Dmitro Strokachenko
Offer Dmitro work on your next project.
Private message 
Offer work 
Odessa,
Ukraine
6 hours 40 minutes back
available for hire
6 Safes completed
2 months 29 days back
1 client
25 proposals made
on the service 7 years
Rating
Language proficiency level
Русский: fluent
Українська: advanced
English: pre-intermediate
Skills and abilities
Programming
Services
Photo, Audio & Video
Portfolio
- All works 6
- Online Stores & E-commerce 2
- AI & Machine Learning 1
- Enterprise Resource Planning (ERP) 3
-
Launch of a women's sportswear store on the Prom marketplace.
Online Stores & E-commerce
Setting up the women's sportswear store FitFeel on the Prom.ua marketplace "turnkey".
https://prom.ua/c4205391-fitfeel-zhenskaya-sportivnaya.html
What has been done:
— Complete setup of the seller's account: company, contacts, schedule, details
… — Connection of payment (Prom-payment, cash on delivery) and delivery (Nova Poshta, Ukrposhta, self-pickup)
— Import of 840+ product items via XML from Horoshop
— Combining products into variations — selection of color and size in one card
— Distribution of products by marketplace categories and structuring of the catalog
— Complete rewriting of product descriptions from scratch
— Creation of product characteristics from scratch for the reference guide of each marketplace category (for the correct operation of search filters)
— Setting up search queries for each product
— SEO optimization of product cards (titles, descriptions, tags)
— Designing the store page, description "About the seller" (UA + RU)
— Testing and launch
Result: the store is launched, products are correctly displayed in the catalog with working variations, filled characteristics, and functioning filters.
-
Comprehensive launch of the online store — FitFeel
Online Stores & E-commerce
Implemented the full cycle of launching an e-commerce project for a women's sportswear brand with over 15,000 customers.
What has been done:
— Development and setup of the store on Horoshop
— Connection of payment systems and delivery
… — Integration with the CRM system
— Setup of analytics
— SEO optimization of categories and subcategories
— Customization for the brand
Result: a fully ready-to-sell store with automated processes.
Website: https://fitfeel.com.ua/
-
AI consultant for tire selection in Telegram
Enterprise Resource Planning (ERP)
Task
The tire shop is losing inquiries during non-working hours and wasting managers' time on standard questions: "which tires are suitable for my car," "how much do they cost," "are they in stock." A system is needed that conducts initial consultations 24/7, qualifies clients, and passes warm leads to the manager.
Solution
… A Telegram bot based on LLM, orchestrated through n8n. The bot operates like a live consultant: it determines the client's language, collects parameters in a natural dialogue format, selects suitable tires from the real store catalog, and guides the interested client to a request — with contacts and a list of desired models in a table for the manager.
Architecture
Telegram Trigger → AI Agent (GPT-4o-mini) with dialogue memory and access to the tire catalog (Google Sheets as a tool) → parsing the response and extracting structured data → sending to the client + logging → merge logic for leads → CRM table.
Key Features
Smart Dialogue
Auto-detection of language (Ukrainian / Russian) from the first message and maintaining it throughout the dialogue
Memory for 20 messages — the bot remembers the context
Funnel: car parameters → season → budget → selection → processing
Short messages with 1-2 questions at a time — like a live manager, not like a survey
Selection from the Real Catalog
The agent calls Google Sheets as a tool, filters by size and season
Provides 2-3 options with prices, availability, and a brief justification for the choice
Does not hallucinate: if the product is not available — it honestly states so and offers an alternative
CRM Funnel
Classification of each dialogue: HOT / WARM / COLD
Hot leads are saved in a separate table with contacts and a list of recommended tires
Automatic calculation of conversion time (from the first contact to readiness to buy)
Status model: New → Hot → Contacted → Closed — the manager leads the client in the same table, the bot does not overwrite their changes
Analytics
All dialogues are logged with reference to the lead status
Data for optimization: what inquiries come in, at what step clients drop off, which tires are recommended more often
Scalability
The current architecture is optimal for catalogs of up to 300-500 items — the full catalog is loaded into the LLM context, ensuring maximum accuracy in selection. For larger catalogs, it can easily scale to a RAG architecture with vector search (Qdrant / Supabase).
