Expert Evidence Identity Chain Orchestrator for Brisbane Litigation Lawyers: Track Every Hand That Touched Your Expert’s Report

The expert’s report landed in your inbox at 4pm Friday. It’s clean, it’s well-written, and the conclusions are exactly what you need for the ART hearing on Tuesday. Then you remember: the expert mentioned in an earlier call that her research assistant runs Claude for literature reviews, and her instructing solicitor sent annotated drafts back through a generative AI editor. You now have an expert report whose drafting chain you can’t reconstruct — and the Administrative Review Tribunal’s expert evidence practice direction expects the opinion to be that of the named expert, not a downstream model. The Expert Evidence Identity Chain Orchestrator is built so you can answer the question “who actually wrote this paragraph” before the cross-examiner asks it.

The problem

The ART’s published practice directions on expert evidence require that an expert’s opinion be the expert’s own, formed on stated assumptions and within the expert’s area of expertise. That requirement was drafted for a world where the inputs to a report were a brief, the expert’s notes, and the expert’s keyboard. It now has to accommodate a workflow where a junior associate might paste a draft into a chatbot, an expert’s PA might run a “polish” pass through an LLM, and an instructing solicitor’s review tool silently rewrites a paragraph for clarity. None of those steps is necessarily improper — but if you can’t say who introduced which words, the credibility of the whole report becomes contestable.

Australian Solicitors’ Conduct Rule 19 (candour to the court) and Rule 24 (the integrity of evidence) apply to the conduct of a solicitor briefing an expert, not just to advocacy. If the report tendered under the expert’s name materially reflects AI-generated content that the expert didn’t author or adopt with understanding, you have a problem that pre-dates the hearing — and one that’s hard to remediate retroactively without a contemporaneous record.

What the Expert Evidence Identity Chain Orchestrator does

The Orchestrator produces an auditable identity chain for every artefact that contributes to an expert report: who created it, who modified it, when, on what device, and whether any AI tooling was involved at that step. The deliverable is a structured chain-of-custody record covering:

• The brief and instructions sent to the expert
• Each draft version of the report (author, timestamp, modification type)
• Any AI assistance used at each stage, declared by the contributor and logged at the point of use
• The expert’s final adoption statement linking the report back to the expert as author of opinion
• A reconciliation report flagging gaps, undeclared edits, or AI-attributed passages requiring expert re-verification

It’s a governance layer around the expert evidence workflow, not a drafting tool. It does not generate evidence and does not opine on the substance of the report.

How it works

1. Matter set-up. You register the matter, the expert, and the contributors (instructing solicitor, paralegal, expert’s research staff). Each contributor is issued an identity token tied to their role.
2. Brief and instructions logged. The brief sent to the expert is registered as the first artefact in the chain, with a cryptographic hash.
3. Draft tracking. Each draft of the report is registered as it’s exchanged. Contributors declare any AI assistance used (tool, scope, prompt summary) at the point of upload. The Orchestrator records who modified what relative to the previous version.
4. Expert adoption. Before finalisation, the expert reviews the chain, confirms the opinion is theirs, and signs the adoption record. Any AI-attributed passages are flagged for explicit expert acknowledgement or revision.
5. Reconciliation report. You receive a chain-of-custody document suitable for filing alongside the report or producing on request, identifying every hand that touched the artefact and every AI step declared.

Why this matters in Brisbane

Brisbane litigation teams running Commonwealth administrative matters — NDIS, veterans’ entitlements, migration, social security — appear before the ART under its expert evidence practice direction. The directions apply uniformly across registries, and the expectation that an expert’s opinion be genuinely the expert’s own does not soften because the report was prepared under time pressure. Queensland firms that brief interstate experts add another wrinkle: drafts move across jurisdictions, between firms, and through whatever tooling each office happens to use. Without a single record of that journey, the only person who can attest to authorship is the expert themselves — under cross-examination, on the day. The Orchestrator exists to make that conversation a document review rather than a memory test.

Sources

• Administrative Review Tribunal — Practice Directions and Other Guidance: https://www.art.gov.au/help-and-resources/professionals-and-practitioners/practice-directions-and-other-guidance
• Federal Court of Australia — Use of Generative Artificial Intelligence Practice Note (GPN-AI): https://www.fedcourt.gov.au/law-and-practice/practice-documents/practice-notes/gpn-ai
• Law Council of Australia — Australian Solicitors’ Conduct Rules: https://lawcouncil.au/policy-agenda/regulation-of-the-profession-and-ethics/australian-solicitors-conduct-rules

Exegesis capability references:

• Expert Evidence Identity Chain Orchestrator spec
• RuleCheck by Exegesis — open-source citation verifier

Join the waitlist

Join the waitlist — be the first to know when the Expert Evidence Identity Chain Orchestrator opens to Brisbane litigation teams

This is a tier-3 service shape: it sits across the expert, the instructing firm, and any contributors in between. We’re scoping early-access partners now — what we hear from waitlist members shapes how the contributor-identity model and the AI-declaration workflow get built.