# AfterQuery

> AfterQuery is an applied research lab curating data solutions to accelerate foundation model development.

AfterQuery works with domain experts to create training data, evaluation datasets, and reinforcement-learning environments that capture how professionals reason, decide, and use software.

## Company and offerings

- [Homepage](https://www.afterquery.com/): Official overview of AfterQuery and its approach to expert-curated AI training data.
- [Products](https://www.afterquery.com/products): Rubric- and verifier-based reinforcement learning, tool-calling environments, supervised fine-tuning, computer-use environments, RLHF, code generation, deep research, multimodal data, and custom evaluations.
- [Enterprise solutions](https://www.afterquery.com/solutions): Custom datasets, vertical-specific AI consulting, agent deployment, and simulation or reinforcement-learning environments.
- [Contact](https://www.afterquery.com/contact): Contact AfterQuery about data and research partnerships.
- [Trust and safety](https://www.afterquery.com/trust): Official information for verifying AfterQuery websites, opportunities, recruiting communications, and support channels.
- [Offer verification](https://www.afterquery.com/verify-offer): Steps for verifying an AfterQuery job or contract expert opportunity and recognizing impersonation attempts.

## Research and benchmarks

- [Research and blog](https://www.afterquery.com/research): AfterQuery research, benchmark work, and technical articles.
- [Leaderboards](https://www.afterquery.com/leaderboard): AfterQuery benchmark leaderboards.
- [IDE-Bench](https://www.afterquery.com/leaderboard/ide-bench): Evaluation of AI agents on end-to-end software engineering tasks.
- [Market-Bench](https://www.afterquery.com/leaderboard/market-bench): Evaluation of language models on introductory quantitative trading.
- [App-Bench](https://www.afterquery.com/leaderboard/app-bench): Evaluation of coding agents on economically useful web-app generation.
- [FinanceArena](https://www.afterquery.com/leaderboard/finance-arena): Evaluation of assumption-based financial analysis.
- [How AfterQuery helped NVIDIA hill-climb GDPval](https://www.afterquery.com/blog/how-afterquery-helped-nvidia-hill-climb-gdpval)
- [On-policy distillation for GDPval](https://www.afterquery.com/blog/on-policy-distillation-gdpval)
- [Why DeployCo and ServiceCo are betting on the last mile](https://www.afterquery.com/blog/deployco)
- [Solving the last mile problem with The Raine Group](https://www.afterquery.com/blog/solving-the-last-mile-problem-in-partnership-with-the-raine-group)
- [Human expertise, reimagined](https://www.afterquery.com/blog/human-expertise-reimagined)
- [Expert data and model performance on tau-squared bench](https://www.afterquery.com/blog/how-afterquery-expert-data-drives-model-performance-on-t2-bench)
- [Improving Terminal-Bench 2.0 with Tinker and Harbor](https://www.afterquery.com/blog/how-we-improved-terminal-bench-2-with-tinker-and-harbor)
- [The AfterQuery thesis](https://www.afterquery.com/blog/the-afterquery-thesis)

## Educational resources

- [AI training data knowledge base](https://www.afterquery.com/knowledge)
- [Training data for machine learning](https://www.afterquery.com/knowledge/what-is-training-data-for-machine-learning)
- [What happens during model pre-training](https://www.afterquery.com/knowledge/what-happens-during-model-pre-training)
- [The role of human data in training AI models](https://www.afterquery.com/knowledge/the-role-of-human-data-in-training-ai-models)
- [Dataset curation for machine learning](https://www.afterquery.com/knowledge/dataset-curation-for-machine-learning)
- [Supervised fine-tuning](https://www.afterquery.com/knowledge/supervised-fine-tuning-sft-how-models-learn-from-demonstrations)
- [Preference training](https://www.afterquery.com/knowledge/preference-training-how-models-learn-what-humans-want)
- [Expert data as the bottleneck in AI training](https://www.afterquery.com/knowledge/expert-data-as-the-bottleneck-in-ai-training)
- [Evaluation dataset design for frontier models](https://www.afterquery.com/knowledge/evaluation-dataset-design-for-frontier-models)

## Company links

- [Careers](https://www.afterquery.com/careers)
- [LinkedIn](https://www.linkedin.com/company/afterquery)
- [X](https://x.com/afterquery)

## Canonical and policy information

- Canonical website: https://www.afterquery.com/
- Sitemap: https://www.afterquery.com/sitemap.xml
- [Privacy policy](https://www.afterquery.com/privacy)
- [Terms of service](https://www.afterquery.com/terms)