Fixing a Telegram bot in Python (or a parser)

A Telegram bot needs to be developed in Stand Pulse for the client's test. The test has 5-7 questions with 5-7 answer options. Based on the client's answers, the bot will calculate scores and provide a result (6 options).

Develop a Telegram bot for receiving and processing customer inquiries, as well as a web administrative panel for managers. The Telegram bot should provide a modern and convenient communication format, similar to the Monobank support service: displaying an inquiry counter (under the nickname), confidentiality (clients have access only to this chat, other users are restricted), a convenient chat with the manager, and an intuitive interface for the user. The administrative panel should provide managers with full functionality for effective work with inquiries, including their distribution, maintaining a communication history, changing application statuses, and internal interaction. Special attention should be paid to the analytical module, which will allow tracking key performance indicators: inquiry statistics, first response speed, average application processing time, productivity of each manager, inquiry conversion, team workload, and other KPIs for assessing service quality. We have attached a more detailed technical specification in the format of Google Sheets for your review (in addition to the specification itself, other sheets contain deadlines and other questions that may interest you).

There is a Telegram bot on aiogram/FastAPI (CRM for an event project) and a separate ManyChat bot in Instagram Direct for communication with clients.Task 1 — fix the logic of the Instagram Direct bot.The current bot is made according to a strict script: it works step by step (greeting → about the event → response to "too expensive" → response to "I'll think about it"), with 3 random text options for each step. The problem is that the bot does not understand the meaning of the message, but guesses the step number and sends a template that is off-topic. Because of this: when asked directly about the price, the bot does not provide numbers but sends general text the language jumps — sometimes Ukrainian, sometimes Russian essentially, it is a randomizer of templates, not a dialogueIn a week, the bot lost several live leads. I can provide screenshots of conversations as examples.Need: for the bot to actually analyze the content of the message (question about price, objection "too expensive", doubts "I'll think about it", non-standard question, etc.) and respond appropriately — based on AI (for example, Claude API), not according to a strict script. The tone should be lively, not robotic, and the language should be Ukrainian. Basic scenarios (price, discounts, handling "too expensive"/"I'll think about it") need to be preserved, but the AI should choose the appropriate response based on the context.Task 2 (optional, but also needed) — auto-posting in Instagram.Posting through the official Meta Graph API: reels, stories, posts, carousels. Tags in the bot: [reels] / [stories] / [post] / [carousel] + [geo] / [poll] / [countdown]. Multi-user panel /admin — adding/removing people, roles (posting / viewing / all), activity log. Dynamic price from Google Sheets — the bot pulls the current price from the "Price" column.Questions for the performer: Is it better to implement Task 1 (AI logic for Instagram Direct) on top of the current ManyChat via webhook + external AI processor, or as a separate bot on an architecture like aiogram/FastAPI, connected to Instagram through the official Meta API? Are you taking on both tasks together (Direct logic + auto-posting)? What is the total cost and timeframe for the entire scope (task 1 + task 2)?Requirements: Experience with Meta Graph API (Instagram) Experience integrating AI models (Claude API / OpenAI API) into chatbots Preferably — experience with aiogram/FastAPI or ManyChat webhooks Portfolio with similar projects

Project Title: Automation of content publication on social media via a Telegram bot using AI Task Description: Our company sells premium fitness equipment from the Italian manufacturer Panatta in Ukraine. We manage several social media platforms: Instagram, Facebook, TikTok, and a Telegram channel. An automated solution needs to be developed that will allow us to quickly adapt and publish video content across all our social media platforms. Main Logic of Operation: I send a link to a video from YouTube, Instagram, or TikTok to the Telegram bot. The system automatically retrieves the description of this video, translates it into Ukrainian, adapts the text to the live communication style of the Panatta brand, adds links to our social media, and publishes the finished post on: Instagram, Facebook, TikTok, Telegram channel. Important: The video itself does not need to be changed or translated. We need to work with the video description: translation, adaptation, text optimization, and publication together with the video or a link to it — depending on the technical capabilities of the specific platform. Desired Workflow Scenario: I send a link to the video to the Telegram bot. The system identifies the source: YouTube, Instagram, or TikTok. The system retrieves the original video description. AI translates the description into Ukrainian. AI adapts the text to the premium brand style of Panatta: professionally, lively, without dry machine translation. Links to our social media are automatically added to the text: Instagram, Facebook, TikTok, Telegram. The system prepares the publication for each platform. The publication is automatically posted on Facebook, Instagram, TikTok, and the Telegram channel. It is preferable to have the option to review the text and confirm publication via the Telegram bot before posting. Desired Functionality of the Telegram Bot: The bot should accept links to videos. The bot should display the generated Ukrainian text before publication. It is preferable to add buttons: "Publish", "Edit", "Generate Again", "Cancel". The bot should notify whether the post was successfully published on each social media platform. It is preferable to keep a history of processed links. Possible Technical Stack: We are considering various implementation options: Make.com, n8n, Zapier, custom backend, Telegram Bot API, OpenAI API, or other AI services. We are open to contractor suggestions regarding the optimal technical solution. Additional Considerations: It is necessary to check the technical limitations of the APIs for Instagram, Facebook, TikTok, and YouTube. A stable account authorization scheme needs to be proposed. It should be explained whether fully automatic publication is possible on all social media or if manual confirmation is required for some platforms. Protection against post duplication should be anticipated. The solution should be made as simple as possible for daily use. Expected Result: A working automation system where a link to a video can be sent via the Telegram bot, an adapted Ukrainian description can be received, and content can be published on Facebook, Instagram, TikTok, and the Telegram channel. What is required from the contractor in the response: Briefly describe how you propose to implement this solution. What stack will you use: Make.com, n8n, custom development, or another option. Which social media can be fully automated, and where might there be limitations. Estimated implementation timelines. Estimated cost. Examples of similar automations, if any. Additional Information: The Panatta brand represents premium Italian sports equipment for fitness clubs. Therefore, the texts must not only be translated but also adapted to the Ukrainian market, with the correct positioning: premium quality, Made in Italy, biomechanics, design, professional level of equipment. Links to our social media will be provided to the selected contractor.

Set up ManyChat Pro + OpenAI API (model gpt-4o-mini, but you can suggest something niche). Without Make/Zapier, if it can be implemented with ManyChat's internal tools, or with them if you justify the need.Bot operation logic:Triggered by any incoming message from a new client (including transitions from ads).The bot should conduct a dialogue based on the provided prompt (information about the company/prices/FAQ will be provided). The goal of the bot is to consult and collect contact details (phone) or lead to a specific purchase request.Conditions for transferring to a manager:The client directly requests a person/manager.The client has left contact details.The bot does not know the answer to the question.Action upon transfer: the bot must inform the client that it is connecting a person, send a notification, and definitely stop automation so that AI does not respond while the manager is working.Requirements for the executor:Show 1-2 similar casesSet up protection against hallucinations (so that the bot does not invent prices and does not promise what is not available).Deliver the finished bot, explain where to edit the prompt (instructions for AI) and where managers can view chats.