Share your ideas to make Manychat better.
Hi! I would love it if we could download a csv file of all email addresses collected, especially if we could pull by date. Currently, I can only pull one csv per automation vs. one for all email addresses.
I wanted to suggest a small but impactful feature: enabling automatic synchronization for image URLs used in flows.Currently, when an image is inserted by URL, ManyChat caches it on the CDN, which means that if the image on the hosting server is updated, the change doesn’t immediately reflect in ManyChat. For businesses that frequently update creative assets (like banners or product images), this creates extra steps of versioning URLs manually (?v=2, ?v=3, etc.).It would be very helpful if ManyChat could either: Respect cache-control headers set by the hosting server, or Provide an option to force a fresh fetch of image URLs in flows. This would save time and streamline content updates for many users.Thanks for considering this suggestion, and for continuing to improve the platform!
El problemaManyChat no trae memoria ni base de datos nativa para sostener un flujo conversacional. Cada mensaje empieza “en blanco”.La solución (en corto)Usamos campos de usuario (User Fields) + acciones ChatGPT para construir y mantener un Historial de preguntas y respuestas. El flujo se arma con dos módulos y dos acciones clave que se repiten.Preparación (1 vez)Crea estos Campos de usuario (tipo Texto): consulta respuesta historial MÓDULO ACCIONES 1 — inicializa la memoriaAcción 1 — ChatGPT (respuesta a la consulta) Entrada (Mensaje de entrada): {{consulta}} Salida (Guardar respuesta en): respuesta (Aquí puedes usar el prompt del asistente que necesites para responder al usuario). Acción 2 — ChatGPT (construye historial) Prompt (copiar/pegar tal cual): TU funcion es armar un historial ordenado, sin modificar nada de la siguiente informacion. Pregunta: "{{consulta}}" Respuesta: "{{respuesta}}" Mensaje de entrada: (vacío) Salida (Guardar respuesta en): historial Módulo Recopilación de Datos WhatsApp — muestra y capturaEste módulo envía el historial al usuario y espera la nueva consulta. Enviar mensaje: {{historial}} (el usuario verá el historial como respuesta) Esperar respuesta de texto → Guardar en campo: consulta Conecta la salida “Siguiente paso” a MÓDULO ACCIONES 2.MÓDULO ACCIONES 2 — ciclo continuo con límiteAcción 1 — ChatGPT (respuesta a la nueva consulta) Entrada: {{consulta}} Salida: respuesta (Mismo prompt de tu asistente que en Acciones 1). Acción 2 — ChatGPT (actualiza historial con límite) Prompt (copiar/pegar tal cual): TU funcion es armar un historial ordenado, sin modificar nada de la siguiente informacion. Pero solo entrega las ultimas 4 preguntas y respuestas. (Ajusta el limite si hace falta: muchos caracteres pueden ralentizar el flujo) Hitorial de preguntas: "{{historial}}" Pregunta: "{{consulta}}" Respuesta: "{{respuesta}}" Último mensaje del usuario: VACIO Entrada: (vacío) Salida (Guardar respuesta en): historial Rutas desde este módulo: Acción en respuesta: “Establecer campo de usuario” → Historial = {{historial}} Siguiente paso: volver a Módulo Recopilación de Datos WhatsApp (para mostrar el historial actualizado y esperar la próxima consulta). Vista rápida del flujo (esquema) [Usuario escribe] ↓ (se guarda en consulta) [MÓDULO ACCIONES 1] 1) ChatGPT => respuesta 2) ChatGPT => historial (agrega Q/A) ↓ [Recopilación WhatsApp] Enviar {{historial}} → Esperar texto → guardar en consulta ↓ [MÓDULO ACCIONES 2] (bucle) 1) ChatGPT => respuesta 2) ChatGPT => historial (mantiene solo últimas 4 Q/A) Acción en respuesta: set Historial Siguiente paso → Recopilación WhatsApp Notas operativas Si historial está vacío al inicio, el primer mensaje puede ser una cabecera breve (opcional) o simplemente no enviar nada hasta tener la primera Q/A. Ajusta el límite de Q/A según el canal y el tamaño de prompt admitido. Mantén tus prompts cortos y deterministas. Todo se basa en campos de usuario; no se requiere base de datos externa.
