hook + one example. Ask student to choose what they want to be (give 4 choices).

Turn 2: Sentence frame with blanks. Student fills in 1 sentence.

Turn 3: Add 1 extra detail (where/when/how). Student improves their sentence.

Turn 4: Introduce “because …” expansion. Model it. Student adds “because …”.

Turn 5: Switch to a new noun. Student writes a new full sentence independently.

Turn 6: Spot-and-fix mini-check: present 2 short sentences, one correct and one wrong (e.g., “If I was a bird, I would fly.”). Ask which is correct and why (kid-friendly).

Turn 7: Final task: student writes TWO sentences: one with an animal, one with a job, at least one using “because”. Praise + very brief feedback.

Output format:

- Only write the assistant’s message for the current turn, based on the student’s last reply.

- Do not write stage directions, hidden analysis, or extra turns.

Step 3: Publish

======================

OBSERVATIONS

1. The resulting prompt bot can be shared via a Share Link. But users must have a Poe account and be signed in. This is unlike Poe's App Creator, the result of which can be shared as a Preview link. 

2. If you use Gemini, the steps are: 

a. Use the chatbot to get the prompt. 

b. Then go to 'Create Canvas' and paste in the prompt from Step (a). 

3. Like Poe, the Prompt Bot created with Gemini, when shared, requires the user to sign in to their Google account. 

4. Canva AI's code for me, however, does not require users to sign in to open the share link. 

5. Of course, if you wish to have more control on the content of the prompt bot, then you have to provide more detailed instructions (e..g., the example sentences to use) in your prompt. 

Created a 'Read lecture transcript and Answer 3 MC questions' app using Poe's App Creator

 Originally, I went to Gemini and asked how to write a prompt to create a canvas app similar to the P4 Listening app created by Alex Lam. 

After 2 turns, it gave me a sample prompt, as below: 

You are an expert Marine Biologist. Create a Poe Canvas app for a listening and comprehension task about Coral Reefs.
The Lesson: Discuss the symbiotic relationship between polyps and algae.
Interface: Create a dashboard in the Canvas. When I click 'Start,' show a 'Transcript' of a lecture. Below it, provide 3 comprehension questions one by one.
Style: Use a blue ocean theme for the UI. Use React-style components (HTML/JS) to handle the question logic so the page doesn't refresh, but updates dynamically as I answer.

==============

I copied it into Poe's App Creator. It returned the output app below in about 2 minutes: 

https://poe.com/preview/psOeQWeHJ9sKNiZsqEAW

So the prompt given by Gemini worked. But there was no audio in the app. Then I asked App Creator to add a Play button and Audio to the app, but I was going beyond the required points. So I stopped there. 

=======

TAKEAWAY: 

It's OK to ask a chatbot to provide you with a prompt to use in creating a canvas app. 

Used Google Vids to create an instructional video on Self Regulated Learning.

 如果要生成一個簡短的general introduction to a topic or concept的video, 我試過的AI 工具中，暫時最滿意的是Google Vids。NotebookLM 的Video Overview當然很好，但用法不同，它主要依靠用者上傳的資料。

但Google Vids, 用者只要打入topic 或concept, 它便先生成一個outline,如果滿意不作edit, 再按generate, 它便生成一個兩分鐘的video。乾手淨脚。

下面是我以Key concepts in self-regulated learning為topic 生成的overview video；只要不用於high-stakes場合(例如考試)，這方法是不錯的，可讓課堂更multimodal。

Google Vids does not need to be installed. It appears after clicking 'add' in Google Drive. 

https://youtu.be/ygEkmJ96lIA

Gemini's "Create Image' function: PROJECT AC vs PERSONAL AC

1ST TRY

PROMPT: Create an image that illustrates Newton's first law of motion 

=====================================================

PROJECT AC OUTPUT: 

PERSONAL AC OUTPUT

=======================================================

2ND TRY

PROMPT: An image that explains how a typhoon is formed. 

PROJECT OUTPUT: 

PERSONAL AC OUTPUT: 

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

OBSERVATIONS

1. Outputs can be different, eg, the number of stages. 

2. No obvious 'better' tool. But Personal AC Output might look slightly 'better.' 

Insert AI voice into a poster in Canva: steps

 1. Finish editing the image page. 

2. Click on AI voice on the left-hand pane. 

3. Choose a voice (eg, AmE vs BrE; male vs female) to preview. 

4. Then click 'Generate Voice' at the bottom. 

5. Then Edit as video. Adjust the length of the voice track. 

6. Download the video as MP4. 

7. The above can be repeated page after page. 

=========

TAKEAWAY

Can add voiceover to images in Canva. 

Uploading a PPT to Wayground and having the links still clickable: Steps

 1. Prepare PPT; insert links in slides as usual.

2. Upload to Google Drive as a Google Slidedeck. JUST UPLOADING THE PPT won't work for the links. 

3. Go to Wayground; import from Google Drive. 

4. Publish 

========

In 'Preview' mode, we can see that the links are clickable. 

