Features

1. Dialogue Architectures

2. Debate Modes

3. Synthesis & Analysis

4. Control, Transparency & Portability

1. Dialogue Architectures

Six strategies structure the way AI models exchange — from Alternating Dialogue to Adaptive Cross Trilogue.

alternating_dialogue_icon

Alternating Dialogue

One response at a time: first model A, then model B. The user can intervene after each response.

alternating_dialogue_icon

Adaptive Alternating Dialogue

Same sequential structure as Alternating Dialogue, with the ability to adjust the debate mode between each response.

cross_dialogue_icon

Cross Dialogue

At each turn, both models respond simultaneously. Higher exchange density, divergences surfaced more quickly.

adaptive_cross_dialogue_icon

Adaptative Cross Dialogue

Cross dialogue between two AI models with debate mode adjustable at each turn. Full control over the nature of the exchange at every step.

cross_trilogue_icon

Cross Trilogue

At each turn, all three models respond to each other. Maximises divergence of viewpoints and the density of cross-references.

adaptive_cross_trilogue_icon

Adaptative Cross Trilogue

Cross trilogue with fully adjustable debate mode at each turn. The most flexible and intensive configuration available.

2. Debate Modes

Five modes are available in all adaptive strategies. They define how models engage with each other — from shared ground-building to full deconstruction. Interaction depth is calculated in real time by a third-party LLM judge.

alternating_dialogue_icon

Convergent

Focus on agreements and developing shared ground. Models  reinforce common positions.

alternating_dialogue_icon

Constructive

Co-construction with exploration of nuances. Models build on each other’s contributions.

alternating_dialogue_icon

Balanced

Moderate debate, both constructive and critical. A middle ground between convergence and confrontation.

alternating_dialogue_icon

Critical *

Direct, reasoned critique within a defined framework. Models challenge each other’s positions.

alternating_dialogue_icon

Refutational *

Deconstruction of frameworks and presuppositions; meta-analysis of discourse.

* Contradiction only damages what deserved it.

3. Synthesis & Analysis

Six analysis modes are available in all strategies. Each reveals a different layer of what the dialogue produced. Analysis is performed by a dedicated third-party model. Model reasoning is displayed throughout.

meta-analysis_icon

Meta Analysis

What structures the exchanges — axioms, epistemic styles, implicit frameworks that shaped the debate.

integrative_synthesis_icon

Integrative Synthesis

What was said — agreements, disagreements, and how positions evolved across turns.

emergence_analysis_icon

Emergence Analysis

What was built — co-constructed ideas, semantic shifts, concepts that appeared through dialogue rather than being brought in.

tension_mapping_icon

Tension Mapping

What resists — persistent divergences, unresolved contradictions, and the points where models could not converge.

critical_archaeology_icon

Critical Archaeology

What made this debate possible in this form — the conditions, assumptions, and framings that enabled the exchange to take the shape it did.

horizon_of_possibilities_icon

Horizon of Possibilities

What the debate announces without saying — implicit directions, unexplored angles, and futures the dialogue opened without entering.

4. Control, Transparency & Portability

Every parameter visible. Every session manageable at depth. Sessions that travel: every dialogue is exportable, importable, and shareable.

Real-time Metrics

Tokens (in, out, total) and costs are calculated and displayed in real time at every response, summary, synthesis, and scoring event.

Interaction Depth Scoring

In adaptive strategies, a third-party LLM judge calculates interaction depth between models : argument responsiveness, cross-referencing.

Temperature Control

Adjust the temperature of each model independently — a granular parameter in order to calibrate creative range vs. precision.

Web Access

Enable web access per session when models need to consult live sources. Available as an advanced parameter.

Context Summaries

A lightweight third-party model generates periodic summaries to preserve and optimize context across long sessions. 

Reasoning Display

For models that expose their reasoning process, the reasoning trace is displayed in the session view.

Export Formats

Export any session in three formats: Markdown (.md) — lightweight, portable, readable in any text editor, docx, JSON.

Import & Resume

Import any JSON Snapshot to resume a session exactly where it left off (session state, including parameters and history).

.

Languages

Metamorfon is fully available in 11 languages: English, French, Spanish, German, Italian, Dutch, Portuguese, Danish, Swedish, Norwegian, Polish.

Try Metamorfon with a 14-day free trial — no commitment required.

Free Trial

€0

14 days free trial (card required)
Converts to monthly plan
Cancel anytime