I currently have several flows where users meet certain goals and these goals are stored as tags so that the advisor can more quickly identify key aspects in the conversation.One of the important labels to quickly identify is the source of the lead, so I would like to be able to identify it quickly with a specific color.
A useful feature is missing: color-coded labels for chats. With a high volume of conversations, a visual label that allows the identification of the lead's status or the conversation facilitates development for sales and customer service teams. WhatsApp Business, Instagram, and Zenvia already use these alternatives. It would be a great addition to ManyChat.
Please! Make tags visible on the main live chat screen without having to open each conversation to see which tags are assigned, and allow for different colors for each tag. This would greatly help in categorizing customers more clearly, similar to what we can do in WhatsApp Business.
Hi Manychat Team,I hope you're doing well!I'd like to suggest a feature that I believe would greatly improve organization and productivity within the platform: the ability to add custom colors to tags and to display tags directly in the conversation list, rather than only showing them when a specific conversation is opened.Currently, tags are only visible once you open a conversation. By showing them in the main conversation list and allowing color coding, it would be much easier to visually identify conversations by category, priority, or funnel stage.It would also make it easier to spot conversations that have multiple tags applied, streamlining the triage and follow-up process.I’ve created a few example images to illustrate how this feature might look and work in practice — attaching them here for your reference.Thanks so much for considering this idea, and congratulations on the great work you're doing with the platform!Here are the prints: Could you help me with this, @Raquel C , @Marina?Best regards,Heric Fernandes
Give an opportunity for live agents to edit the canned messages generated by chatgpt through the mobile app (and not only on the desktop)
It would be a very useful feature to be able to export all of the keywords, their active status, channel(s), and automation name to a CSV file. Some users, myself included, have many keywords and automations and it becomes difficult to keep track of what’s currently live/inactive etc. This way we could have a reference document to easily see what may need updating. Thank you.
When a single vertical image is uploaded, it gets cropped instead of showing the full picture. It would be great if the entire image could be displayed without any cropping. This could apply for both simple image blocks as well as card blocks with images or gallery blocks. Then if an instagram message automation sends more than one image in sequence, they could be clustered the way Instagram already does, rather than sending them as separate images, or at least they can be horizontally scrollable like the gallery blocks - also as vertical images. I would really appreciate these features for my business.
It is very hard to find certain chats with search function. It would be helpful to be able to find people with their insta/fb username.
Summary:I propose that ManyChat’s integrated AI can understand audio (transcribe + extract intent) and images (OCR / recognize context). Today users prefer sending voice notes and images; allowing ManyChat to process them natively will reduce friction and enable new support and sales flows.Problem: Many users send voice messages and images because it’s more convenient; bots currently ask them to type or repeat information. This causes delays and extra work for agents. Proposal: Enable processing of voice messages to produce a transcription and the user’s main intent. Enable basic image recognition (read text in photos like tickets/receipts and detect image type: product / receipt / ID). Allow flows to combine voice + image + text to make decisions (for example: detect a complaint and automatically create a ticket). Use cases: Support: customer sends a product photo and says by voice “it arrived broken” → bot identifies order and creates a refund proposal or ticket. Commerce: user sends a photo of a product and asks the price by voice → bot replies with options and a purchase button. Pre-human assistance: automatic summary of audio + photo so the agent sees the essentials before replying. Accessibility: people who have trouble writing use voice and images to complete forms. Closing / Request:Please consider prioritizing multimodal capabilities (processing audio and images) in ManyChat’s AI. I can provide concrete flow examples if the product team wants them.
