Konze Legal AI

Aussizz Group is an Australian immigration consultancy. Konze is its dedicated AI and legal-tech product line, and Konze Legal AI is the research assistant its migration agents use to answer questions about Australian immigration law.

That law is unusually hard to research. It spans four document types - Acts, Regulations, Policy and Legal Instruments - that are updated constantly and cross-reference each other heavily. A single Regulation page carries dozens of outgoing citations on average. Answering a client question correctly rarely means finding one passage; it means following the citations from that passage to the provisions that qualify it.

This is compliance-critical work. A migration agent advising on a visa application is relying on the answer being both right and traceable.

• Retrieve across four interlinked corpora of Australian immigration law, not one flat document set.
• Follow citation chains the way a human legal researcher would, rather than returning the single most semantically similar passage.
• Return one synthesised answer with every claim traceable to its source document.
• Let the client judge model quality on their own questions rather than take a vendor's word for it.

Reckonsys paired Claude with a purpose-built legislative knowledge graph. Semantic search alone finds a relevant passage; it does not know that the passage is qualified by a provision three citations away. The graph does.

• A knowledge graph of the legislation
  21,727 legislative documents and 99,854 citation relationships modelled in Neo4j, so the structure of the law is queryable rather than implicit in the text.
• Semantic retrieval over the corpus
  114,162 embedded legislation chunks across Acts, Regulations and Legal Instruments, indexed for meaning rather than keyword match.
• Graph traversal at query time
  Retrieval starts from the semantically relevant passage, then walks the citation chain outward, gathering the provisions a researcher would have followed by hand.
• Claude synthesises across documents
  Claude 3.7 Sonnet reads the assembled chain and produces a single cited answer, rather than handing back four documents for the agent to reconcile.

Claude 3.7 Sonnet is the default model for both halves of the pipeline: query analysis, which interprets the legal question and determines what to retrieve, and response generation, which synthesises the retrieved chain into one answer with citations intact.

Claude 3.5 Sonnet and Claude 3.5 Haiku are integrated as user-selectable alternatives, so the workload can be matched to the question.

The reason Claude suits this work is the same reason the knowledge graph is necessary. A legal answer has to stay inside the retrieved provisions, attribute every claim, and decline to go further than the source supports. Synthesising across four documents that qualify one another - while keeping each claim tied to the document that supports it - is reasoning under constraint, and it is precisely where a confident but unsourced answer would be most damaging.

The platform includes a model comparison capability spanning 11 models across 4 providers, letting Aussizz evaluate Claude head-to-head against alternatives on their own real immigration questions rather than on benchmarks.

Claude 3.7 Sonnet is the default. On a compliance-critical workload, with the client able to switch models at will and compare outputs on the questions that matter to their business, that default is a verdict rather than a vendor preference.

The pipeline was validated end to end against real client-provided test question sets across six visa categories - Partner, Parent, Student, Employer-Sponsored and Tourist visas among them. Not synthetic evaluation questions: the questions Aussizz's agents actually field.

• Phase 1 · complete
  Core Claude-powered retrieval and knowledge-graph pipeline built and validated against real client test cases.
• Phase 2 · current
  Production infrastructure hardening - dedicated hosting, cost monitoring, and a legislative data-refresh cadence to keep the corpus current as the law changes.
• Phase 3 · next
  Full integration with the Aussizz client platform, replacing the demo environment's auth stub with their live login, and extending coverage into the policy domain where a further ~97,000 chunks are prepared for indexing.

Reckonsys continues as Konze's engineering partner on the programme.

Claude 3.7 Sonnet · Claude 3.5 Sonnet · Claude 3.5 Haiku · Claude API · Neo4j knowledge graph · vector embedding and semantic retrieval · citation-chain graph traversal · multi-provider model comparison across 11 models