decagondev

Action Item Progress Meeting Notes

Background Progress

• Analyzed and documented the agent code and its flow
• Examined the utility profit API
• Developed hypothetical flow for data acquisition
• Executed various curl requests to test endpoints
• Created automation script for initial flow
• Combined actual data with mocked data to produce sample JSON in required format

decagondev

Dev Process - FE/FBase

1. Login to Firebase Console
2. Create New App
   • Include Analytics
   • Add Auth
   • Add Firestore
   • Add Storage
3. Use my Tailwind 4.0 Template

• either the Vanilla or CI/CD

decagondev

🧠 Fine-Tuning vs RAG: When to Use Each

Overview

Choosing between RAG (Retrieval-Augmented Generation) and fine-tuning depends on your use case, data type, infrastructure, and latency/accuracy needs. This guide helps you understand when to use each technique.

---

🧠 When to Use Fine-Tuning

You change the model itself.

decagondev

🚀 Real-World Applications of RAG vs Fine-Tuning

This document outlines practical applications where either Retrieval-Augmented Generation (RAG), fine-tuning, or both are best suited. It also includes a rough cost breakdown to help with planning.

---

1. Customer Support Chatbots

🔹 Technique: RAG + Optional Fine-Tuning

• Why RAG: Fetch live policy, FAQ, or documentation.

decagondev

🧠 MODEL_INTELLIGENCE.md

How 'Dumb' is Too Dumb? Understanding Model Limits in Fine-Tuning

Fine-tuning can work wonders — but only within the bounds of a model's inherent intelligence. This guide explores when a model is too small to meet your task’s quality requirements and how to tell if you've hit that limit.

---

1. The Ceiling of Small Models

decagondev

📊 LANGSMITH.md

Overview

LangSmith (by LangChain) and LangFuse are powerful observability and analytics tools for LLM workflows. You can use them to track, analyze, and improve model performance — and even synthesize better training data using real user interactions.

This guide covers:

• How to connect LangSmith or LangFuse
• How to log successful Q&A pairs
• How to use logged data for fine-tuning or RAG
• Sample integration script

decagondev

🧹 DATA-SANITIZATION

Overview

Cleaning and validating your fine-tuning dataset is one of the most important steps to ensure effective model training. Poorly formatted or inconsistent data leads to degraded model quality, wasted GPU hours, and hard-to-debug behaviors.

This doc covers:

• Common formatting pitfalls
• Best practices
• A sample validation script

decagondev

🎯 EDGE-CASES.md

Should You Include Edge Cases Early in Fine-Tuning?

This doc helps you decide when and how to include edge cases or rare patterns in your fine-tuning dataset.

---

✅ Start With Consistency

decagondev

GUARDING

Security, Stability, and Guardrails for Autonomous Agent Behavior Target Use Case: Travel Agency Chatbot Agent

---

🧱 1. Input Validation & Sanitization

• Validate all user inputs before processing.

decagondev

PROBLEM 1: Longest Substring Without Repeating Characters

Problem Statement

Given a string s, find the length of the longest substring without repeating characters.

Concepts Covered

• Sliding Window
• Hashing
• Two Pointers