§ projects

Open-source systems & research artifacts.

A selection of open-source systems and research artifacts by Ademar Tutor: GLAMLI (Master's dissertation), LexiTau and LexExtract (agentic Text-to-SQL over financial documents), an LLM-as-a-Judge evaluator, and SafeBeautyLedger. Most started as research questions and ended up as code — from papers, from production problems, or from a weekend's curiosity. Each links to a write-up, the repo, or both.

indexjump to
§ 01research & OSS
  • GLAMLI (Dissertation)

    2025– · in progress

    Guided LLM-Augmented Machine Learning Interface — an agent that walks non-experts through a real ML workflow (load → profile → train → evaluate → deploy).

    • Planner-with-revision orchestration topology
    • Typed tool registry (data primitives) the agents call into
    • Sandboxed code execution for generated Python
    • Structured observability traces for trust calibration and failure analysis
  • LexiTau

    2025 · agentic text-to-sql

    Agentic Text-to-SQL pipeline for financial document querying. End-to-end: profiling → metadata → schema linking → SQL draft → safety checks → execution → narrative explanation.

    • RAG-based schema context retrieval (Jaccard over metadata, cosine on queries)
    • Multi-tenant isolation: per-tenant embeddings, scoped auth, row-level policies
    • OCR ingestion (Azure Form Recognizer) normalised into tenant-scoped tables
    • Stack: FastAPI · PostgreSQL+pgvector · SQLAlchemy · Celery/Redis · Next.js · Docker Compose

    Multi-tenant RAG with real isolation is rare in public artifacts.

  • LLM-as-a-Judge Evaluator

    2025 · evaluation methodology

    Statistical-rigor evaluation framework for LLM-judged outputs. Seven SPIN-based scoring dimensions, evaluated with QWK, Pearson r, and ±1 accuracy — three metrics that disagree about which judge is best, which is the point.

    • Pydantic schema enforcement; prompt-level contracts for deterministic, auditable outputs
    • Tenant-scoped prompt versioning with audit trails (Postgres + SQLAlchemy)
    • Score-once / evaluate-many workflow that cuts LLM cost without losing fidelity
    • Multi-LLM provider integration (OpenAI · Anthropic · Google)
    • Stack: FastAPI · PostgreSQL · SQLAlchemy · LangChain · Docker · Azure Container Apps
  • LexExtract

    2024 · ocr → text-to-sql

    OCR-to-Text-to-SQL platform for financial document querying. Natural-language queries over PDF-extracted financial data.

    • Full pipeline: PaddleOCR → LLM-based Text-to-SQL with memory-efficient processing and progressive fallback
    • Explainable query outputs through structured SQL generation and validation layers
    • Stack: FastAPI · PostgreSQL · PaddleOCR · Mistral 7B · Docker
  • SafeBeautyLedger

    2024 · blockchain · gdip

    Blockchain traceability for beauty-industry product provenance. Immutable history, public verification, on-chain product registry.

    • Solidity smart contracts (Hardhat) with versioned product records, event-driven history retrieval
    • On-chain / off-chain data flow integration
    • Stack: Solidity (Hardhat) · Node.js + TypeScript · PostgreSQL · Ethers.js · Next.js

    Outside the multi-agent work, but a useful counterpoint — different problem class, same engineering discipline.

§ 02get in touch

Open to conversations about applied multi-agent research.

See also: about · writing.