
Seventy percent of companies are piloting automation technologies in at least one business unit.[1] Businesses today rely on artificial intelligence (AI) and large language models (LLMs) to automate complex tasks and enhance operational efficiency across functions. Powering that automation is agentic workflows, which use AI agents to execute the work.
Agentic workflows represent a paradigm shift from traditional automated processes, enabling a new level of autonomy and intelligence in business operations across all operational verticals. These workflows can be created to be self-sufficient, able to learn from interactions and make decisions without constant human oversight. We will look at the basics of agentic workflows, how they can revolutionize your operations, reduce costs and inaccuracies, and improve customer experience. By the end, you will have a clear idea of how you can incorporate LLM-driven agentic workflows into your business processes.
At its core, an agentic workflow is a process in which an LLM acts on behalf of users to perform tasks or provide assistance. These workflows leverage a model's capabilities to act as an intelligent intermediary between users and the information or services they require, enhancing productivity, efficiency and user experience. Agentic workflows have four types of design patterns:
Input Reception: The LLM receives input from users or systems, such as text prompts, queries, commands, or requests for information or assistance.
The agent might create a step-by-step plan to execute more complex tasks like helping a customer start a return for a defective product.
The agent might further break down the task into subtasks and delegate to agents with different roles: gathering information, initializing returns and customer support.
After any step in the typical workflow, we can prompt the agent to critique its own work for correctness and efficiency, provide constructive feedback on how it can improve, and incorporate that feedback before or the next time it executes.
As the example of a typical workflow illustrated, there are varying levels of interaction and autonomy within an agentic workflow. How you build it depends on your requirements and the resources available. Workflow autonomy is categorized into several levels, each offering increasing degrees of self-sufficiency and decision-making capabilities. You can think of these levels similarly to those of self-driving vehicles as defined by SAE International,[2] where level 0 is entirely manual, and level 5 represents full autonomy:
The role of autonomy in agentic workflows is crucial for enhancing operational efficiency, reducing human intervention, and enabling the system to handle tasks that are dynamic, complex and require a high degree of intelligence.
Agentic workflows offer numerous advantages over traditional automated systems. Without the need for human intervention, organizations can process larger amounts of work more accurately and quickly with agentic workflows. In practice, however, they are likely used to augment humans in the loop, freeing them up to complete more meaningful or impactful tasks. This autonomy leads to significant efficiency gains in process speed and resource capacity. Key benefits of agentic workflows include:
Agentic workflows can also offer higher performance on tasks with smaller language models. For example, Andrew Ng, Joaquin Dominguez and John Santerre, in collaboration with Sequoia Capital, discovered that agentic workflows via GPT 3.5 can outperform non-agentic workflows with GPT 4, as depicted in Figure 1.[3]
Figure 1: Comparing Performance of Non-Agent vs. Agent LLM Applications
Additionally, Du et al. 2023 studied the impact of multiple agents in a workflow, which demonstrated that multiple agents outperform the use of single agents, as shown in Figure 2.[4] NB: MMLU in the below chart is “Measuring Massive Multitask Language Understanding,” a standard benchmark for evaluating the performance of language models, consisting of about 16,000 multiple-choice questions spanning over 50 academic subjects including mathematics, philosophy, law and medicine.
Figure 2: Performance of Single vs. Multi-Agent Workflows
The application of agentic workflows allows businesses to use smaller, cheaper and easier-to-maintain language models — lowering the cost and barrier to entry for generative AI projects.
Now that you know the fundamentals of agentic workflows leveraging LLMs, how do you implement them into your processes?
The easiest way to get started is to use an out-of-the-box package. There are many options in the market from which to choose. In our work and research, we have found that CrewAI, Microsoft’s Autogen and LangChain’s LangGraph are platforms that offer unique features and capabilities, making them suitable for different use cases and preferences. There are new providers and tools for agentic workflows constantly launching. The three we deep dive below represent a nonexhaustive list.
While agentic workflows with LLMs offer organizations significant benefits, take these considerations into account before implementing this technology in your organization:
Organizations that adopt LLM-driven agentic workflows will be well-positioned to stay ahead of the technological curve. The future of agentic workflows in LLM applications holds great promise. As we strive to create autonomous systems that augment and enable humans to dedicate more time to impactful tasks, A&MPLIFY is here to help. We are leading the way in leveraging these methods with proprietary tools and firm expertise to help you develop and implement autonomous systems throughout your enterprise. Take the next step and contact the A&MPLIFY team today.
[1] McKinsey & Company. “Your questions about automation, answered.” Survey report. July 8, 2022. https://www.mckinsey.com/capabilities/operations/our-insights/your-questions-about-automation-answered.
[2] SAE International. “SAE Levels of Driving Automation Refined for Clarity and International Audience.” SAE Blog, May 3, 2021. https://www.sae.org/blog/sae-j3016-update.
[3] Sequoia Capital. "What's next for AI agentic workflows ft. Andrew Ng of AI Fund." YouTube video, 13:18. June 22, 2023. https://www.youtube.com/watch?v=sal78ACtGTc.
[4] Qian, Yujia, Xuhui Zhou, Yixuan Su, Liang Zhou, Shuang Xu, Huan Sun, and Yiming Yang. "ChatDev: Conversational AI for Software Development." arXiv preprint arXiv:2305.14325 (2023). https://arxiv.org/pdf/2305.14325.