CGT Square Talk
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.
CGT Square Talk
CGT Square Talk - Agentic AI Explained: Models, Costs & Security Risks | Part 2
Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.
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!