Unsupervised Learning for the assessment of the Accelerometer data.

It is necessary to develop a service based on Claude or another suitable AI model that can automatically find competitor companies, contact them via email and phone, gather necessary information, and enter the results into a single table. Main task of the service The user specifies a specific request, for example: - to find out the price of a certain type of meat; - to find out the price of a specific type of wood; - to clarify the cost of a product or service; - to check the availability of a product; - to find out the delivery times; - to get the terms of cooperation. After that, the system should: 1. Find suitable companies. 2. Collect their contact details. 3. Send them personalized emails. 4. Call the companies using an AI bot. 5. Get answers to the questions asked. 6. Save all results in Google Sheets or another table. For each new task, the user should be able to change search queries, selection criteria, email text, and phone call script. Stage 1. Company database collection Stage 2. Email distribution and response collection Stage 3. AI calling of companies --- Important technical requirements - Ability to use Claude for generating emails, analyzing responses, and managing dialogue. - Ability to replace the AI model without a complete system overhaul. - Integration with Google Sheets. - Integration with Gmail or another email service. - Integration with an AI telephony service. - History of all emails, calls, and changes. - Ability to stop or pause a task. - Control of expenses for calls, emails, and AI requests. - Limitation on the number of calls per day. - Protection against resending emails and making repeated calls to the same company. - Compliance with legislation on phone calls, recording conversations, email distributions, and the use of personal data. --- Expected result As a result, there should be a service in which the user creates a task, specifies what information needs to be obtained, selects geography and sources, after which the system independently: 1. Collects a database of companies. 2. Finds contact details. 3. Sends personalized emails. 4. Calls companies according to the specified script. 5. Analyzes responses. 6. Forms a single table with results. 7. Shows from which source each piece of information was obtained. For the first discussion with the developer, it is also worth asking to separately estimate the cost and timelines for MVP, automatic parsing, AI telephony, and monthly infrastructure.

It is necessary to develop a prompt for AI (preferably Gemini but alternatives can be suggested), where we can use a specific style for generating images. The AI should take the style as a basis and, without changing it, create all the necessary forms of objects or people with the most predictable results. For example, generating characters based on photos that will resemble a real person and be organically integrated into the overall scene while maintaining the style.

Hello everyone! There are currently many sellers on the market selling claude tokens through proxies. I need to test different sellers and understand which API works most reliably for coding claude code. You will need to authenticate through the terminal in claude code and monitor the stability of the API (run it under load) and find the most optimal one. Who can take this on right now?

I'm looking for a performer to build an AI-agent system that automates the marketing and sales pipeline: from content generation to lead segmentation in CRM and hypothesis analytics. Below are the tasks grouped by functional purpose. How many services/agents will be in the final architecture and on which stack is up to you, based on your own experience. The main thing is that the solution covers all the tasks below, is functional, maintainable, scalable, and must have a convenient mechanism for review/approval of results by a person before publication or launching ads. Block 1. Content Generation (Multichannel Copywriting)One or several generating modules that produce texts for various formats based on project materials (course programs, interviews, broadcasts): Landing page texts Email sequences: warming chains, newsletters Posts in Telegram bot/channel Advertising texts for Meta, including variants for different hypotheses Content plan and posts for Facebook / Instagram / Telegram Blog articles (including based on transcribed videos — see Block 3)Block 2. Production of Final MaterialsTransforming the finished text into a final artifact ready for publication: Lead magnets — layout and assembly of a ready PDF (checklists, guides) with Canva/Figma integration for editing Meta advertising creatives — static visuals with resizes for campaign formats Landing pages on Framer — page structure, CMS filling, assembly of a ready page for launch.Block 3. Video → Blog Transcription of videos (broadcasts, interviews, workshops) Cutting the transcript into articles that lead into the funnel Publication in the blog on the main site (there is currently no blog — possibly a blog section needed on Framer CMS; open question: can the system create it itself, or is this a separate task)Block 4. Integration with Meta Advertising Cabinet Uploading finished texts and creatives to the cabinet Tagging ads/campaigns by hypothesesBlock 5. CRM and Lead Routing Automatic segmentation of leads in the Telegram bot (attended/did not attend the event, funnel branch, offer) Transferring segments to CRM Auto-tagging new leads in CRM when entering the funnel (through registration)Block 6. Hypothesis Analytics Formation of a table/dashboard of hypotheses: costs/results for each funnel, lead magnet, creative. Periodic AI analysis with recommendations: what to scale, what to stop Evaluation of landing page conversion ratesWhat We Expect in the Response Architecture Vision — how would you break these 6 blocks into agents/services, on which stack (orchestration, generation, data storage). Portfolio/Cases — examples of similar automation systems (marketing, leads, content generation). Estimated assessment of timelines and costs, preferably step by step. Questions about the Terms of Reference, if something is unclear.

We are looking for an experienced Python/AI developer (or a small team) to create an AI service based on a Telegram bot. The project automates the acceptance of orders from masters and service centers on an active B2B marketplace for spare parts for mobile devices and electronics (catalog of ~30,000 SKUs). What the bot should do:Multimodal input: accept text, voice messages (Whisper API), and photos of parts/markings (GPT-4o Vision), recognize nomenclature, revisions, and part numbers.Smart search: match masters' jargon (battery, accumulator, display, original) with official names through vector search (Vector DB).Interactive UI: when there are several quality options (Original, High Copy, etc.) — group them into one message, display inline checkboxes with prices and stock, recalculate the cart "on the fly".Cascading clarifications (Slot Filling): when faced with an ambiguous request, clarify parameters step by step (model → color → revision).Order processing: automatically send the completed JSON order package to the website via API after confirming the cart.Stack: Python (FastAPI), Aiogram 3.x, OpenAI API (GPT-4o + Whisper), Qdrant, Docker + docker-compose. Implementation period: 5–7 weeks.⚠️ Mandatory condition for response: To filter out auto-responses from spam bots, please indicate in your message: which embedding model you will choose for vector semantic search across 30,000 technical SKUs and why? Responses with template text that do not answer this question will be automatically rejected.