MiroFish | AI Simulation Chat for Scenario Prediction

MiroFish is an AI simulation chat tool for scenario prediction. It turns text, PDF, MD, and TXT input into graph building, simulation, reporting, and follow-up chat through one continuous AI prediction workflow. The product is positioned as a way to predict anything while talking to it like ChatGPT, combining a text-first chat interface with an optional attachment path and a multi-agent backend that runs graph building, simulation, and reporting behind the scenes while keeping the user inside a single conversation. The workflow begins with seed material. A user can start from a plain-language question, a report, a policy draft, a market note, or a story fragment. From there, MiroFish extracts actors, relationships, pressures, and factual anchors into a knowledge graph so that agents reason from structure rather than from a single isolated answer. The next step is agent simulation, where personas interact across short-form and threaded social surfaces over multiple rounds. The system then condenses emergent behavior into a prediction report that highlights turning points, risks, confidence signals, and follow-up paths. Finally, deep interaction lets the user continue asking questions against the generated world instead of stopping at a static answer. MiroFish is text-first, meaning a user can start with a question and then decide whether supporting files are necessary without losing the speed of chat. Optional attachments include PDF, Markdown, and TXT files, which work best when they contain concrete actors, incentives, constraints, or prior context, such as a strategy memo, product FAQ, policy brief, market note, or customer research summary. Result cards drop a structured result card below each answer with a summary, a report entry point, and a follow-up path. The site lists several use cases where reaction matters more than a static answer. Campaign Test pressure-tests a launch narrative before it goes public, simulating how audience groups might amplify, resist, or reinterpret a campaign message before the first spend is committed. Pricing Reaction explores the friction behind a price increase, modeling customer sentiment, value perception, and likely objection paths across different segments before the change is announced. Policy Stress Test finds the groups, incentives, and loopholes in a policy rollout, using simulation as a tabletop exercise for controversy, coalition formation, and second-order reactions. Market Narrative watches narrative, incentives, and sentiment interact, stress-testing market stories where spreadsheets miss the feedback loop between analysts, retail attention, and public discourse.