Agentic development · Real data · No black boxes
is the future, today.
I build agentic systems and data tools for real problems. Clear, auditable, and made to last.
I don’t sell AI for its own sake. I use it when it genuinely reduces work, and choose a simpler solution when it doesn’t.
Where the work runs
I choose the environment around the risk, data, and operation.
You choose.
The infrastructure I design. Your rules.
I design each tool to run where it makes sense: on your machines, on managed servers, or in your own cloud.
Deploy where it fits
I can run the solution locally, on private servers, or in the cloud. The architecture adapts to the project’s risk and constraints.
Open source, auditable
I build components that can be inspected, reviewed, and maintained. No hidden APIs or opaque models behind a promise you cannot verify.
From bottleneck to operations in three steps.
Identify the bottleneck
Duplicate data? Reports that break on Mondays? Audits that take weeks? Each tool targets a specific problem.
Deploy the right tool
No month-long implementations. Activate the product that solves it, connect to existing infrastructure, and it starts working.
Scale operations
What starts solving a single problem becomes the team's operational backbone. Monitoring, traceability and automatic documentation.
A suite of tools that get it done.
Each product I build targets a specific problem. It can be deployed independently and grow with the operation.
Swarm-Driven Development
A review-first operating system for building with AI agents
An open-source workflow for turning ambiguous work into small, reviewable units. It keeps human judgment, evidence, and delivery gates in the loop instead of hiding them behind an agent swarm.
- Explicit roles and handoffs
- Evidence-driven review gates
- Recovery instead of silent failure
DataVIZ / BI Bridge Studio
Tableau and Power BI migration toward portable, verifiable BI
An engineering project for importing BI assets, preserving their intent, and building a validation workflow for numerical, semantic, and visual fidelity. Tableau → Power BI is the MVP; DataVIZ aims at a neutral, portable web runtime.
- Tableau → Power BI migration
- Neutral IR and technical lineage
- Numerical and structural validation
Data Governance Suite
Total visibility of data flows, risk auditing, and technical lineage
Comprehensive platform for Apache NiFi. Automates security backups, detects critical changes in SQL code, tracks field-level lineage, and sends impact alerts to Microsoft Teams.
- Deep Lineage: Field-to-field data tracking
- Smart Alerts: Microsoft Teams integration
- Audit & Diff: SQL and Security (PII/Secrets) auditing
- Impact Analysis: Blast Radius calculation
Data Governance Chat Bot
Instant queries about policies and metadata
Conversational assistant specialized in internal data structures, business rules, and governance policies. Find definitions without checking outdated wikis.
- Interactive metadata chat
- Lineage resolution in natural language
- 24/7 support for analytics teams
Data Governance Auto Documentator
Automatic technical documentation generation
Autonomous value-stream documentor. Scans DBs, ETLs, Power BI DAX, Schedulers, AWS, and NiFi clusters to generate accurate data dictionaries and lineage maps.
- Supports DB, ETL, PBI DAX, Schedulers, AWS, NIFI
- Continuous technical glossary updates
- End-to-end dependency mapping
OCR to Word for Translations
Accurate image to editable document conversion
OCR engine designed for translators. Respects original formatting and outputs clean Word (DOCX) files, ready for CAT tools and Translation Memories.
- Multilingual text extraction
- Layout and table preservation
- Native export to translation pipelines
Audio CC for meetings
Local live Closed Captions for meetings and translations
Real-time CC generation for any video calling platform. Facilitates comprehension and simultaneous translation with no visible latency.
- Real-time CC generation
- Platform agnostic (Teams, Zoom, Meet)
- Total privacy via edge processing
Tableau → Power BI Migrator
Automatic dashboard migration without manual rebuild
Converts Tableau workbooks into Power BI reports automatically. Parses calculated fields, relationships, and visual layouts via AST analysis, no manual re-creation needed.
- Automatic calculated field conversion
- Visual layout preservation
- Relationship and data source mapping
Mindsight
Physical and mental wellness dashboard focused on sleep
Personal health platform that measures, visualizes, and gamifies sleep and wellness habits. Turns health data into actionable metrics to improve quality of life day by day.
- Sleep tracking and wellness metrics
- Gamification with achievement system
- Trend and pattern visualization
Engineering, not magic.
AI is a tool, not a religion. I use it where it genuinely reduces work and discard it where a simpler solution does the same job. What matters: the product works, is understandable, and is maintainable.
What I build
I build tools for concrete problems: data organization, smart search, automated auditing, and measurable wellbeing.
What I don’t do
I don’t sell AI just to inflate the bill. I don’t ship demos that only work on stage or add complexity where a simpler tool would be better.
Real code. No tricks.
This is what a governance audit looks like inside. No prompts, no middleware layers — direct logic on real data.
# governance/audit.py — No magic, just engineering
def audit_data_asset(asset_id: str, config: AuditConfig) -> AuditReport:
"""Complete technical audit. No prompts,
no wrappers. Real validation on real data.
"""
asset = catalog.get(asset_id)
checks = [
validate_schema(asset, config.expected_schema),Validates that data structure hasn’t changed
check_freshness(asset, max_staleness_hours=config.sla_hours),Detects stale data before it breaks reports
]
findings = [c for c in checks if c.severity != Severity.OK]Surfaces only what actually failed
return AuditReport(asset=asset, findings=findings)The code is open.
Explore the products, try the tools, or book a demo directly.