An AI oral-argument trainer for litigation practice.

What it is

Argua is a practice simulator for oral argument before a federal judge. Built around curated case packets, constrained authority sets, and doctrine-specific grading criteria, it is designed for law students, moot court and mock trial teams, legal clinics, and practitioners developing courtroom argument skills.

Argua is not a freeform legal chatbot. Each simulation is structured around a defined case packet, constrained authorities, and rubric-based feedback tied to the session transcript — graded against the doctrine and record the module establishes.

How it works

The AI judge follows structured pressure flows calibrated to the module's doctrine — interrupting when argument drifts, demanding engagement with specific facts and pleadings, and escalating under the configured bench persona and difficulty level.

After the session, Argua grades the argument against a five-part rubric: doctrinal accuracy, record engagement, analytical development, procedural discipline, and responsiveness to the bench. Feedback is formative — the score reflects how the doctrine was applied and how the bench was answered, not whether the motion was granted.

What it is not

Argua is a training simulator. It is not legal advice, not legal research, and not a brief-writing tool. Nothing generated in an Argua session should be submitted in any proceeding or relied on as legal authority. Use of Argua does not create an attorney-client relationship and is not a substitute for legal counsel.

Status

Argua is currently in private beta. The beta module covers federal civil procedure — specifically, Rule 12(b)(6) motions to dismiss and the Twombly/Iqbal plausibility standard applied to antitrust conspiracy allegations under Sherman Act § 1.

Additional civil procedure modules are in development. The antitrust complaint is the vehicle for this module; Argua's broader focus is federal motion practice and civil litigation reasoning.