<IA/>
Projects

CASE STUDY / 01

Make an institute's research queryable, without letting the model make answers up.

A chatbot that answers with the institute's own publications, researchers and patents — never at random.

ROLE
AI design & reasoning engineering
SCOPE
Ontology modeling · RAG · Graph-constrained reasoning
STATUS
In development
YEAR
2026
PythonLangGraphLangChainQdrantRAGGraph Reasoning
01

CONTEXT

The problem

The institute's research output — publications, researchers, patents — is hard to explore unless you already know where to look. A plain LLM chatbot would answer fast, but with no guarantee the answer is true or traceable back to its source.

02

RESPONSE

The response

I modeled an ontology of the institute's research, then built graph-constrained reasoning: the model only answers by grounding itself in entities and relations that actually exist in the graph, retrieved through semantic search.

03

FLOW

From question to answer

  1. 01

    Ask

    The user asks a question in natural language.

  2. 02

    Retrieve

    Semantic search across the institute's knowledge graph.

  3. 03

    Constrain

    Reasoning is constrained to the retrieved entities and relations.

  4. 04

    Answer

    A reliable answer, traceable back to its sources.

04

SYSTEM

Reasoning pipeline

INGESTIONAGENTSMEMORYRESPONSECONSTRAINED REASONING

Ingestion, agents, memory, response — reasoning stays graph-constrained at every step.

05

TRADE-OFFS

Design decisions

01

Ontology before prompting

Structure the domain in a graph rather than leaving everything to prompt engineering.

02

Constrained reasoning

Deliberately narrow the answer space to reduce hallucinations.

06

EVIDENCE

What it changes

  • Answers grounded in real sources, not freely generated.
  • Institutional research finally searchable in natural language.

NEXT PROJECT

E-OPS