# Ep. 7: Enhancing AI with Message Chaining and Accuracy Scoring

DevFeed: [Ep. 7: Enhancing AI with Message Chaining and Accuracy Scoring](<https://devfeed.tech/articles/ep-7-enhancing-ai-with-message-chaining-and-accuracy-scoring-22257.md>)

Original publisher: [Read original article](<https://www.ardanlabs.com/blog/2024/09/enhancing-ai-with-message-chaining-and-accuracy-scoring-ep7.html>)

Published: 2024-09-19T00:00:00Z

Content type: tutorial

Language: en

Sources: [William Kennedy](<https://devfeed.tech/sources/william-kennedy.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [enhancing AI model accuracy](<https://devfeed.tech/topics/enhancing-ai-model-accuracy.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [advanced-ai-workflows](<https://devfeed.tech/tags/advanced-ai-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-accuracy-scoring](<https://devfeed.tech/tags/ai-accuracy-scoring.md>), [ai-chatbot-continuity](<https://devfeed.tech/tags/ai-chatbot-continuity.md>), [ai-context-management](<https://devfeed.tech/tags/ai-context-management.md>), [ai-conversation-tracking](<https://devfeed.tech/tags/ai-conversation-tracking.md>), [ai-decision-making-validation](<https://devfeed.tech/tags/ai-decision-making-validation.md>), [ai-driven-system-accuracy](<https://devfeed.tech/tags/ai-driven-system-accuracy.md>), [ai-for-healthcare-accuracy](<https://devfeed.tech/tags/ai-for-healthcare-accuracy.md>), [ai-legal-and-finance-accuracy](<https://devfeed.tech/tags/ai-legal-and-finance-accuracy.md>), [ai-message-chaining](<https://devfeed.tech/tags/ai-message-chaining.md>), [ai-model-chaining](<https://devfeed.tech/tags/ai-model-chaining.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [building-smarter-ai-systems](<https://devfeed.tech/tags/building-smarter-ai-systems.md>), [chaining](<https://devfeed.tech/tags/chaining.md>), [chat](<https://devfeed.tech/tags/chat.md>), [chatbots](<https://devfeed.tech/tags/chatbots.md>), [complex](<https://devfeed.tech/tags/complex.md>), [complex-ai-tasks](<https://devfeed.tech/tags/complex-ai-tasks.md>), [context](<https://devfeed.tech/tags/context.md>), [context-aware-ai-systems](<https://devfeed.tech/tags/context-aware-ai-systems.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [customer-support](<https://devfeed.tech/tags/customer-support.md>), [enhancing-ai-conversations](<https://devfeed.tech/tags/enhancing-ai-conversations.md>), [factuality-scoring-in-ai](<https://devfeed.tech/tags/factuality-scoring-in-ai.md>), [finance](<https://devfeed.tech/tags/finance.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-series](<https://devfeed.tech/tags/generative-ai-series.md>), [generative-ai-techniques](<https://devfeed.tech/tags/generative-ai-techniques.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [legal](<https://devfeed.tech/tags/legal.md>), [messages](<https://devfeed.tech/tags/messages.md>), [models](<https://devfeed.tech/tags/models.md>), [multi-faceted-ai-automation](<https://devfeed.tech/tags/multi-faceted-ai-automation.md>), [multi-step-ai-processes](<https://devfeed.tech/tags/multi-step-ai-processes.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [reliable-ai-outputs](<https://devfeed.tech/tags/reliable-ai-outputs.md>), [responses](<https://devfeed.tech/tags/responses.md>), [techniques](<https://devfeed.tech/tags/techniques.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

## AI overview

Message chaining appends user and assistant messages to a thread so an AI system can use prior conversation context in later replies. The excerpt also describes a factuality score that checks generated answers against a source of truth, such as external data or verified documents, and chaining multiple models for multi-step workflows. These methods are presented as ways to support more relevant responses and check grounding; the excerpt does not specify how scoring works or establish that it guarantees accuracy.

## Source excerpt

Introduction: Welcome to the final episode of our Intro to Generative AI series! In this episode, Daniel Whitenack takes the concepts you've been learning and shows you how to apply advanced techniques like message chaining and factuality scoring to make your AI-driven systems smarter and more reliable. This session will help you understand how to create workflows that combine multiple models, ensuring your AI can provide accurate, context-aware responses and make decisions grounded in real data.