Anastasiia A.
Offer Anastasiia work on your next project.
Private message
Offer work
Lvov,
Ukraine
1 month 13 days back
available for hire
on the service 1 month 17 days
Rating
Successful projects
Average rating
Language proficiency level
Українська: fluent
English: upper-intermediate
Skills and abilities
Programming
Services
Portfolio
-
225 USD AI assistant for café volunteers
Bot Development
Creation of an intelligent Telegram agent that automates volunteer support for a non-profit café, allowing the team to focus on hospitality rather than searching for operational answers.
Context
D.Café is a non-profit project where all profits go to charity. The team consists of volunteers who work in shifts and have varying levels of training. The core philosophy of the café is "radical hospitality." Before the implementation of the solution, volunteers spent time searching for answers regarding operational processes, which distracted them from interacting with guests.
…
Problem
Lack of quick access to a knowledge base: cash register procedures, equipment usage, menu standards, and communication scripts.
The need to constantly distract experienced team members for basic instructions.
Loss of focus on guests due to technical and organizational questions, especially during the onboarding of new volunteers.
Goal: to provide volunteers with instant access to all operational information through a familiar tool (Telegram) without the need for additional training.
Solution
A conversational AI agent has been developed that acts as a digital administrator. The system is based on a structured knowledge base containing a complete description of the café's processes. The agent uses semantic search, allowing it to understand the context of questions rather than just keywords.
Key Features:
RAG Architecture: responses are based solely on the uploaded café instructions, ensuring their accuracy.
Tone of Voice: setting a warm and welcoming communication style that aligns with the values of D.Café.
Zero entry threshold: using Telegram as the main interface, which does not require the installation of new applications.
Accuracy control: the agent is configured to report the absence of information instead of providing unverified data.
Implementation Process
Audit and structuring of knowledge: gathering instructions for opening/closing shifts, kitchen rules, cash procedures, and guest interaction scripts.
Building a knowledge base: organizing information into a vector database optimized for precise contextual search.
Agent architecture in n8n: using OpenAI Chat Model with Simple Memory integration to maintain conversation context and OpenAI Embeddings for semantic search.
Tone configuration: programming a specific style of responses (using phrases like "happy to help," "have a blessed day," etc.).
Testing and launch: deploying the bot, conducting briefings for volunteers, and collecting feedback directly during shifts.
Results
Automatic processing of 10-20 requests per shift that previously required administrator involvement.
Average response time of up to 60 seconds, allowing volunteers to quickly return to working with guests.
Minimal operating costs for the system due to optimized API requests.
Accelerated onboarding: new volunteers receive real-time support.
High level of trust in the system due to the accuracy of responses and adherence to corporate communication ethics.
#n8n #AI_Assistant #RAG #KnowledgeBase #OpenAI #Telegram_Automation #NonProfit_Tech #CustomerService_AI #SemanticSearch #VectorDatabase #VolunteerManagement
-
270 USD AI agent for automating content creation
Bot Development
Understood, we will make the description more restrained and professional. Here is a case presentation option without emojis:
Project Title:
Multimodal AI Agent in Telegram for Automating Content Creation (n8n + OpenAI + Google Sheets)
…
Job Description:
Development of an intelligent system in Telegram that automates the process of transforming ideas (text or voice) into structured posts with visual content generation.
Context:
The content creation process for social media typically consists of several manual stages: recording thoughts, transcription, structuring text, selecting visual elements, and saving results in a database. The project aimed to create a single entry point for instant idea processing.
Problem:
The difficulty of capturing thoughts in real time.
The need to use several separate services for transcription, text generation, and image creation.
The lack of an automated draft archive, leading to chaotic data storage.
Goal: to maximize the simplification of the path from idea to finished draft in Google Sheets.
Solution:
A complex architecture based on n8n was developed, integrating several AI agents. The system automatically determines the type of input data, processes it using specialized instructions, and outputs the final result to the messenger and database.
Key Technical Features:
Processing voice messages: integration with Whisper for converting audio to text.
Memory-enabled AI agents: using Memory nodes to maintain dialogue context and develop post structure.
Image generation: integration with visual content generation models directly in the bot interface.
Database: automatic logging of results in Google Sheets for further use.
Implementation Process:
Building routing logic for correct processing of different types of messages and commands.
Implementing a chat context preservation system to improve generation quality.
Configuring Speech-to-Text nodes for instant audio transcription.
Developing and testing system prompts for agents responsible for text and images.
Setting up final integration with Google Sheets API for structuring output data.
Results:
Complete automation of the idea processing workflow: from incoming message to finished result in less than 30 seconds.
Combining several stages of content production in one interface.
Creating an organized database of ideas and drafts.
The ability to easily adapt the system to different communication styles or platforms.
#n8n #Telegram_Bot #AI_Agents #OpenAI #Whisper #DALL-E #Automation #Content_Marketing #Google_Sheets_API #SpeechToText
-
449 USD AI agent for media monitoring automation
Bot Development
Creation of an intelligent system that replaces 30+ hours of manual monitoring per month with a fully autonomous agent based on RAG architecture.
Context
Caritas Ukraine is one of the largest charitable organizations in the country (over 40 regional branches) in the NGO and humanitarian aid sector. The communications team manually monitored the media daily: searching on Google, copying headlines into Google Sheets, checking Facebook, Instagram, and LinkedIn. Existing third-party solutions had a limit of 10 queries per session, which was absolutely insufficient for such scale.
…
Problem
Relevance: The search yielded hundreds of results about Caritas's international offices, most of which were not related to activities in Ukraine.
Criticality: A missed mention could mean an inappropriate press inquiry or a timely identified reputational risk for any of the 40+ local offices.
Losses: Over 30 hours per month were spent on mechanical "copy-paste" work — a whole working week of a specialist.
Goal: Complete automation of data collection, geographical filtering, and report generation.
Solution
I designed an autonomous AI agent based on n8n, using RAG (Retrieval-Augmented Generation) architecture. Instead of simple keyword searches, the system works with the deep context of the organization: it "understands" which branches exist, where they operate, and which topics are relevant for each of them.
The agent independently searches for information in the media and social networks, filters out irrelevant international mentions, classifies results by topics and sentiment, removes duplicates, and prepares draft reports for management — without human involvement.
Implementation Process
Audit and Research: A complete structure of the organization (40+ branches) was formed to create accurate geographical and contextual filters.
Architecture Design: The logic of the "Analytical Agent" was developed — a multi-step workflow that works with the organization's vectorized data.
Building the RAG System: A vector database (Pinecone) was integrated, containing data about the structure and regional context of Caritas Ukraine.
Prompt Engineering: Prompts were configured for deduplication, topic classification, and sentiment analysis for different types of publications.
A/B Testing: A comparison of the results of manual searches and the AI agent's output was conducted to confirm filtering accuracy.
Optimization: Batch processing of data was implemented, which reduced API costs by 10 times without loss of quality.
Results
- Time savings of 85% — 8 hours of manual work per week fully automated.
- Budget preservation (~$180/month) — comparison of the cost of specialist working hours to API expenses.
- Filtering accuracy of 95% — confirmed by A/B tests; complete absence of duplicates.
- Reduction of API costs by 10 times due to process optimization.
- Strategic shift: the communications team moved from data collection to strategic analysis.
- Reliability and transparency: each mention is logged, classified, and easily traceable.
#N8N #AI_Agents #openai-api #ChatGPT-4 #RAG #API_Integration #AI_Automation #MediaMonitoring #Workflow_Optimization #DataAnalysis