Intro to AI Agents ƻ EuRuKo 2024 Friday, September 13th, 2024 by Andrei Bondarev

Work Source Labs LLC Software-development firm Clients: VC-backed startups and Enterprises We <3 Rails Patterns AI Applied AI research organization Open-source work We <3 Ruby

GenAI Impact Before: 1 month Label data 3 months Train custom model 3 months Deploy (optimize) After: Few days Prompt engineering Few weeks Basic RAG (if needed) Few days Deploy

Common ML tasks Classification Named Entity Recognition Summarization Translation

Capabilities, an API call away Adoption Cost

(Re-)Rise of AI Agents 1950s 1970s — 1980s 1990s — 2000s Intelligent Machines Expert Systems 2010s Software Agents 2020s Chatbots LLMs as Agents

The Vision

AI Agent ƻ Definition: An autonomous software system capable of perceiving its environment, making decisions, and taking actions to achieve specific goals. ♻ Environment awareness 2 Decision-making Ƣ Action-taking

Agent vs Assistant Assistant Conversational system that continuously takes directions from a human Agent Autonomous system that independently executes a task (like a background job)

Agent vs Assistant Conversational Assistant Free-for-all input from user Autonomous Agent Guided-input from user

Use-cases Automating business processes Mundane low-IQ tasks Personal assistant (co-pilot) Tasks in a consulting business: Creating invoices from timesheets Categorizing business expenses Writing project proposals (incl. service offering, meeting notes) Writing job descriptions. Writing JIRA tickets.

Components of an AI agent 1. Planning & Reasoning 2. Role Playing 3. Environment Perception 4. Tool Calling 5. Memory 6. Evaluations (Evals)

Planning Plan formulation Decomposing a top-level task into numerous sub- tasks. Plan reflection Leveraging feedback mechanism to reflect upon a plan and evaluate its merits.

Reasoning Cornerstone for problem-solving, decision-making and critical analysis. Deductive, inductive, abductive are the primary forms of reasoning. Reasoning capacity is crucial for solving complex tasks.

Chain-of-Thought (CoT) Forcing the AI to explain it's reasoning. Without Chain-of-Thought prompting With Chain-of-Thought prompting

Role playing Forcing the AI to adopt certain personality, character, and behavior, via prompt engineering Ɗ Strict Manager % Relaxed Manager Dungeon Master Ƽ Helpful AI assistant

Environment perception "Today is September 13, 2024 "

Tool/Function Calling Structured Outputs Response adhere to a predefined JSON schema External Tools Intent detection

Tool Calling Use tools to do the following: Get data from external sources (APIs) Get real-time data Take actions Execute deterministic tasks1 Without Tools Using the Tool (Code Interpreter)

Tool Calling

Memory ("remembering") Saving the environment, progress, tool calling to memory

Memory => Retrieval Augmented Generation (RAG)

Common problems ♻ Hallucinations 2 Poor reasoning Ƣ Unreliable tool calling

Evaluations Benchmarks Comparing to a large dataset of question-answer pairs. "LLM as a Judge" Asking LLM whether the answer fits a list of criteria.

Benchmarks huggingface gretelai/gsm8k-synthetic-diverse-405b · Datasets at Hugging Face We ʼ re on a journey to advance and democratize artificial intelligence through open source and open science .

Reasoning (Next Frontier) Training models specifically on reasoning data but… No good training data

langchainrb ⭐ Ruby framework for building LLM-powered applications

Demo

Nerds & Threads Selling comfortable nerdy t-shirts for software engineers that work from home Services ú Customer Management ✉ Email Service Payment Gateway Service Order Management Inventory Management Shipping Service

Diagram

Code

Demo AI Assistant Chat

Why would you use this? Changing requirements on the fly Text-to-SQL using the Database tool

Recap

Thank you! ɉ @rushing_andrei @andreibondarev in/andreibondarev [email protected] Discord

References "Tool Use with Open-Source LLMs" by Rick Lamers (Groq) 1. https://arxiv.org/abs/2309.07864 2. https://www.promptingguide.ai/techniques/cot 3. https://docs.google.com/presentation/d/1EH11pXLanLMoLGEXd_YduYxEEk3X2Y63KOOFsysq1LY 4. https://www.ibm.com/think/topics/ai-agents 5. Berkeley Function-Calling Leaderboard 6. https://garymarcus.substack.com/p/math-is-hard-if-you-are-an-llm-and 7. https://obie.medium.com/my-kids-and-i-just-played-d-d-with-chatgpt4-as-the-dm-43258e72b2c6 8.

langchain.rb contributors