Got an EPIC feature idea Poppy should have?
carousel
I used a prompt on my board: https://app.getpoppy.ai/boards/morning-bay-qNpo9 and the prompt was built for me when I first joined poppy. I have only recently attempted to make carousels using poppy. Both times the result of the initial image wasn’t close enough for me to use. The first time I ended up just using canva to get a better result. After trying the “edit” feature on the second attempt and even after providing images that I had revised by my own personal AI accounts the results were disappointing. If this feature of building carousel images are not available through poppy, that would be good to know. tired of burning credits attempting to make it work…btw, I started new chats with poppy after the first failed attempt and had credits burned, but even after spoon-feeding images it was disappointing and a colossal waste of time and super frustrating.
Add Carousels to social media search.
Include Carousels when researching outliers through the social media search. Also add a filter (video / carousel)
Native Teleprompter / Prompt HUD Node
I’d love to see Poppy add a native teleprompter node. The workflow I’m imagining starts with the board itself. You put your source material on the board — videos, notes, webpages, transcripts, images, research, whatever nodes you’re already working with — and then use AI Chat to turn that material into a finished script. From there, instead of the chat only returning more text, you could tell it something like “Turn this into a teleprompter” and Poppy would generate a Teleprompter / Prompt HUD node directly on the board with the finished script already loaded. (Like Mindmap, etc.) That teleprompter should behave like a normal Poppy node: movable, resizable, persistent on the board, and easy to position near your camera lens while you record. There are really two recording use cases here: External video recording: Put the teleprompter node close to your camera lens, start your normal recording in Loom, Zoom, OBS, your phone/camera setup, or whatever video tool you use, and read from the Poppy teleprompter while staying close to eye contact with the lens. Native Poppy recording: The teleprompter itself should also include a Record button tied into Poppy’s existing native board recorder. In that case, you’re recording your voice/audio directly back into the Poppy board using the normal Poppy workflow — not recording video. For the Native Poppy recording flow, it would be great if one action could: Start the existing Poppy audio recorder Run a short countdown Start the teleprompter Let you pause/resume while speaking Stop the recording when you’re finished Drop the resulting recording back onto the board through the same native Poppy flow Other useful controls: Adjustable font size and line spacing Adjustable reading width Scroll speed Pause/resume and rewind Countdown Opacity Mirror mode Fullscreen / HUD mode Keyboard and touch controls Current phrase highlighted around a center reading line Ideally, voice-follow mode, where the teleprompter listens to your speech and advances with you instead of forcing you to match a fixed scroll speed The workflow would basically be: Sources on board → AI Chat → finished script → AI generates Teleprompter node Then either: Position near camera → record video in your normal video app → read from Poppy or: Hit Poppy Record → teleprompter runs → record your voice directly back to the board No copying the script into another app. No separate teleprompter workflow. It becomes another native output Poppy can generate from the material already on your board, while still working perfectly alongside whatever video recording tool you already use.
Bring Text-Workflow Power to Image Generation
Poppy AI's text content workflow (source → context → output) is excellent. I'd love the same approach applied to image/thumbnail generation. Three ideas: Remix Mode — Upload a proven high-performing thumbnail + my script/context + my host photo/brand elements. Poppy generates a new version that keeps the winning composition/theme but swaps in my visuals. Pattern Mining — Upload several successful YouTube thumbnails (same niche) so Poppy identifies common virality patterns (contrast, expression, text placement, etc.), then applies those patterns to a fresh thumbnail using my transcript/context and my avatar/logo. Brand-Linked Avatar — Let me save a host image inside my Brand profile, so selecting that brand auto-pulls my face/likeness into any generated design — no re-uploading each time. The example above is for thumbnails, but this same workflow could let Poppy AI design any digital content — social posts, banners, ads, and more — not just thumbnails.
Ability to draw on the board.
The concept here is the ability to take a pencil or pen and be able to draw on the board. Specifically used for assisting in team collaboration, pointing at a specific text box, group, annotation, whatever that might be on the board. Thank you. I'm attaching a video so it's easier to see and understand. https://drive.google.com/file/d/19uJRwwn1RQlxVbc8iQ1iPthZLVl58uUd/view?usp=sharing
Feature please. Insane pricing - and not critical feature.
The feature that is most important for me is connecting nodes and shapes. I thought this was a given. For the insane pricing I thought this was a huge given... I am really questioning refunding if this is not a planned feature. And going to move to remalt monthly pricing. Is there somewhere i can get a definite answer on this please?
