AIntivirus
A character LLM, voice clone, and automated podcast pipeline moved from private corpus to published episode with minimal human touch.
Public writing, private unreleased material, reply constraints, voice synthesis, and cross-channel publishing formed one operated character system, not a standalone chatbot demo.
Role
AI product leadInteraction designNarrative strategy
Outcome
A cross-channel character product used by ~10,000 active chatbot users, supported by an automated media pipeline and a 1.2M-follower distribution surface.
The character runtime
A voice needed a corpus and operating system.
AIntivirus used public writing and private unreleased material to ground an interactive John McAfee character in a specific source record. Reply selection, constraints, interaction history, and deployment connected the model across X, Telegram, and the web. A voice clone and podcast pipeline moved from script to published audio with minimal human touch. The product reached roughly 10,000 chatbot users in front of an inherited 1.2M-follower audience, while keeping product use and distribution reach distinct.
At a glance
~10,000 active chatbot users · 1.2M-follower X audience · Script-to-publication content system
In the record
Private/public corpus boundary map · Character runtime + channel architecture · Podcast automation sequence · Source-corpus permissions ledger · Voice-synthesis publishing workflow · Interaction-history and safety constraints
Ground the character
Public work and private unreleased material formed a source corpus specific enough to produce a voice rather than an impression.
Operate the runtime
Reply logic, constraints, stored interaction history, safety, and deployment surrounded the model with continuity across channels.
Publish at multiple speeds
Live exchange, episodic voice media, and an always-on product surface let one character behave as conversation, show, and roadmap.