AnthrolyticAnthrolytic
ProblemHow It WorksResultsDocsAbout UsFAQ
Get Started
Resources

Research & Documentation

Explore our latest essays, technical research, and methodologies on AI-driven candidate screening and interactive soft skills evaluation.

Mission Statement

Our mission and strategic direction

An overview of Anthrolytic's mission, vision, and product direction for AI-powered candidate screening.

March 2026Read paper →

Domain-Specific Fine-Tuning of PersonaPlex-7b for Customer Persona Simulation

Our research into creating a human-like customer service experience

We fine-tuned NVIDIA's PersonaPlex-7b-v1 model on 200 synthetic coffee shop customer conversations to address hallucinations and poor task adherence in customer-facing deployments. Using LoRA training with ChatterboxTTS audio and LibriSpeech voices, we introduced a semantic-weighted loss function and voice prompt injection mechanism to improve emotional accuracy and reduce role-inversion hallucinations. LLM-as-judge evaluation shows improvements over the base model across all three tested configurations.

February 2026Read paper →

Start with VirtualShift

Ready to find your stars?

VirtualShift pre-screens candidates in 20 minutes and scores them with the VibEye algorithm. You only meet the ones worth meeting.

Get Started
AnthrolyticAnthrolytic
ContactPrivacy PolicyTerms & ConditionsCookies

ABN: 62 696 306 484  |  ACN: 696306484

© 2026 Anthrolytic. All rights reserved.