The age of AI is upon us. No one can deny the impact and importance of AI’s potential to make work more efficient, creativity more free-flowing, and ultimately make the world a very different place. But right now, there is still a big gap between AI possibilities and actuality. Lucky for us, builders are just getting started. In this blog post we delve into the intricacies and importance of tools like ChainML's Council that combine the capabilities of generative AI and bespoke applications.
To really achieve the future we must tackle the question of gaps. Recent advances in LLMs like GPT-4, Llama 2, and Claude 2 — and their identity in consumer and business-friendly applications like ChatGPT and Bing Chat — have unlocked endless new capabilities for integrating vast knowledge with reasoning, code generation, and analysis.
We’ve all had a front-row seat to tremendous opportunities to leverage LLMs and generative AI to empower knowledge workers like researchers, analysts, and product managers by building systems built for specialized tasks that use them as modular components, i.e., agents.
For example, an AI assistant for analyzing user churn can use one agent to query databases, another to clean and prepare data, a third to generate hypotheses and perform statistical analysis, and a fourth to generate visual or written insights.
However, we’ve also seen the risks of what happens when generative AI chatbots and the agents which help guide them are developed and deployed irresponsibly. These agents can hallucinate, misinterpret prompts, and respond inconsistently, leading to significant consequences for users, applications, developers, and businesses. Simplistic schemes for integrating them into applications can cause errors to compound at scale — and applications built without oversight can codify harmful biases, diminish user trust, or act without regard for common sense constraints.
We have built a solution to address this. Council is an open-source platform that allows developers to rapidly deploy customized generative AI applications using AI agents. Council integrates with a wide variety of Large Language Models (LLMs), such as GPT-4, Llama 2, and Claude 2, to unlock generative AI for business applications.
Council extends the thriving Large Language Model (LLM) ecosystem by enabling advanced control and scalable oversight for AI applications using these agents, which are designed to have limited autonomy - with the ability to act on a task within a budget and under human supervision. Users can leverage this approach to create sophisticated agents with predictable behavior, which allows automated routing among agents, comparing, evaluating, and selecting the best results for a (sub-)task.
For example, developers can build flexible, scalable, and adaptable AI applications that help with customer support-related questions, data analysis and graph generation, insight automation, financial forecasting and investment strategies, and more. Check out some more potential use cases for Council in the below chart.
Like many of you, I believe the future of AI is open-source. As builders in technology, we are responsible for empowering developers, users, and applications to operate with control, confidence, and efficiency.
Council is the culmination of a lot of hard work from our entire team. In the spirit of open-source, if you want to get more insight into what we’ve been working on, I urge you to check out some of our developer documentation (and toss us a star) on Github, and read our content blog.
Also, be sure to follow us on
And for a little more insight into what we've been up to ahead of the launch, check out our CEO
Stay tuned for more updates on the launch and thanks for reading. I hope you’ll join us as we empower AI through Council and everything else that’s yet to come.
Product Lead and Co-Founder at ChainML