Result
The bot completely replaces the manager at the initial qualification stage. The manager receives only hot clients with ready information: what they want, which tires they viewed, when they contacted, and their contacts. The lead processing time is reduced significantly.
Stack
n8n · OpenAI API (GPT-4o-mini) · Google Sheets API · Telegram Bot API · JavaScript (Code nodes) · Prompt Engineering
-
AI Product Description Generator
AI & Machine Learning
Web tool for automatic generation of product descriptions using artificial intelligence. You insert a link to the product or the model name — you receive a ready-made SEO description based on your template in Ukrainian.
What has been implemented:
- Auto-parsing of product pages
… - Searching for specifications by model name through AI web search
- Several templates for different product categories with auto-saving
- Export/import of templates as .json
- Downloading the result as .txt
- Telegram notifications for monitoring
- Deployment on Vercel
Stack: Next.js, Claude API (Anthropic), ScraperAPI, Vercel
-
Automation of warehouse synchronization KeyCRM → Google Sheets
Enterprise Resource Planning (ERP)
Many online stores face a problem: product stock in the CRM is updated, but in the accounting, analytics, or team tables, it remains outdated. This leads to manual data entry, errors in stock levels, and a lack of timely notifications about critical product quantities.
I have developed an automatic solution for synchronizing data between KeyCRM and Google Sheets in real-time with a notification system.
… What has been implemented:
- updating product stock via webhook from KeyCRM
- adding new products through polling API
- automatic recording of stock change history
- processing orders with recording in a separate Google Sheets sheet
- notifications in Telegram for critical product stock (≤5 or 0)
Technologies:
- Google Apps Script, KeyCRM API, Telegram Bot API, Google Sheets.
Result:
- automatic inventory control
- instant notifications about critical stock levels
- elimination of manual data entry
- reduced risk of errors in product accounting
- the solution works without a server (serverless)
- secure storage of API keys and tokens
Expansion possibilities:
- sales and stock analytics
- automatic reports
- integration with other CRMs or marketplaces
- automatic order creation
-
AI system for automating content publication in Telegram
Enterprise Resource Planning (ERP)
AI news auto-publishing system for Telegram channel
Task
Automatically gather news, process it, format posts, and publish in the channel, leaving final confirmation to the administrator.
…
Solution
Hybrid system on Python and Make
Collects fresh news from specified sources
Excludes duplicates
Transforms text into a ready Telegram post via AI
Selects and enhances images, adds logo and branding
Sends preview to the administrator and waits for confirmation before publishing
Example of system operation
AI processed news from World of Tanks: HEAT
Added branding to the image
Sent preview to the administrator with confirmation buttons
After confirmation, the post is published in Telegram
Architecture
Python (parsing) → Webhook → Make → AI processing → Telegram Bot API → moderation via inline buttons
Result
Complete automation of the publishing process
Minimal manual work — the administrator only confirms
The system is easily scalable to other topics: games, media, e-commerce, etc.
Technologies used
Python, Make, OpenAI API, Telegram Bot API, Google Sheets
Reviews and compliments on completed projects 6
25 March
17 USD
Translation of the SRX 55MAG instruction
Quality
Professionalism
Cost
Contactability
Deadlines
The work was completed quickly, without comments.
Serhii M
| Personal | Response review
23 March
223 USD
Translation of 10 instructions for exercise machines
Quality
Professionalism
Cost
Contactability
Deadlines
Done quickly and efficiently according to the technical assignment.
|
23 March
223 USD
Translation of 10 instructions for exercise machines
Quality
Professionalism
Cost
Contactability
Deadlines
The order was completed quickly. I recommend.
Serhii M
| Personal | Response review
20 March
22 USD
Translation of the instruction for the treadmill FK 855 Slim
Quality
Professionalism
Cost
Contactability
Deadlines
Completed quickly. Everything is good. I recommend.
Serhii M
| Personal | Response review
19 March
22 USD
Translation of the instruction for the treadmill Mirage C60
Quality
Professionalism
Cost
Contactability
Deadlines
The translation was done on time and of high quality.
Serhii M
| Personal | Response review
18 March
11 USD
Translation of the instruction for the treadmill Mirage C90
Quality
Professionalism
Cost
Contactability
Deadlines
Done quickly and quite well, all comments were changed quickly. Technical terms were used in the translation. I recommend.
Serhii M
| Personal | Response review
