Welcome to the CXHACKS Blog

The Engine of Agentic AI: From Reasoning to Action

Published on May 4, 2026

Beyond retrieval: understand AI Agents that make decisions, access customer data, and take actions. Explore the reasoning-retrieval-action loop and when to use agents vs RAG for customer support and contact center applications.

RAG is Maturing: From Foundations to Production Patterns

Published on May 3, 2026

Explore advanced RAG patterns for production systems: HyDE, Corrective RAG, Agentic RAG, and Graph RAG. Learn when and how to apply each pattern to build reliable, scalable AI systems that go beyond basic retrieval.

The Secret Engine Behind Modern AI: Vector Databases Explained

Published on May 2, 2026

Understand how vector databases power Retrieval-Augmented Generation (RAG) and why they're critical for building production-grade AI systems. Learn about embeddings, chunking strategies, and why most RAG implementations fail silently in production.

When the Cloud Wobbles: BCP, Failover, and Degraded Modes in CCaaS

Published on Mar 23, 2026

A practical field guide to continuity in CCaaS. This post breaks down the difference between cloud "wobble" and full outage, explains what customers really mean when they ask about redundancy, and shows how degraded modes, recovery paths, and dependency containment make failover credible.

Build vs Buy for RAG: Making the Right Choice

Published on May 28, 2025

This post explores the trade-offs between building and buying RAG solutions, focusing on real-world considerations like speed, reliability, and long-term ownership. It examines the nuances of each approach, from the risks of building to the benefits of buying, and provides a balanced view of when each might be the right choice.

Prompt Engineering: Part 3.6 – Prompting with External Tools & Logic Systems

Published on Mar 07, 2025

Go beyond statistical prompting and bring symbolic precision into your LLM workflows. This final post in the series explores how to align model outputs with rule engines, schemas, and external logic — covering logic-aware prompting, constraint formats, symbolic scaffolding, and retrieval-based rule injection for CX, compliance, and enterprise-grade reliability.

Prompt Engineering: Part 3.5 – Structured Reasoning & Long-Horizon Thinking

Published on Mar 06, 2025

Learn how to design prompts that help LLMs think in structured, multi-stage ways. This post covers decomposition, scratchpad prompting, constraint-aware logic, and long-horizon task planning — essential for handling complex CX scenarios like compliance checks, escalations, or multi-turn support flows.

Prompt Engineering: Part 3.4 – Tools, Chains, and Automated Prompt Design

Published on Mar 03, 2025

Go beyond basic prompting with advanced techniques like Prompt Chaining, Tool Use, and APE (Automatic Prompt Engineering). Learn how to build scalable, multi-step workflows and integrate your LLM with APIs, customer data, and runtime logic.

Prompt Engineering: Part 3.3 – Agent-like Behavior

Published on Feb 29, 2025

Learn how to structure prompts that simulate intelligent agent behavior. This post explores patterns like ReAct (Reason + Act) and Reflexion — enabling your LLM to make decisions, use tools, revise outputs, and handle ambiguous queries like a true assistant.

Prompt Engineering: Part 3.2 – Prompting for Control & Reliability

Published on Feb 27, 2025

Learn how to make your LLM outputs more trustworthy, structured, and aligned with user needs. This post covers advanced techniques like Reflection, Expert Prompting, and Prompt Rails — used to reduce hallucinations, simulate expertise, and enforce safer, more consistent responses in production workflows.

Prompt Engineering: Part 3.1 – Advanced Reasoning Techniques

Published on Feb 25, 2025

Go beyond basic prompts and guide your LLM to reason like a human. This post explores techniques like Chain-of-Thought prompting, Self-Consistency, and Step-back prompting — essential for complex logic, math, and decision-making tasks.

Prompt Engineering: Part 3 – Advanced Prompting for Reasoning & Reliability

Published on Feb 21, 2025

Prompt engineering isn't just about getting the model to respond — it's about making sure it reasons effectively, answers reliably, performs complex tasks under real-world constraints, and adheres to safety and ethical guidelines. This post introduces the techniques explored in the advanced module.

Prompt Engineering: Part 2.4 – Designing Better Prompts

Published on Feb 17, 2025

The ultimate guide to crafting production-ready prompts. Explore key design principles, common pitfalls and their fixes, reusable patterns, and optimization strategies for real-world AI systems.

Prompt Engineering: Part 2.3 – Prompting Techniques

Published on Feb 15, 2025

Dive into core prompting styles like Zero-shot, Few-shot, and Chain-of-Thought (CoT) prompting. Learn when and how to apply each technique for different types of tasks, from simple classification to complex reasoning problems.

