AnyQuest on Any Device

Happy New Year to all members of the AnyQuest Community!

We begin this year with a monster update, making it much easier to publish and use AI assistants and agents on AnyQuest:

  1. The AnyQuest app is now available on any device with a web browser. Open the app in the browser, save it to the home screen, and use it as any other app.
  2. Launch agents with a tap, see the list of all running jobs in the Agent Jobs view, and securely share agent output via a web link.
  3. Agents can now be saved in human-readable JSON format and copied across workspaces and accounts, which is excellent for testing, sharing, reusing, and repurposing.
  4. Agent API keys can now be generated and used to invoke AI agents via web API, turning AnyQuest into a "system of intelligence" for myriad applications and use cases.
  5. SAML is now supported as an enterprise single sign-on option, making it super easy to provide AnyQuest as a service to everyone in an organization.
  6. AnyQuest is now integrated with Groq Cloud, providing access to blazingly fast inference with Llama and Mixtral models on Groq LPUs.
  7. Any web API conforming to the OpenAPI standard can now be used as a tool by an agent: Apollo, Nasdaq, FRED, Google Search, YouTube, and many others.
  8. Numerous improvements to the core platform and the agent builder – guarded links, progressive summarization, text-to-sql, etc. – expand the realm of use cases and apps enabled by AnyQuest.

We thank our valued partners and champions for providing feedback and ideas for these updates. Keep them coming! 

Gen AI in 2025: The Year of Quantity

What can we expect from Gen AI next year? For most of 2024, the narrative has been about quality. Models are measured and compared on a range of qualitative and quantitative benchmarks. In almost every dimension, the difference in performance among frontier models is now within a tenth of a

Optimizing Business Processes with Gen AI and Use Case Crowdsourcing

Gen AI is set to revolutionize business by automating numerous steps in enterprise processes. But where should one begin? We suggest establishing a robust cycle of Ideation, Prioritization, Testing, and Analysis. Here are some typical errors and best practices for the Ideation stage.

Can GPT-4 Outsmart Wall Street Stock Pickers?

I provided a large language model with last year's market outlook reports and asked it to generate aggressive growth portfolios. Next, I backtested the portfolios against historical market data. Here are the results.