Dmitry Ivanov

AI Implementation Engineer

I build Go-to-Market systems, AI-powered outreach, and automation pipelines that ship to production. From concept to deployed system.

Classification pipelines Cold outreach automation RAG & knowledge systems Multi-agent platforms
neurocraft — data classification
> data classification _

From Idea to Production

I specialize in turning AI concepts into working production systems. My focus is on practical implementation: building RAG pipelines that handle complex documents, classification systems that process millions of records, and automation that replaces manual workflows.

Most projects in my portfolio run in production with real users and real data, while others are demos or proof-of-concepts ready to scale. I work across the full stack: from designing database schemas and vector search architectures to building React interfaces and deploying with Docker.

BasBot

Event-driven B2B AI agent platform: multi-LLM, multi-tenant, production-grade. Built on FastAPI + asyncpg + PostgreSQL with no LangChain, no Celery, no ORM. PostgreSQL is the only datastore and job broker.

Ingress
Telegram / Web
input
Routing
LLM intent
classify
Context
L0 / L1 / L2
memory
Planning
structured plan
strategy
Executor
Docker sandbox
isolated
Delivery
chat / Telegram
output
Multi-LLM routing
Claude, Gemini, Kimi, MiMo, GLM: backend + model configurable per-stage via DB. Swap providers at runtime without code changes.
Docker-isolated executor
Executor sidecar with iptables blocking private and metadata IPs. No host source mount. Credentialed ops go through named capability proxies.
Tiered memory + graph
L0/L1/L2 tiers with dual embeddings. BM25 + vector hybrid retrieval. Graph entity extraction. Context persists and compounds across sessions.
Operator approval gate
Planner produces structured plans; executor acts only after operator approval. Kanban board with real-time task lifecycle and artifact viewer.
Pluggable skills system
Runtime skill registry with per-bundle filtering. Skills declared in Markdown, injected at planning time. Zero hardcoded domain logic in core stages.
B2B multi-tenant
Workspace isolation, per-tenant LLM configs, browser session auth + Bearer API keys. FOR UPDATE SKIP LOCKED as the only job queue primitive.
Currently building

Company Brain

Durable, searchable memory for a whole company. It pulls in meetings, Slack, email, Jira, Confluence, CRM, ERP, and whatever else the team runs on, then turns it all into one typed knowledge graph where every fact keeps a link to its source. Ask a question, get an answer with citations back to where it came from.

Incoming signals
  • Slack "customers charged twice"
  • Meeting billing bug blocks release
  • Jira epic blocked 6 days
  • HubSpot repeated request
Company topic
Billing
At risk
Morning brief
  • 2 active blockers
  • 4 customer reports
  • 1 problem without Jira
  • Decision changed 12 Jul
View evidence
  • Slack "customers charged twice"
  • Meeting billing bug blocks release
  • Jira epic blocked 6 days
  • HubSpot repeated request
Evidence-backed synthesis
AI proposes topics, links and summaries; confidence gates, schemas and source provenance keep an uncertain conclusion from silently becoming a stated fact.
Entity resolution under uncertainty
Jira issues, meetings, people and customer requests get reconciled against each other, not just tagged. A typed schema blocks invalid graph shapes, but can't rule out a plausible-sounding relation that was never actually said.
Proactive gap detection
Finds repeated customer pain, stalled promises, and decisions that never became planned work: the problems nobody filed a ticket for.

HubSpot AI Integration

Intelligent ticket processing with intent classification, type detection, and AI-proposed actions. Enriches tickets with internal system data for faster resolution.

Production

Tender Processing Pipeline

Enterprise automation processing tender emails from 9 procurement platforms. 4-stage LLM pipeline for classification and extraction with local Qwen2.5-14B on RTX 4090.

Production

RAG Knowledge System

Enterprise Q&A over technical documentation with semantic search, vector embeddings, and GPT-4 answer generation. Powers internal knowledge discovery.

Production

Vision RAG for Tables

RAG system specialized for complex PDF documents with tables. Vision models for layout understanding, table healing for broken cells, hybrid search with semantic + keyword retrieval.

Demo

YouTube Shorts Analyzer

Viral content analysis platform. Batch processes YouTube Shorts, extracts frames, transcribes audio with Whisper, classifies with Claude Vision. Builds trend database.

Demo

EdTech Suite

Unified language learning platform with handwriting OCR, Cambridge assessment, AI audio lessons with multi-voice TTS, interactive exercises. 13 languages supported.

Demo

PriceScout

Computer vision price tag detection using YOLOv8. Extracts prices with EasyOCR and matches products using vector embeddings.

PoC

Core Stack

AI / LLM

Claude OpenAI Gemini DeepSeek Kimi OpenRouter

AI Dev Tools

Claude Code Codex Cursor v0

Multimodal

Whisper ElevenLabs PaddleOCR

Backend

Python FastAPI asyncpg Node.js Rust C#

Data

PostgreSQL pgvector SQL / SSRS Power BI Redis

Infrastructure

Docker Nginx React TypeScript Alembic

Let's Build Something

Have an AI project that needs to ship to production? I'm available for contract work and consulting.