RL Environment
RL Environments and Agents
Custom RL environments and verifier design for training and evaluating agentic models.
Surge · 100% completeCompany-reported
Enterprise
Replicas of the software that runs companies (CRMs, ERPs, ticketing systems, spreadsheets, email) wired into environments where agents complete real business workflows. The bet: the biggest economic value of agents is in enterprise back-office work, so labs need training grounds that look exactly like it.
10 companies · 11 cataloged artifacts · as of 2026-08-16
| Name | Domains | Type / catalog | Location | Team | Funding | Raising |
|---|---|---|---|---|---|---|
| Akhara Enterprise and code RL environments | Enterprise, Coding | Pure-play commercial Catalog unknown | San Francisco | 1-10 | - | Unknown |
| Applied Compute Ex-OpenAI trio applying RL to build specialist enterprise models | Enterprise, Machine Learning, Custom Environments | Pure-play commercial Catalog unknown | San Francisco | 11-25 | $80M total at $700M valuation (Oct 2025) | Yes |
| BenchFlow Open-source benchmark hub and eval infrastructure for agents | Enterprise, Browser, Coding | Pure-play commercial Catalog unknown | San Francisco | 1-10 | ~$1M (reported) | Unknown |
| Collinear Enterprise simulation, judges, and long-horizon trajectory generation | Enterprise, Long Horizon, Machine Learning, Simulation | Pure-play commercial Catalog unknown | Mountain View, Sunnyvale | 11-25 | - | Unknown |
| Halluminate Sandboxed RL environments for finance and enterprise workflows | Finance, Enterprise, Browser | Pure-play commercial Catalog unknown | San Francisco | 26-50 | - | Unknown |
| Huzzle Labs Long-horizon code, tool-use, and enterprise workflow environments | Long Horizon, Coding, Enterprise | Pure-play commercial Catalog unknown | London, Berlin, San Francisco | 26-50 | ~$6M (reported) | Unknown |
| Metaphi Code and enterprise RL environments | Coding, Enterprise | Pure-play commercial Catalog unknown | San Francisco, New York | 1-10 | - | Unknown |
| Plato High-fidelity replicas of websites and software for agent training | Browser, Enterprise, Simulation | Pure-play commercial Catalog unknown | San Francisco | 1-10 | - | Unknown |
| Rise Data Labs RL environments and tasks across multiple domains, supported by a large expert network | Computer Use, Coding, Finance, Cybersecurity, Legal, Data Labeling, Enterprise, Multi-Domain, RLHF, Custom Environments | Data + environments 3 artifacts | New York, United States | 11-25 | - | Unknown |
| Veris AI High-fidelity simulated environments to train enterprise AI agents | Enterprise, Custom Environments, Simulation | Pure-play commercial Catalog unknown | New York | 1-10 | Seed, $8.5M (Decibel and Acrew, June 2025) | Unknown |
Available environments, datasets & benchmarks
Source-backed catalog records connected to enterprise.
Custom capability
Environment Bundle
Off-The-Shelf Data Catalog
Pre-built commercial datasets and RL environments spanning coding, enterprise agents, STEM, tool use, and reasoning.
Surge · 100% completeCompany-reported
Benchmark
CoreCraft
A simulated enterprise environment where agents complete customer-support and operational tasks inside a fictional PC retailer.
Surge · 100% completeCompany-reported
Benchmark
HANDBOOK.md Agents
A long-context enterprise-agent benchmark built from unique RL environments with internal tools and external MCP servers.
Surge · 100% completeCompany-reported
Environment Bundle
Long-Horizon Knowledge-Work Tasks
Private commercial long-horizon tasks spanning multiple knowledge-work domains.
Rise Data Labs · 100% completeVendor submitted
Environment Bundle
Finance Tasks
A private commercial catalog of finance tasks for RL training and evaluation.
Rise Data Labs · 100% completeVendor submitted
RL Environment
Custom Enterprise Environments
A custom environment-development capability based on a buyer’s workflows, tools, data, and success criteria.
Rise Data Labs · 100% completeCompany-reported
Benchmark
SWE-Bench Pro - Private Dataset
The proprietary-repository subset of SWE-Bench Pro, documented publicly but not distributed as an open dataset.
Scale · 100% completeCompany-reported
Verifier
Gandalf the Grader
An open-source reactive agent-as-judge that inspects files and environment state while grading agent work.
Handshake · 100% completeConfirmed
Benchmark
BankerToolBench
A banking-workflow benchmark used to evaluate agents and verifier behavior on artifact-heavy tasks.
Handshake · 100% completeConfirmed
Benchmark
APEX
An expert-authored benchmark of economically valuable tasks in finance, consulting, law, and medicine.
Mercor · 100% completeConfirmed