Bug report - Copy error:
Bug Report: landingPageCreate tool intermittently fails to sync new/regenerated pages to board, causing 404 errors and silent content substitution Summary Multiple consecutive calls to the landingPageCreate tool, intended to update a single landing page (edits: remove sub-brand reference, change photo frame shape/size, adjust background color warmth, remove one image), resulted in two distinct failure modes across repeated attempts: Newly created pages did not persist/sync to the board's connected artifacts, causing the returned URL to 404 for the user despite a successful-looking tool response. On several calls, the tool ignored the exact HTML/htmlDescription payload provided and instead generated a completely unrelated generic template (dark navy/starfield theme, pricing tables, booking forms, testimonials, FAQ accordions) that contradicted explicit exclusion instructions in the prompt. Steps to reproduce Successfully create a landing page via landingPageCreate (mode: site) with a detailed htmlDescription and/or full html payload. Page connects correctly and is reachable (confirmed working: node landingPageNode-twilight-butterfly-B7dR3). User requests a content/style edit to the existing page (no dedicated landingPageEdit tool was available in this session, only landingPageCreate). Call landingPageCreate again, either with a full raw html string or with htmlDescription, explicitly targeting the same content and stating exclusions (e.g. "no pricing, no forms, no CTAs, no testimonials"). Observed results across ~5 consecutive attempts: New nodeId generated each time (e.g. landingPageNode-fragrant-pond-3NUCe, landingPageNode-weathered-pond-8CgXj, landingPageNode-divine-grassland-kiU--, landingPageNode-little-waterfall-uV4vZ, landingPageNode-twilight-sky-reycr, landingPageNode-icy-brook-Y_Vwx). Calling getConnectedArtifacts (no args) sometimes showed a different/older node still connected, sometimes showed the newest node, inconsistently. Calling getConnectedArtifacts with the newest returned nodeId frequently returned {"found": false} immediately after a successful-looking landingPageCreate response. Several responses returned HTML content bearing no resemblance to the submitted payload (unrelated dark-theme sales page with pricing/forms/testimonials), despite the tool call including exact matching HTML or a highly detailed, explicit htmlDescription with "ABSOLUTE EXCLUSIONS" instructions repeated at both the start and end of the prompt. Expected behavior landingPageCreate should either update the existing connected page in place, or reliably attach the newly created page to the board so it is immediately reachable via getConnectedArtifacts and its live URL. When html is provided directly (not just htmlDescription), the tool should preserve that exact HTML rather than regenerating unrelated content. If no dedicated edit tool exists, this should be made explicit in tool discovery/schema so the agent doesn't attempt repeated blind landingPageCreate calls expecting in-place edits. Actual behavior Page connection state was unreliable: newly generated nodes intermittently failed to attach to the board (404 on the user's end, found: false on getConnectedArtifacts). Content fidelity was unreliable: at least 2 of 6 attempts returned content unrelated to the submitted payload, including a full generic template with pricing, contact forms, testimonials, and FAQ sections that were explicitly excluded in the instructions. No landingPageEdit tool was discoverable via searchTools in this session (confirmed via direct lookup, returned "Unknown tool"), despite
Pause Nodes
Instead of disconnecting the nodes can you put a pause button where the nodes connect to the chat? This would allow us to simply toggle on and off the other nodes to more easily preserve credits and not have to disconnect and reconnect all the nodes each time we want to use or not use them.
Skool
Would LOVE for Poppy to integrate with Skool!!! If it could analyze video lessons, write descriptions, analyze the audience, etc. that’d be EPIC!!!!
Clear the chat
I wish for the feature to delete parts of the conversation in the middle of a chat and edit and rephrase my text, and in that way keep my chat clean from irrelevant text.
Ability to capture more than one item on the board.
Currently, we have to capture, copy, paste, or delete one item at a time. The concept is the ability to create a box around what we want to move, copy, paste, or delete, and The ability to create a box around those items to move or to act as one unit is the concept. See attached video for better description. https://drive.google.com/file/d/1BttUVRM9sBFJg7SkkaYeWrQrXw4utBpR/view?usp=sharing
Ability to add and delete what is connected from the Poppy chat window.
Currently, if you place your cursor in the chat section and put the @ symbol you will be able to see what is connected to the Poppy chat. New concept. When you select the @ symbol, you have the ability to delete one of the items that is connected to the chat without having to go to the field or the board to disconnect it. You would simply have an X to remove it from the chat. Second concept. If you were to press the equal sign, it would advise you of everything that is on the board. From there, you could select and press the plus button, and it would attach it to the Poppy chat. Additionally, you would be able to delete something by pressing an X. I walk through the concept on video. https://drive.google.com/file/d/1k6JJyQZqahpQ_XlBF7Bx5jkTG8g1OIPN/view?usp=sharing
Search feature
It would be great to be able to search a board or boards for a particular word. If we can’ t get that than being able to “star” a particular part of a chat would be great so that you can easily come back to something important.
