Cirrius TalkAgentic AI
Agentic AI
How AI agents actually get built and run in production: frameworks, context engineering, security, economics, and the operating system around the model. Practical episodes from the team building agents for real businesses.
Hosted by Greg Banks and Tim Harting
Start here
Greg’s picks if you are new to the show.
Start here · Episode 17Agents, MCPs, and Skills: The 3 Building Blocks of AI Agents Explained
What if your AI agents were architected as intentionally as your Salesforce org?
All episodes
Agentic AIClaude Duet: The AI Agent That Works While You SleepChat sessions and scheduled jobs only do what you already knew to ask for, and the things you never thought to check are the ones that cost you.
Agentic AIMCP Apps: Your AI Assistant Can Finally Show You a Screen, Not a CSVAsk an AI assistant for every sale in your region and you get a CSV, or a table the model improvised, and then you scroll and Control-F through it like a spreadsheet.
Agentic AIJev vs LLMs: Decisions in Milliseconds for 4 Cents per Million TokensEvery agentic pipeline is full of small yes-or-no and which-bucket decisions, and running each one through a large language model costs seconds and real money at scale.
Agentic AIThe Artifact Ladder: 5 Tiers From PowerPoint to Full AI-Built AppsYour team is generating more with AI than ever, and most of it still lands in a slide deck or a long email that nobody has time to read.
Agentic AIClaude vs GPT-5.6: How to Choose the Model Behind Your AI AgentsEvery agent you build runs on a large language model, and that choice quietly decides whether your AI program pays for itself or drains the budget.
Agentic AIIs Your Team’s Claude Code Setup the Wild West? Plugins Fix ThatThe moment one person on your team builds a genuinely useful agent setup in Claude Code or Claude Cowork, you hit a new problem: sharing it without it splintering into a dozen diverging copies.
Agentic AISkills vs Commands: When to Use Each in Your Agentic OSThe agentic AI race has a new leader every few months, and a platform bet that ignores that churn will cost you.
Agentic AISignal, Sort, Store: The Discipline Behind Smart AgentsYou have dreamed up a dozen things an AI agent could do for you, but the moment you open it, it feels like a stranger who has never met you.
Agentic AIAgentic OS Explained: 4 Pillars That Keep Your AI Agent SharpMost AI practitioners build an agent, use it for a few weeks, and then watch it quietly get worse.
Agentic AIAI Agent Strategy: 7 Deliverables to Lock In Before DevelopmentMost AI agent initiatives do not fail in the build.
Agentic AIAI Dev Tool Security: 4 Risks to Act On, 4 to IgnoreThe AI security conversation has two volume settings: hand over the keys, or the sky is falling.
Agentic AIClaude Code vs Wireframes: Building Interactive POCs in Hours, Not WeeksEvery consulting project carries the same hidden risk: the client doesn’t really know what they’re getting until UAT, and by then the time and money to change it are gone.
Agentic AIAgentic AI – Evolution of Agent HostingYou picked your LLM, you picked your use case, and now someone hands you a list of hosting options that all sound like they solve the same problem.
Agentic AIAgentic AI – Token Economics: Designing Agents That Don’t Blow the BudgetToken stewardship is quickly becoming a make-or-break discipline for Agentic AI because it directly impacts cost, throttling, and whether teams can scale AI usage without losing velocity.
Agentic AIBuild an Employee Agent – Skills That ScaleLocal agents can unlock real productivity, but only if you avoid the “skills wild west.” In this episode, we break down how Cirrius is rolling out a locally based employee agent and governing skills so teams get consistent, scalable results.
Agentic AIAgentic AI – Local vs Cloud-Hosted AgentsLocal AI agents vs cloud-hosted AI agents isn’t just a technical debate, it’s a productivity and security decision.
Agentic AIAgentic AI Boundaries: Multi-Tenancy Done RightMulti-tenancy in agentic AI is not the same thing as multi-user, and getting it wrong can create serious security, compliance, and data boundary risks.
Agentic AIPrompt Injection: 4 Practical Defenses for Your AI AgentsAgentic AI security is now the difference between “we shipped” and “we leaked.” In this episode, we break down the real security risks AI agents introduce, and the practical ways to mitigate them.
Agentic AIBuild Your First Custom AI Agent: A Step-by-Step WalkthroughAI conversations can feel like alphabet soup, but building a custom AI agent doesn’t have to.
Agentic AITop 3 Agentic AI Frameworks (and How to Choose Without Analysis Paralysis)Agentic AI frameworks are multiplying fast, but most teams only need a clear “when to use what” map to start building.
Agentic AIMCP Servers Deep Dive: Secure, Reusable Tools for AI AgentsAI agents are powerful, but without the right “tooling layer,” they can be risky, inconsistent, and hard to scale.
Agentic AIContext Engineering: The Secret Sauce Behind Great AI AgentsAI agents don’t fail because they’re “not smart enough”, they fail because they’re missing the right context.
Agentic AIAgentforce vs Custom Agents: The Real Cost Breakdown (With Numbers)As AI headlines accelerated through 2025, costing remains one of the hardest areas for leaders to “get grounded” on.
Agentic AIAgents, MCPs, and Skills: The 3 Building Blocks of AI Agents ExplainedWhat if your AI agents were architected as intentionally as your Salesforce org?
Agentic AIFrom Clicks to Code: How AI Is Redefining Salesforce DevelopmentIn this episode, Greg Banks and Tim Harting welcome Gavin Franklin to explore how AI is transforming the world of Salesforce development.
Agentic AIDreamforce Debrief: AI Agents, Slack Smarts, and the Changing Consulting GameIn this episode of Cirrius Talk, host Greg Banks is joined by Allie Nelson and Tim Harting.
Agentic AISalesforce × OpenAI: Agents, Slack, and the Race for ‘Data 360′In this episode of Cirrius Talk, we highlight the bombshell dropped at Dreamforce: Salesforce + OpenAI.
Agentic AIPicking Your First AI Agent: A 5-Factor Decision FrameworkIn this episode of Cirrius Talk, host Greg Banks, along with Chad Anderson and Tim Harting, delve into the significant announcements from Dreamforce.
Agentic AIAgentforce 101: When to Build an AI Agent vs Use Out-of-the-BoxIn this episode of Cirrius Talk, hosts Greg Banks, Chad Anderson, and Tim Harting explore the integration of AI within the Salesforce ecosystem, focusing on the distinctions between AI agents and Agent Force.More from Cirrius Talk
Also on Cirrius TalkSalesforce at Scale
Also on Cirrius TalkThe Military Minute