Prompt Engineering: Part 2.2 – Prompting Basics

Published on Feb 10, 2025

What goes into a good prompt? This post covers the essential building blocks — from clear instructions to structured formats — and introduces the concepts of zero-shot and few-shot prompting. Great for beginners who want to go beyond trial and error.

Cheatsheet: LLM Settings

Published on Feb 9, 2025

A practical guide to configuring large language models like GPT-4-turbo, Claude, and Gemini. Learn how temperature, top_p, max tokens, stop sequences, and more influence output behavior — with clear examples and real-world tips.

Prompt Engineering: Part 2.1 – Cheatsheet: LLM Settings

Published on Feb 9, 2025

A quick-reference guide to LLM settings like temperature, top_p, max_tokens, stop sequences, and more. Understand what each setting controls and how to tune it for better results — with plain-English explanations and real-world tips for developers.

Prompt Engineering: Part 2 – Foundations of Prompting

Published on Feb 04, 2025

This post lays the groundwork for crafting effective prompts with LLMs. We explore key ideas like prompt structure, inference settings (temperature, top_p, etc.), and how to think about clarity, context, and control when prompting. It's the foundation every builder should master before diving into advanced techniques.

Prompt Engineering: Part 1 – The Art (and Science) of Talking to Machines

Published on Feb 02, 2025

The opening post of our Prompt Engineering series sets the stage for what this discipline is all about. We explore why prompts matter, how they influence LLM behavior, and what to expect in the rest of the series.

LLM Engineering: Part 2 – Prepping Data for Your First LLM Call

Published on Jan 18, 2025

Before making your first LLM call, we need useful input. In this post, we scrape a real FAQ webpage, clean the content using BeautifulSoup, and structure the text to be LLM-ready. It's a practical walkthrough of preparing raw data for smarter AI output.

LLM Engineering: Part 1 – Minimal Setup

Published on Jan 17, 2025

Part 1 walks you through creating a lightweight but flexible development setup for LLM applications. We build a Conda environment, install key packages, configure JupyterLab, and securely manage API keys — everything you need to get started without overcomplicating it.

LLM Engineering: Part 0.5 The LLM Engineering Glossary

Published on Jan 13, 2025

This glossary-style post is your quick reference guide to common terms in LLM Engineering. From embeddings and vector stores to prompt injection and token limits, it breaks down the jargon you'll encounter while building with GenAI. Ideal for beginners or anyone grokking the space as they build — keep it open as your go-to cheat sheet while working through the series.

LLM Engineering: Part 0 – The Series Introduction

Published on Jan 10, 2025

The opening post of the LLM Engineering for Busy Builders series explains why this series exists and what to expect. We outline the key themes, upcoming topics, and set the tone: lightweight, practical, and written while learning. Think of it as a living build-log for real-world LLM systems.

The Ethical Edge: Bias, Adversarial Attacks, and Responsible AI

Published on Dec 07, 2024

The final post in our AI Foundations series. This article explores the critical ethical dimensions of AI—how bias creeps into models, the risks of adversarial attacks, and why thoughtful leadership is essential to ensure AI systems are fair, secure, and trustworthy.

The AI Transformation Playbook: From Projects to an AI-First Company

Published on Dec 05, 2024

Part 3 explores how to scale beyond experiments. Learn the 5-step transformation playbook—starting with pilot projects and ending in enterprise-wide AI maturity. With real-world strategies tailored to CX and contact center teams.

Beyond the Hype: Building Real-World AI Projects

Published on Dec 03, 2024

This post walks through how to turn AI ideas into impact—by identifying high-value projects, evaluating feasibility, and executing an iterative build-deploy-monitor loop. Perfect for anyone trying to ship working AI in CX and CPaaS.

Demystifying AI: What It Is, What It Isn't, and Why It Matters

Published on Dec 01, 2024

The kickoff to our AI Foundations series. This post breaks down the key concepts behind modern AI systems — from narrow vs. general intelligence to machine learning, neural networks, and what it truly means to build an AI-driven company.

Facebook Messenger Channel Setup Guide

Published on September 27, 2024

This guide walks you through configuring Facebook Messenger as a Channel in Webex Contact Center. Covers the complete Messenger setup process, including page creation, webex connect asset creation, channel and queue setup, and workflow design. Bonus tips advanced configuration, qr codes, and more.

Email Channel Setup Guide - Gmail

Published on September 23, 2024

This guide walks you through the step-by-step process of configuring Gmail as an Email Channel in Webex Contact Center using OAuth 2.0. The setup process includes configuring your Gmail account, creating Email Assets, setting up the Entry Point, and designing the associated workflows. These steps are essential to successfully connect your support email account with the Webex Contact Center platform.