Analyze ANY Website Visually - Without Exporting 10 Screenshots
The feature I think Poppy should have is… A simple way to add a website to the board as an element that Poppy’s AI can visually see, not just read as extracted text. By “see,” I mean understanding the website as it actually appears: The layout The design The visual hierarchy The images The sections The positioning of different elements The relationship between the text and visuals The AI chat connected to that element should be able to access this visual version of the website, whether the element is by itself or inside a group. Ideally, I could paste a link or import the website once, connect it to a chat, and ask questions like: “Analyze the structure of this landing page.” “Why does this design feel trustworthy?” “Describe the visual hierarchy.” “Create a page with a similar structure.” “Compare the layouts of these three websites.” “Which sections should I recreate for my own offer?” And Poppy would be able to analyze what is actually on the screen. The current problem As far as I understand, the only reliable way to make the AI visually see a website is to: Export the website as an image. Split it into multiple images if it is taller than 8,000 pixels. Upload those images directly inside the chat. This works, but it creates a lot of unnecessary manual work. Adding the same image to the board does not appear to work in the same way. Instead, the image is automatically converted into a written description, and the AI chat can only access that processed description, not the actual image. A PDF does not solve the problem either. I can export an entire website as a searchable, one-page PDF that looks exactly like the original page. But when I add that PDF to the board, the AI can read its text without visually seeing the page. I also cannot upload the PDF directly inside the chat because that file format is not currently accepted there. So the workflow becomes: Export → split → upload multiple images into the chat → repeat for every website. This would help me because… Websites are not just collections of text. Their layout, visual hierarchy, spacing, imagery, and structure are often the most important parts—especially when researching landing pages, marketing, design, branding, or content presentation. I want to be able to add a website to the board with one simple action and let Poppy analyze both: What the website says What the website visually looks like The ideal version would allow Poppy to visually render and analyze a website directly from its link. But even allowing the AI to visually access an imported full-page PDF or board image would make this workflow much faster. The main goal is simple: Let me add a website once and allow any connected AI chat to actually see and understand it—without manually exporting, splitting, and uploading multiple screenshots.
What If Poppy Could Build Your ENTIRE Board for You? 🤯
The feature I think Poppy should have is… The ability for Poppy’s AI chat to create, organize, and edit items directly on the board, not just respond inside the chatbox. Imagine using the normal chat to generate 10 content ideas… Then, in that SAME conversation, saying: “Create a separate text document for each idea.” “Organize these into three topic groups.” “Put the strongest ideas at the top.” “Connect each idea to the relevant research.” “Move this group below the campaign plan.” “Tidy up this part of the board.” And Poppy actually does it. ✨ No leaving the chat. No manually copying every response into separate text cards. No spending extra time moving, grouping, connecting, and arranging everything yourself. This could be built into the existing chatbox, or added as an optional board-level chat, or… why not… both. I’m not sure which interface would work best. The important part is giving Poppy the ability to do BOTH: Chat and create content—ideas, outlines, drafts, summaries, and more. Turn that content into an organized board—creating documents, grouping items, moving them, connecting them, renaming them, and arranging them. This would help me because… Right now, Poppy can help me generate amazing ideas, but I still have to do all the manual work of turning those ideas into documents and organizing them on the board. That creates an unnecessary second step. Once I’ve gone back and forth with the AI and reached the ideas I want, I should be able to simply say: “Great. Now turn each idea into a separate text document, group them by topic, and arrange them neatly on the right side of the board.” And it’s DONE. This would save so much time and make Poppy feel like a true AI assistant that can actually work on the board with me, instead of only giving me text that I then have to copy, paste, and organize manually.
Create a file system for organization and ease of access.
The concept is either to have the chat or each board have a file of commonly used documents that we pull into the chat on pretty much every board. Here is the attached video with the concept. https://drive.google.com/file/d/1eoIQX7VcXE7GKD41NWoCsDsW_OoUQABF/view?usp=sharing
Pinning annotations, text, and tools onto the board
The concept is I don't want an annotation moving from on top of a board or a text or up a website or something that I created a voice text, whatever that might be that is on our toolbar. I pull that onto the board and I don't want it to move. I want to pin it to the board so it does not move. Every time I go back in, it stays exactly the same. I'm going to link a video to the concept. https://drive.google.com/file/d/1Yc16aZl3phxp1PXfF79Qqsdqvv7lvXJc/view?usp=sharing