===============================

TAKEAWAY: 

- It's OK to start with PPT, which has many functions. 

Canva.com to edit text in Image: List of useful functions

 Earlier on, I created a poster using Gemini. The visual output is fine, but there was a spelling mistake. 

Thanks to Ada Lam, who alerted me to the "EXIT TEXT IN IMAGE" function in Canva: 

1. 

https://www.canva.com/features/edit-text-in-image/

2. Upload problem image. 

3. Grab text box in uploaded image. 

3. Click 'Edit' icon: 

4. Choose 'Fix Spelling'

5. Check 'Replaced Text'; click ''Replace" if accepted: 

===========================================

Create a Heading Matching task using Canva AI on Environmental Protection: Can't base it on my own infographic

 Previously, I created an infographic on Saving the Environment, from a simple prompt, using Canva AI. 

Just now, I wanted to use Canva's Code for Me, to create an interactive blank-filling task (fill in the headings for the 5 sections in the infographic).

But I was not able to upload my infographic. It referred to my prompt, and generated a general one as below: https://paulsze.net/eco-friendly-tips

Created a Save the Environment infographic using Canva.AI: 1 output chosen for generating reading comprehension questions

 Canva: 

Left-hand pane > Canva AI >

Prompt box:

    Create a horizontal infographic for grade 7 students titled ‘5 Things You Can Do to Save the Environment’. The infographic should include text and images. The images should help illustrate the action in question.

OUTPUTS:

4 versions:

I chose one of them: https://www.canva.com/design/DAHCz2AgS6I/4696TXRECl3Sdqg8EGrsxA/view?utm_content=DAHCz2AgS6I&utm_campaign=designshare&utm_medium=link2&utm_source=uniquelinks&utlId=hc617aace8e

downloaded it.

Then I went to POE, uploaded the infographic image file, and asked the chatbot to generate 6 reading comprehension questions based on the infographic.

It worked.

https://poe.com/s/2nr37yFmu77eaGXsUrNW

Found a Workaround to convert the main headings of a Workflowy session rundown into an EdrawMind Mindmap: Make use of Markdown

 STEPS: 

1. In Workflowy, collapse a rundown to the levels which I want to show on a mindmap. 

2. Copy and paste this list into Dynalist

3. In Dynalist, copy this back to Workflowy

4. Export as a Markdown file

4. In EdrawMind, under FILE, import this Markdown file. 

==

KEY TAKEAWAY

- Unlike Xmind and Mindmeister, a mind map thus created in Edrawmind can start with the top node. 

Tried and compared Doubao and Copilot for realtime voice chat: both performing well

最近test-drive 了幾個供實時turn-based 的voice chat AI app。背後的科技已發展得很好，是很好的外語conversation practice 的工具。Elsa Speak, Loora AI， Speak 等更可以因Learner 的需要，進行customised 的voice chat, 但要收費。

當然有些chatbot 也可以和用者進行English voice chat；暫時我試過最好的是Copilot, 就算我說得「論盡」, 它也明白我的意思；而且它反應夠快，你說完後不夠一秒，它已經回應，結果是一個很natural 的對話。除了fluency practice, Copilot voice chat還可以教你features of English pronunciation 例如stress, rhythm, intonation。

Doubao也不錯，還會把雙方的說話實時在螢幕transcribe 出來。對中小學生是很有用的功能。

 

	WEB APP	ANDROID APP
DOUBAO	Yes, but need to click ‘Play’ to listen to AI conversant -          Simultaneous transcription	Fully realtime -          Simultaneous transcription
COPILOT	(in Edge) Fully realtime           -          Post-chat transcription available	Fully realtime -          Post-chat transcription available

 

Tried Doubao's Audio Chat function: Not bad though not real-time

 I tried the Web version on my computer, as well as the desktop app. 

The setting for microphone input was a bit complicated. 

Anyway, from the homepage, I clicked the microphone icon in the lower right corner of the prompt box. 

I then started speaking in English. When i was done, I clicked on the icon again. 

My utterance would be transcribed. 

Then Doubao would reply in text format. 

If I want to hear it, I clicked on the loudspeaker icon below the prompt box. 

===

KEY TAKEAWAYS

1. It does a good job in recognizing my utterances. 

2. it prompts the conversation quite naturally. 

3. But it's not real time, like Loora AI, as to hear Doubao, I have to press the button every time. 

4. On the other hand, for ESL learners, it may be an asset, as they have the written dialogue to refer to. 

Canva AI can generate an infographic from a text: The output is full of spelling mistakes

Canva AI can also generate infographics from a text, and the outputs are quite eye-catching. On closer look, however, like the free tier of Google Gemini, the generated infographic is full of spelling mistakes!

So, NotebookLM still trumps all other AI tools as far as generating infographics is concerned.