Agentic Coders

Building Enterprise AI

Technology EN ↓ 4 episodes

Building Enterprise AI is a podcast about domain-specific LLMs, fine-tuning, and deploying AI systems in the enterprise. Real experience from practitioners, architects, and technology leaders. No hype. No theory. Just the things that broke and how they fixed them.

Author

Agentic Coders

Episodes

The LLM Command Center: Running the Full Domain-LLM Lifecycle in One Place 30.06.2026 11:51

Part 1 was the why. Part 2 was the where. Part 3 is the how. Alex and Maya walk through the LLM Command Center, a single console for the entire domain-specific LLM lifecycle. Topics covered: - Recap of the series: why domain-specific LLMs (the Pluribus framing) and why hospitality - The Command Center: chat compare, pipeline, observe, data, quality, lineage, HP sweep, train, register, deploy, eval...

Cross-Platform A2A: Salesforce AgentForce + AWS Bedrock AgentCore 18.05.2026 7:50

Alex and Maya break down cross-platform agent-to-agent collaboration: the Strategy Hub on AWS Bedrock AgentCore now coordinates with a Salesforce AgentForce agent using federated identity (Cognito JWT + OAuth2). Topics covered: - Cross-platform A2A: one orchestrator, multiple platforms - Live demo: Revenue Optimizer + Guest Experience + Group Sales agents working together - AgentCore Registry: gov...

Brand Visibility Analyzer: How AI Search Engines Rank Your Brand 01.05.2026 3:59

Alex and Maya introduce the Brand Visibility Analyzer, now live on the Agentic AI Showcase. When travelers ask AI for hotel recommendations, which brands appear first? This tool scores brand visibility across five AI search engines: Perplexity, ChatGPT, Gemini, Claude, and Grok. Topics covered: - Why AI search visibility is the new battleground for brands - Live demo: dashboard, scoring, competiti...

Why Your Enterprise Needs Its Own LLM — Fine-Tuning for $15 01.02.2026 9:47

Alex and Maya break down Abhijeet Patil's hands-on account of building a domain-specific LLM for the enterprise. Why do 88% of organizations use AI but nearly two-thirds haven't scaled it? How did a focused 7-billion parameter model hit 95% accuracy with near-zero hallucinations for $15 per training run? Topics covered: - The agentic AI storm and McKinsey's 2025 findings - The Pluribus Syndrome: w...