| Hi folks! I'm Dimitrios Konstantinidis, and I'm really excited to share what our startup has been working on: https://l.algomo.com/9NS3ap Algomo automates online stores' customer service using AI agents. You log in, connect Algomo to your Shopify shop, run a web crawler, and all is ready to work within a few minutes. Here's a demo video: https://l.algomo.com/UKSggb We believe that most online shop owners want to spend their time doing creative stuff and market their products. Instead, a lot of time at online stores is spent on repetitive customer queries instead. Unlike generic AI agents, our AI agents specialize in customer service for online stores. Customer: "I want black shoes, size 10"
AI Agent: Pulls data from Shopify API and presents the best choices with pictures The agents run modules which include a procedural plan of attack, and execute prompts using RAG (Retrieval-Augmented Generation) to utilize the most up-to-date context to do the job, including documentation and API calls from Shopify, crawled with LangChain and stored in vector DBs. Our agents also escalate and hand-over to humans, do small talk, and potentially can perform tasks like changing a delivery address. The agents can run in our Algomo Cloud, and we plan to also run fully on-premise with self-hosted LLMs. Today, we specialize in e-commerce but we're also building sector agnostic agents that will connect and run on any API, and potentially, we plan to open up Generic Tools to enable the community to build their own modules too by calling any endpoint/API of your choosing. You can try Algomo on any small website for free. For larger websites and stores, we charge based on the number of AI conversations starting from $9/month. Please try it out and let us know what you think. We are obsessed with improving, so please let us know feedback! |
At Algomo, we believe that the potential extends even further. We see language models as the foundational 'intelligence' driving autonomous AI agents in customer service.
Autonomous AI agents?
Standard conversational language models work by taking text input and producing text output. You ask a question, and the language model responds with ‘static’ information from a knowledge base. You can think of them as a ‘conversational search engine.’
LLM-based agents, however, are a step ahead. They not only take text as input but can also interact with 'modules' such as memory, call other specialized LLMs, utilize functions (tools & APIs), and even integrate human judgement. Essentially, they can strategize and execute solutions to any presented problem. Application in Customer Service
Autonomous AI agents can literally redefine the interaction landscape between businesses and their customers. For instance, an agent can integrate into a company's CRM system, using its memory module to recall past interactions and personalize responses. It can employ specialized LLMs to handle technical queries or access APIs for real-time order tracking, or product information, ensuring customers receive accurate and timely information. Even more impressively, these agents can autonomously escalate complex issues or ask feedback from human agents, combining AI efficiency with human empathy.