Automating Cleanup in Google Cloud Artifact Registry

Published on August 30, 2024

This guide explains how to configure automated cleanup policies in Google Cloud Artifact Registry to delete old or untagged artifacts and retain only the latest image versions. Learn how to create and apply cleanup rules using JSON policy files and `gcloud` commands to prevent storage bloat and control costs in environments using Cloud Run and Cloud Functions.

Part 6: Your Python Journey Continues (Beyond the Basics)

Published on August 04, 2024

You’ve just completed a six-part journey into Python, not through academic exercises, but by building logic and tools grounded in the real work of customer experience, automation, and systems thinking. In this post, you’ll see how you can continue your Python journey, and the various paths you can take to add value to your real-world projects.

Part 5: File Handling & Persistence

Published on July 28, 2025

Your bots shouldn’t forget. In this chapter, you’ll teach Python how to remember — by writing to and reading from files. Learn how to save escalation notes, persist customer data, and review past interactions like a real contact center system. This is how your scripts gain memory — the foundation for building smarter, stateful automation.

Part 4: Building Reusable & Resilient Scripts

Published on July 20, 2024

Elevate your Python code from simple scripts to reliable, maintainable systems. Master functions to encapsulate reusable logic (like custom bot actions!), and learn to build **resilient scripts with try-except blocks** that gracefully handle unexpected inputs, API failures, and real-world errors – critical for production-grade CX automation.

Cheatsheet: Jupyter Lab

Published on June 18, 2024

A quick-start guide to Jupyter Lab — the interactive coding notebook used in Python, data science, and machine learning. Learn how to run code, write markdown, navigate the interface, and use built-in shortcuts and magic commands — all in one place.

Cheatsheet: macOS Command Line

Published on June 17, 2024

A practical, no-fluff guide to using Terminal on macOS. Learn essential commands to navigate directories, manage files, handle hidden files, and work efficiently from the command line — all in one place.

Part 3: Smarter Decisions & Structured Data

Published on June 13, 2024

Move beyond linear scripts to build truly dynamic CX logic. This post dives into while loops for repetitive tasks, and introduces essential data structures like dictionaries for named, structured data (customer profiles!), tuples for immutable records, and sets for managing unique values. Master how to store, access, and manipulate complex data like a pro.

Part 2: Smarter Scripts, Realer Logic

Published on June 10, 2024

Level up your Python skills! This post moves beyond basics to help you build dynamic, responsive scripts. You'll master nested logic, powerful comparison and logical operators, and fundamental data structures like lists. Learn to loop through data, slice lists for specific insights, and use built-in methods to manage real-world queues and records.

GraphQL for Dummies: A Cheatsheet for Beginners

Published on June 09, 2024

This guide breaks down GraphQL using simple examples and applies it directly to Webex Contact Center's Search API. You'll learn the basics—schemas, queries, mutations—and go hands-on with real GraphQL queries in Altair. Ideal for developers integrating reporting tools or exploring GraphQL as a smarter alternative to REST.

Part 1: Hello World: Python First Step for Busy Builders

Published on June 07, 2024

Dive into Python basics with a hands-on approach. Learn fundamental concepts like print(), comments, variables, and data types, all while exploring real-world scenarios from customer experience and automation. You'll write your first Python code and understand exactly how it works.

Webex Contact Center API Primer: Why APIs Matter

Published on March 27, 2024

A practical introduction to the Webex Contact Center APIs, this post explains the key APIs that matter for developers and solution designers working with WxCC. Focused on real-world use cases like queue statistics, task queries, and agent data, the primer walks through what these APIs do, where they fit, and why they are useful. Perfect for those looking to go beyond the UI and leverage the full power of Webex CC through API-driven automation and integrations.

Pebble Scripts Cheat Sheet

Published on March 21, 2024

A handy cheat sheet for using Pebble templating syntax inside Webex Contact Center (WxCC) flows. This guide focuses on the real-world use of Pebble within the Webex CC environment — covering variables, conditionals, loops, and string manipulation. If you're building message templates, emails, or flow logic in WxCC, this is your quick reference to get things done faster without digging through documentation.

Published on March 27, 2024

Regular Expressions Cheat Sheet

Published on March 14, 2024

This post breaks down how to use Regular Expressions (Regex) effectively within Webex Contact Center scenarios, like validating phone numbers, checking email formats, or cleaning up input data. Includes common regex patterns and tips for safely applying them in WxCC flows, whether you're handling user input or matching data in your journeys.

Published on March 27, 2024