Technologies

The technology
behind Amicus.

We invest in the building blocks that make AI useful for business — durable, auditable, and built to grow with your data. This page covers the in-house technologies we develop ourselves, starting with the Amicus Knowledge Graph.

01 · The retrieval problem

Retrieval alone isn't enough.

Most enterprise AI today is built on retrieval-augmented generation (RAG). The idea is simple: when you ask a question, the system finds text chunks that look semantically similar to your query, hands them to a language model, and the model writes an answer.

For simple lookups — "what's our return policy?" — this works. But the moment your question requires structure, the cracks show.

× Issue 01

Similarity is not truth

Retrieval ranks documents by how alike their embeddings are. Two passages can be nearest neighbors in vector space without being logically connected.

× Issue 02

No multi-hop reasoning

Questions like "which of our suppliers source from sanctioned regions?" require following relationships across multiple entities. Chunked text can't traverse that.

× Issue 03

No schema, no audit trail

Every document is just text. There is no way to enforce types, validate facts, or trace where a claim originated. Hallucinations slip through unnoticed.

× Issue 04

Unknown unknowns

You can't ask the system what it doesn't cover. The boundaries of the knowledge base are invisible.

These aren't edge cases — they're the questions enterprises actually need to ask.

02 · Why knowledge graphs

Structure changes what AI can do.

Knowledge graphs solve these problems by giving information a shape. Instead of treating the world as a pile of text, a knowledge graph represents it as entities (companies, people, products), relationships between them (owns, supplies, employs), and an ontology — the schema that defines what types of things and connections are allowed.

This structure unlocks everything retrieval can't:

→ Capability 01

Multi-hop traversal

Walk relationships across the graph to answer compound questions that span multiple entities and types.

→ Capability 02

Type safety

Data conforms to a schema; queries return validated facts, not pattern-matched guesses.

→ Capability 03

Provenance

Every entity and relationship can carry a source — you always know where a claim came from.

→ Capability 04

Visible boundaries

The ontology is a map of what the system can and cannot represent — no more invisible knowledge gaps.

But traditional knowledge graphs come with their own pain. They demand an upfront schema. New concepts that weren't anticipated either get force-fit into wrong categories or quietly discarded. Maintaining them is slow, manual, and expensive.

For most teams, the trade-off has historically looked like this: structure or scale, pick one.

03 · Amicus KG

Amicus Knowledge Graph

A knowledge graph that evolves with your data.

Amicus Knowledge Graph is built around a different premise: the schema itself should grow.

Rather than treating the ontology as a fixed artifact designed once and never touched, we treat it as a living structure that adapts as new data arrives. When the graph encounters a concept it can't represent — a new kind of organization, a new relationship type, an attribute it has never seen — the system doesn't ignore it. It generates a structured proposal: here is what I think we should add, why, and what data would populate it.

Humans review those proposals. Approved changes are applied to the schema atomically. Pending data waiting for the change is reprocessed automatically. The graph grows, but it never grows out of control.

This approach — proposal generation by AI, decision-making by humans — is the foundation. We call it ontology in the loop.

04 · Core principles

Five ideas behind the design.

01

Ontology in the Loop

AI scans data and detects gaps in the schema. For each gap, it generates a structured proposal — what to add, why, and which data would benefit. Humans approve, reject, or modify. The schema only changes when a person says yes.

02

Domain-based slicing

Production ontologies grow large — too large to fit into a single AI prompt. We organize the schema into semantic domains (Ownership, Supply Chain, Partnership, etc.) and route each task to only the slice that's relevant. The AI sees less, reasons better, and costs drop alongside.

03

Structured proposals

A proposal isn't a sentence; it's a package. Schema changes, data to enrich the graph once approved, the source document, a confidence score, and a reasoning trail — all in one record. Reviewers see everything they need to decide.

04

Embedding-based validation

Before a proposal reaches a human, the system checks whether something semantically similar already exists. COOPERATES_WITH and PARTNERS_WITH shouldn't be two separate types. Vector similarity catches the duplication before it pollutes the schema.

05

Provenance & auditability

Production data is separated from pending proposals. Approved facts carry their source. Every schema change has a record of who proposed it, who approved it, and what data justified it. The graph is always inspectable, always reversible.

05 · Built on our research

Read the framework in full.

Amicus Knowledge Graph is the product of our published research — Ontology in the Loop: A Framework for AI-Assisted Knowledge Graph Evolution. The paper covers the full architecture, gap detection, proposal lifecycle, and human-in-the-loop workflow in technical detail.

Get in touch

See how Amicus KG fits your data stack.