We build practical data, BI, AI, and automation systems for growing teams - combining enterprise analytics experience with fast, demo-led delivery.
// AI PROJECT REGISTRY
Five inspectable systems, built to click into.
End-to-end data and AI capabilities, delivered as focused engagements with clear scope and measurable outcomes.
We design scalable data architectures and reporting systems that give leadership the clarity they need to act.
Interactive dashboards and self-service analytics that connect to live data and update automatically.
From demand forecasting to churn prediction, we build ML systems that solve concrete business problems.
LLM-powered agents, automated workflows, and custom internal tools that replace manual busywork.
Client Feedback
“You'll absolutely love working with Bálint because he is always ready to transform data into fully accessible and actionable insights. When I worked with him on a project, I was impressed by his professional skills and attention to detail.”
Csaba Mezei
Communications Designer & Marketing Manager
“I recommend Bálint for his exceptional data analysis skills. He consistently delivers quality analysis, demonstrating thoroughness and attention to detail. His commitment to continuous improvement makes him a valuable contributor to any team.”
Gáspár Horváth, MBA
Founder @ Miutcank
“Bálint was extremely helpful and flexible from the very first moment. I could reach him anytime, he responded quickly, and always suggested up-to-date solutions. What I especially appreciated was that he didn't leave me on my own after the website was finished, but continued to support me in using it.”
Anna Laura Selmeci, JD
Founder & Digital Legacy Specialist
About Meniva
I'm a Machine Learning Engineer who loves turning messy data into business impact. I founded Meniva to help growing companies build the data infrastructure they need without the overhead of a full in-house team.
With experience spanning e-commerce analytics, sales forecasting, and AI automation, I focus on practical solutions that drive real revenue and save real time. No buzzwords, just systems that work.
5+
Years in Data & AI
20+
Projects Delivered
A structured approach that delivers results. No surprises, just clear milestones.
Free consultation to understand your data challenges, goals, and current infrastructure.
Detailed proposal with clear scope, timeline, fixed pricing, and expected deliverables.
Agile development with weekly check-ins. We build in focused sprints with continuous feedback.
Production-ready delivery with documentation, training, and optional ongoing support.
// SELECTED AI BUILDS / DEMOS / CASE STUDIES
RAG search, AI copilots, agentic workflows, ML scoring, and learning systems with inspectable proof.
AI / RAG / AGENTIC WORKFLOW / ML / AUTOMATION
Restaurant review intelligence
AI RAG over restaurant reviews. Ask a question, inspect the evidence, open the demo.
1,660
review records indexed
repository fact
4
review sources normalised
repository fact
0
indexing failures
repository fact
AWS Bedrock / OpenSearch / source-linked answers
Hackathon market-intelligence workflow
LLM market-intelligence workflow. One question becomes hypotheses, evidence, and an action plan.
8
validated demo artifacts
repository fact
60
companies in source list
synthetic data
1
decision package per request
repository fact
Structured analysis / Qdrant evidence / workflow trace
Technical learning product demo
AI learning product with practice tracks, RAG explanations, progress events, and a live demo.
1,061
microdrills in test data
recorded test
5
tested learning tracks
recorded test
25/25
API tests passed
recorded test
FastAPI / React / curriculum / RAG configuration
// LABS & R&D
Capability examples under development. Repository facts are separated from benchmarks and outcomes.
Agentic prospecting capability demo
Agentic prospecting workflow. Research leads, keep evidence, score fit, export to CRM.
3
run modes
repository fact
2
export formats
repository fact
1
CRM handoff contract
repository fact
TinyFish / TypeScript / SQLite replay
Lead triage and decisioning prototype
ML-ready lead scoring workspace for enrichment, routing, review, and RevOps automation.
3
ML training paths
repository fact
4
worker roles
repository fact
1
ML feature contract
repository fact
React / Express / Prisma / rules + ML scaffolding
CPU-first research assistant
Local RAG for AI research. Search papers, rerank evidence, synthesize source-backed answers.
12
deterministic research topics
repository fact
25
defined evaluation cases; results not yet published
repository fact
0
paid inference APIs required at runtime
configuration
FAISS / MiniLM / Qwen / FastAPI
// PROFESSIONAL SYSTEMS EXPERIENCE
Alongside Meniva-built demos, Bálint has delivered data and decision systems in employed roles across retail analytics, large-scale data engineering, BI, forecasting, experimentation, and statistical-data modernisation. Examples are anonymised and separated from Meniva IP; no client code, data, names, or confidential results are reproduced here.
EXP 01
Decision workflows over commercial and market data.
EXP 02
Reliable transformation and quality controls at enterprise scale.
EXP 03
Governed semantic models and operational dashboards.
EXP 04
Reproducible models, evaluation, and decision framing.
EXP 05
Schema, quality, lineage, and publishing workflows.
CtrlPlane is the professional writing and research layer of the Meniva ecosystem: essays, field notes and strategic analysis on AI, data work, technology organizations and the changing infrastructure of knowledge work.
Most essays are currently published in Hungarian, with selected English versions planned. The goal is not daily commentary, but careful analysis of the systems, incentives and decisions behind technological change.
Why buying AI licenses is not the same as redesigning how work, data and responsibility flow through an organization.
Read on CtrlPlane Engineering SystemsAgentic coding makes code cheaper to produce, but validation, ownership, security and architecture become more important.
Read on CtrlPlane Labour MarketA research-based look at junior pressure, seniority inflation, productivity expectations and the changing economics of software work.
Read on CtrlPlaneReady to turn your data into a competitive advantage? Let's talk about your challenges.