• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    Eon’s Era offers simulated companies for testing AI agents

    Eon describes connected records across emulated business services, with repeatable datasets and computed benchmark answers.

    EG
    EL
    RP
    4 Sources, ,

    TLDR

    Era by Eon generates connected fictional-company data across simulated business services for agent development and testing. Its documentation describes REST and Model Context Protocol interfaces, while an earlier paper explains repeatable seeded data and benchmark answers computed by code. The benchmark uses a read-only data plane. Eon recommends validating software against a team’s own staging data before deployment.

    Combined views

    21.2K

    4 Sources, first seen 2h ago

    Combined views

    21.2K

    4 Sources, first seen 2h ago

    46 likes

    Useful links

    arXiv.org

    The Era by Eon Benchmark: A Generated Enterprise Estate with Exact...

    arXiv.org

    Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge

    beri.net

    Only 3 of 36 Model Gaps Were Real. Size Your Eval Set.
    2h ago
    first seen 2h ago
    46 likes
    22 comments
    49 saves
    5 reposts
    22 comments
    49 saves
    5 reposts

    Era by Eon is drawing attention as a way to test AI agents against a connected fictional company. In an Oct. 5 post, Santiago highlighted testing across customer records, tickets, messages, files and calls, with the ability to restart from an initial state.

    Featured Source

    One company across simulated services

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Useful Links

    arXiv.org

    The Era by Eon Benchmark: A Generated Enterprise Estate with Exact...

    arXiv.org

    Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge

    beri.net

    Only 3 of 36 Model Gaps Were Real. Size Your Eval Set.
    Today's Rank

    #6

    Today's Rank

    #6

    Eon’s public repository describes an environment that emulates Salesforce, Zendesk, Slack, Jira, Gong and other services through REST APIs that emulate the vendors’ interfaces and Model Context Protocol endpoints. Users choose an industry, company size and set of applications. The same customer can appear in a sales opportunity, support ticket and recorded call.

    The Sept. 9 benchmark preprint explains how a shared seeded entity graph keeps those records consistent. Reusing the seed and configuration reproduces the company’s data, enabling repeated tests after changing an agent.

    For the benchmark’s questions, code computes answer keys from the generated records. Its evaluation data plane is read-only, so agents cannot alter the records used to grade them.

    What the environment covers

    The repository supplies onboarding instructions and examples for several agent frameworks, with environments available through a hosted console or CLI. Eon emphasizes that the data is synthetic and recommends validating against a staging system with a team’s own data before shipping software.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    6 Sources

    GitHubGitHub - eon-io/era: Build, test and benchmark agents across a complete simulated enterprise
    arxiv.orgThe Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents
    @svpinoThis is a very comprehensive way to test agents: You describe a business (any business, in one line), and this app generates a complete synthetic company and writes it across multiple systems: CRM, tickets, Slack, files, emails, call recordings, etc. You can then test your agents against all this connected data and see how they behave. If something breaks, you can reset the company to the initial state and start again.2h
    @rohanpaul_aiEnterprise agents usually get tested against mocks, narrow synthetic datasets or production, and each of those hides something different. Era by Eon tries a 4th option: you describe a company, and it generates one and writes it into Salesforce, Zendesk, Jira, Slack and Gong behind vendor-compatible MCP and REST interfaces. Because Era wrote every record, code computes each question's exact answer without a language model, so grading needs no human or model judge. Developers can then reset the company, swap a model or prompt, and rerun identical tasks to measure whether post-training on earlier failures helped.1h
    @omarsar0Pay attention to this if you are building with agents. Simulated companies are a big deal for improving agentic products. This is because good agent evals need environments that behave like real companies. Era by Eon can generate a complete company across Salesforce, Zendesk, Slack, Jira, and other systems. Each system behaves like the real vendor, down to rate limits, pagination, and error codes. You can reset the company and rerun the same tasks after changing the model or the prompt.58m
    @eladgil👀37m

    Useful Links

    arXiv.org

    The Era by Eon Benchmark: A Generated Enterprise Estate with Exact...

    arXiv.org

    Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge

    beri.net

    Only 3 of 36 Model Gaps Were Real. Size Your Eval Set.

    6 Sources

    GitHubGitHub - eon-io/era: Build, test and benchmark agents across a complete simulated enterprise
    arxiv.orgThe Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents
    @svpinoThis is a very comprehensive way to test agents: You describe a business (any business, in one line), and this app generates a complete synthetic company and writes it across multiple systems: CRM, tickets, Slack, files, emails, call recordings, etc. You can then test your agents against all this connected data and see how they behave. If something breaks, you can reset the company to the initial state and start again.2h
    @rohanpaul_aiEnterprise agents usually get tested against mocks, narrow synthetic datasets or production, and each of those hides something different. Era by Eon tries a 4th option: you describe a company, and it generates one and writes it into Salesforce, Zendesk, Jira, Slack and Gong behind vendor-compatible MCP and REST interfaces. Because Era wrote every record, code computes each question's exact answer without a language model, so grading needs no human or model judge. Developers can then reset the company, swap a model or prompt, and rerun identical tasks to measure whether post-training on earlier failures helped.1h
    @omarsar0Pay attention to this if you are building with agents. Simulated companies are a big deal for improving agentic products. This is because good agent evals need environments that behave like real companies. Era by Eon can generate a complete company across Salesforce, Zendesk, Slack, Jira, and other systems. Each system behaves like the real vendor, down to rate limits, pagination, and error codes. You can reset the company and rerun the same tasks after changing the model or the prompt.58m
    @eladgil👀37m