Summary:I propose that ManyChat’s integrated AI can understand audio (transcribe + extract intent) and images (OCR / recognize context). Today users prefer sending voice notes and images; allowing ManyChat to process them natively will reduce friction and enable new support and sales flows.Problem: Many users send voice messages and images because it’s more convenient; bots currently ask them to type or repeat information. This causes delays and extra work for agents. Proposal: Enable processing of voice messages to produce a transcription and the user’s main intent. Enable basic image recognition (read text in photos like tickets/receipts and detect image type: product / receipt / ID). Allow flows to combine voice + image + text to make decisions (for example: detect a complaint and automatically create a ticket). Use cases: Support: customer sends a product photo and says by voice “it arrived broken” → bot identifies order and creates a refund proposal or ticket. Commerce: user sends a photo of a product and asks the price by voice → bot replies with options and a purchase button. Pre-human assistance: automatic summary of audio + photo so the agent sees the essentials before replying. Accessibility: people who have trouble writing use voice and images to complete forms. Closing / Request:Please consider prioritizing multimodal capabilities (processing audio and images) in ManyChat’s AI. I can provide concrete flow examples if the product team wants them.
An option where AI can be used to set up automatic responses to comments without redirecting to DM. AI then responds to FAQ questions and comments that are written for fun.
Hi.Attending customers in Livechat is a very important way to show our interest in them.Sometimes we make a typing mistake or we simply want to edit the sent message and it’s not posible.Could you please add the delete function.If is possible at least to edit instead of deleting, that would help us a lot.Thanks in advance.Jhony
The need for having official Meta PSID for Messenger contacts is a feature that NEEDS to be allowed in Manychat platform.— Currently, Manychat has its own internal ID for users (ie. contact ID / {{user_id}} system field), this does NOT match/correlate with Meta’s PSID for same user.There are automation needs for PSID (eg. ADs data between Manychat & other platform(s); or even Tracking chats etc) --- Hint: You’ll know when you need this, AND most people have, as seen in existing Manychat user questions as below: and more. Manychat team, we need this PSID available dynamically ; able to be used in External Request actions etc.NB: The current existing manual BULK EXPORT in Contacts, whilst useful, it does NOT suffice when needing dynamic data export as such. @Manychat Community Please consider to action! Thanks
Description:At the moment, Manychat only allows using more than the 3 Live Chat seats included in the Pro/Marketing Automation Plan if you also purchase the full Inbox Plan.This results in effectively paying twice: once for the 3 included seats in the Pro Plan, and again for the entire Inbox Plan – even if we don’t need the Inbox features and only require the extra seats occasionally.Suggestion: • Allow the option to purchase additional seats only, without having to enable the full Inbox Plan • OR: If the Inbox Plan is mandatory for technical reasons, the Pro Plan price should be reduced accordingly or the cost of the 3 included seats should be credited • Make it possible to add extra seats for specific months only (e.g., during promo events) without having to keep the Inbox Plan active across multiple months unnecessarilyThis would reduce unnecessary costs and give businesses more flexibility in scaling team capacity when needed.Is anyone else running into this issue?
As I use unique automation for each of my posts, it would be extremely beneficial to be able to search by the "word" that trigged the automation. What I'm doing to solve my search problems is to rename the automation related to what I'm posting. But being able to search by the trigger word would be super for us. Anyone elase??
Please please make manychat able to search for posts on instagram with link or ID just like for Facebook automations. Thank you!
The date picker functionality is clunky. Although it’s great that we can get users to submit a date - date of birth for example - once they have submitted that info, the window doesn’t auto close. It stays open, obscuring the view of the DM chat. The user then either has to close the window themselves, or click on any follow up messages that pop up in order to return to the chat. There is potential for losing users at this point.
For email and name we can remove the ‘skip’ button so that users have to enter their details. The same functionality does not exist for the ‘date’ field, it requires some sort of text in it, and leads to confusion for the user.
Meta releases whatsapp calling api for users to initiate calls with customers l would love if it would be implemented in manychat
A função do primeiro nome não esta funcionando.Poderia também ter a opção de colocar mais opções de mensagem de boas vindas, tipo ser randômico, Ex: Envia a mensagem 1, quando outro seguir envia a mensagem 2 e assim sucessivamente.Uma opção também de colocar o dia da semana na mensagem: Ex: Tenha uma ótima quarta-feira.
No account yet? Create an account
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.