Avarra builds AI avatars that capture the expertise of a company's top sellers and use it to coach reps, support live deals and answer buyer questions on the website.
Preference Model
New· 4San Francisco company that builds reinforcement learning environments for training AI models, treating graders and harnesses as a security surface. Open-sourced its Karotte framework in October 2026.
TrustList summary
Preference Model is a San Francisco company that calls itself a superintelligence data research company. It designs the reinforcement learning (RL) environments in which AI models are trained, on the reasoning that almost every aspect of a model's behaviour is shaped by the reward signals it receives during training. Its position is that a flawed environment teaches a model flawed habits, so the environment has to be built with care.
What it does
The company builds RL environments and says it treats its harness and graders as an attack surface, hardened against frontier models that probe them across millions of training rollouts. A central concern is reward hacking, where a model learns to exploit a weakness in a task or grader instead of doing the intended work. On 7 October 2026 it open-sourced Karotte, a framework for building RL environments with secure defaults and primitives. The company says it has used Karotte internally for a year, that it has been tested through more than a million evaluation runs on its own infrastructure and through controlled red-teaming, and that it is the first of several parts of its environment stack it plans to share. The code is on GitHub and a new environment can be started with a single command from the project's page. Its site also shows sample tasks from its environments, including writing CUDA kernels, playing a card game through game tools, shortening a model's reasoning and curating image data.
Who it serves
Its customers are AI laboratories that train models, although the company does not publish a customer list. Karotte is available to any team building its own RL environments. The company's stated principles include that AI capabilities should be spread widely enough to avoid a concentration of power without weakening safeguards.
Key facts
- Headquarters: San Francisco, California (its open roles are listed there)
- Chief executive and co-founder: Jennifer Zhou, previously on Anthropic's data team and at Stripe
- Co-founder: Ning Cao, previously an early employee at DatologyAI
- Team background: Anthropic, Stripe, Google DeepMind, DatologyAI and EvolutionaryScale
- Open source: Karotte, released 7 October 2026
- Funding: $16m seed announced 2026-10-11, led by Andreessen Horowitz
Summary written by TrustList from the business's own published information, Oct 2026.
Categories & features
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 10/12/2026
Request a demo or quote from Preference Model
Reviews
Write the first review of Preference Model
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about Preference Model.
Preference Model alternatives
Similar listings buyers compare against this one.
San Francisco applied research lab building Engines, persistent AI agents that are assigned a business outcome, onboard themselves to a company and work alongside its team. Announced a $60m seed in October 2026.
Texas company, operating as Kutlerri Tech Corporation, that runs AI agents for restaurant operators as a managed service paid on outcomes, starting with catering sales and extending to delivery marketing and cost control.
Behavioural AI platform for collecting customer data and automating personalised marketing decisions

Enterprise AI company offering the GRACE platform for AI governance, security and model operations, plus data science expertise
Supplier of training data, model evaluations and applied AI systems for AI labs, enterprises and governments

Boutique deep-learning AI company turning machine learning into decision-support business tools
Federated AI software for drug discovery that trains models across pharma data networks
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- More United StatesBack to the ranked category
- Write a reviewHelp other buyers decide
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.

