CGT Square Talk

Anthony Roth & Armen Gasanyan

On CTG Square Talk we dive into educational topics and explore ways to improve business systems and processes. Our aim is to provide our audience with practical knowledge and actionable takeaways they can implement in their own projects. We hope you can learn something from our conversations.

  1. 2D AGO

    CGT Square Talk - Agentic AI Explained: Models, Costs & Security Risks | Part 2

    Part 2 of our AI series dives deeper into what’s actually powering agentic AI systems, the models behind the scenes. In this episode, the team breaks down how different models are used across AI agents, why a model strategy is critical, and how cost, performance, and reliability all play into real-world implementations. We also explore: Why using a single model isn’t scalable How fallback models prevent downtime The real cost of APIs vs subscriptions Why human-in-the-loop is still essential And a major AI-driven security breach that highlights new risks companies face Whether you're building with AI or just trying to understand how these systems actually work in production, this episode gives you a grounded, behind-the-scenes look. Stay tuned for Part 3, where we’ll walk through a live demo and share practical tips & workflows. 00:00 – Intro & Recap of Part 1   00:54 – What AI Models Actually Do (The “Brains”)   02:01 – Why Model Strategy Matters   03:30 – Cost Considerations & Token Limits   05:02 – Primary vs Fallback Models Explained   07:30 – Real Issues Switching Between Models   09:44 – Trial & Error: Choosing the Right Model   10:38 – When AI Gets It Wrong (Fake Sources Example)   11:27 – Matching Models to Tasks (Research vs Coding)   12:50 – Human-in-the-Loop: Why It’s Critical   15:07 – AI in Development: Junior vs Senior Engineers   16:47 – Where AI Fits in the SDLC   18:48 – AI as a Tool, Not a Replacement   20:32 – Strategy Before Implementation   21:06 – Real Model Stack (What They Actually Use)   23:49 – Subscription vs API Cost Breakdown   26:01 – Real Example: $100 API Cost in One Day   27:30 – Cheaper Model Alternatives (AWS, Open Models)   28:54 – The Future of AI Cost Optimization   32:54 – Enterprise vs Open Source Models   34:33 – Compute Power & Infrastructure Realities   35:59 – Why Design Matters Before Building AI   37:39 – From Experimentation to Architecture   40:20 – The “Skunkworks” Approach to AI   41:40 – Major AI Security Risks (Real Breach Case)   42:37 – How AI Can Exploit APIs   44:25 – Why This Security Threat Matters   46:55 – Is Software Security Falling Behind?   49:59 – Why Traditional Pen Testing Isn’t Enough   51:19 – AI vs Human Security Testing   52:51 – What’s Coming in Part 3 (Demo + Tips) CGT Square Talk Hosted by: Anthony Roth & Armen Gasanyan  New episodes every other Monday!

    54 min
  2. APR 14

    CGT Square Talk - Agentic AI Explained: Building Real Software with Autonomous Agents | Part 1

    AI isn’t just a buzzword anymore; it’s actively reshaping how software gets built. In this episode of CGT Square Talk, we sit down with Kenny Gibbons to break down how we used agentic AI to automate parts of the software development lifecycle and actually built a working feature in just a few hours. From security concerns and “blast radius” thinking to real-world implementation inside a regulated pharma environment, this is a candid look at what AI can (and can’t) do today. 💡 In Part 1, we cover: What agentic AI actually is (and why it matters) The risks of open-source AI tools How we set up guardrails and “mission control.” Training AI agents to understand real systems The future of AI in regulated industries 👉 In Part 2, we go deeper into scaling this approach and what it means for the future of work. 00:00 – Intro & Why AI Is Back on the Agenda 00:46 – Meet the Team & Backgrounds 02:17 – What Is Clawbot / OpenClaw? 03:10 – Armin’s Technical Background & Journey 04:32 – Why Agentic AI Is a Big Deal 06:35 – Security Risks: “Anyone Can Download This” 07:35 – Guardrails & Controlling the “Blast Radius” 10:08 – What Is Agentic AI (Explained Simply) 12:25 – Balancing Innovation vs. Control 13:43 – Setting Up the System (VPS + Security) 15:35 – Building “Mission Control” for AI Agents 19:12 – Why Architecture Matters More Than Just Spinning Up Agents 23:07 – Where AI Fits in the Software Development Lifecycle 26:20 – Hybrid Agile + Compliance (Pharma Reality) 30:03 – Deciding What Should (and Shouldn’t) Be Automated 31:48 – Training the AI Agents 34:21 – Teaching AI Compliance (CFR 21 Part 11) 36:56 – The Power of Autonomous Learning 39:09 – Will AI Change Regulation? 41:06 – The Future: AI in the FDA & Compliance 45:16 – How We Trained the Developer Agent 47:32 – Building the Full AI Workflow 49:08 – Human Checkpoints & Safeguards 51:41 – Running the First Real Test 53:07 – Building a Feature in 3 Hours 54:16 – AI Finding Its Own Bugs (and Yours) 57:25 – Risks, Hallucinations & Control 1:00:01 – Building Internal Tools with AI 1:04:18 – Will AI Replace SaaS? 1:07:24 – The Risks of Democratizing Software 1:10:05 – Final Advice: Don’t Take the Leash Off Yet CGT Square Talk Hosted by: Anthony Roth & Armen Gasanyan  New episodes every other Monday!

    1h 12m

Ratings & Reviews

5
out of 5
4 Ratings

About

On CTG Square Talk we dive into educational topics and explore ways to improve business systems and processes. Our aim is to provide our audience with practical knowledge and actionable takeaways they can implement in their own projects. We hope you can learn something from our conversations.