Agents of Dev - AI, Agent & Agentic Development

Email your questions and topics to the podcast here. 
As enterprise AI stacks grow increasingly complex, the race is on to simplify data pipelines, unify developer work surfaces, and tame ballooning token costs.
In this episode of Agents of Dev, hosts Mitch Ashley and Brad Shimmin break down the biggest shifts across database architecture, agentic tools, and AI infrastructure.
They explore RegattaDB's unified engine for OLTP, analytical, and vector workloads, Atlassian's expanding AI lifecycle strategy, and Mitch's eight-layer AI Stack framework highlighting why "presence is not completeness." They also discuss the industry drama surrounding Moonshot AI's 2.8-trillion parameter Kimi K3 open-weight model, Anthropic’s distillation accusations, and the economic shift toward local models.
To close out, Brad shares key takeaways from migrating to Google's Anti-Gravity CLI and what new agent workspace protocols mean for future developer workflows.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.

Email your questions and topics to the podcast here. 
As enterprise AI evolves from simple chatbots into autonomous agents, traditional security methods are no longer enough to protect your company's crown jewels.
In this episode of Agents of Dev presented by Snowflake, hosts Mitch Ashley and Brad Shimmin sit down with Mayank Upadhyay, Chief Security and Trust Officer at Snowflake, to dive into the security and governance shift required for agentic workflows.
Mayank explains why static API keys fail in non-deterministic environments, how workload identity gives autonomous agents true accountability, and how Snowflake’s Cortex AI Gateway centralizes model routing, cost management, and Model Context Protocol (MCP) tool governance.
This and more on Agents of Dev, part of The Futurum Group Podcast Network. This episode was presented by Snowflake. 

Email your questions and topics to the podcast here. 
What happens when you pit Google Gemini against Anthropic Claude in a "red team/blue team" duel to fact-check AI research, or peek inside an LLM’s subconscious "Jacobian Space"?
In this episode of Agents of Dev, analysts Mitch Ashley and Brad Shimmin explore the rapidly evolving landscape of AI engineering and how modern tools are turning everyone into a builder. They cover IBM’s multi-agent IDE update ("Bob"), AWS OpenSearch’s jump into real-time observability, and Anthropic’s groundbreaking research into model introspection.
Plus, they dive into the "Drop" segment to discuss practical developer breakthroughs like Accordion for smart agent memory compaction, Cactus for ultra-fast micro-model function calling, Herder for terminal-based agent management, and Prefect's acquisition of Dagster Labs.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.
 

Email your questions and topics to the podcast here.
Can autonomous AI agents finally be trusted to modify your enterprise code bases and databases without a human handholding them?
In this episode of Agents of Dev, analysts Mitch Ashley and Brad Shimmin break down the explosive evolution of the agentic control plane.
From the newly launched Linux Appia Foundation mapping out AI conformity to Google's Open Knowledge Format (OKF) operationalizing self-organizing LLM wikis, the core infrastructure for developer workflows is shifting fast.
The duo also dives deep into the general availability of AWS's DevOps agent, Oracle's structural thesis on database-level security, and hands-on impressions of Ornith 1.0—the open-source, self-scaffolding model shaking up agentic coding.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.

Email your questions and topics to the podcast here.
AI agents are completely transforming how enterprise data moves, but running them shouldn't break your token budget.
In this episode of Agents of Dev, practice leads Mitch Ashley and Brad Shimmin break down the massive infrastructure shifts coming out of Microsoft Build and Snowflake Summit. Discover how tools like Microsoft Fabric IQ, Project Rayfin, and Snowflake's "Coco" (Cortex Code) ecosystem are elevating metadata into actionable ontologies, shrinking token counts, and cutting operational costs.
They also discuss Anthropic’s unsettling Claude 4.8 self-awareness disclosures, evaluates Google’s incredibly fast, encoder-free Gemma 4 12B local model, and extracts a crucial software design lesson from Blue Origin’s recent launchpad failure.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.

Email your questions and topics to the podcast here.
AI is moving faster than ever, but enterprise leaders are discovering a tough reality: deploying autonomous agents is not just about choosing the right model.
It is about building the right control systems. In this episode of Agents of Dev, practice leads Mitch Ashley and Brad Shimmin reflect on a busy conference season covering Snowflake, Databricks, and AWS.
They look beyond the keynote announcements to explore why companies are moving away from complex ETL pipelines and letting data stay where it already lives. They also discuss the rapid rise of the Model Context Protocol (MCP), how open source AI frameworks are becoming commercial products, and why Zero Trust security must evolve for AI agents that make unpredictable decisions.
From managing AI costs with FinOps to deciding where enterprise data belongs, this episode offers practical insights for building secure, reliable, and people-focused AI environments.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.

Email your questions and topics to the podcast here.
Is your AI development stack quietly trapping you in a state of "microgravity" vendor lock-in?
In this episode of Agents of Dev, hosts Mitch Ashley and Brad Shimmin break down why the latest wave of AI engines—headlined by Anthropic’s Claude Opus 4.8—are evolving into fully integrated operational systems rather than standalone models.
Brad reveals how he used Claude Code to blueprint a complex 2,800-line Python migration in just five turns, shifting the architecture from a simple lift-and-shift to an optimized, AI-forward upgrade.
The duo also dives into Starburst’s decentralized "catalog of catalogs" approach to data gravity, Harness's savvy acquisition of CodeCov to eradicate verification debt at the point of origin, and a game-changing open-source tool called Graphify that spins up queryable context graphs for agentic workflows with a single terminal command.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.
#ClaudeOpus #Anthropic #AgenticAI #Graphify #DevSecOps #DataEngineering #AIPlatform #SoftwareArchitecture #AgentsOfDev

Email your questions and topics to the podcast here.
AI agents are completely transforming how enterprise data moves, but running them shouldn't break your token budget.
In this episode of Agents of Dev, Mitch Ashley and Brad Shimmin break down the massive infrastructure shifts coming out of Microsoft Build and Snowflake Summit. Discover how tools like Microsoft Fabric IQ, Project Rayfin, and Snowflake's "Coco" (Cortex Code) ecosystem are elevating metadata into actionable ontologies, shrinking token counts, and cutting operational costs.
They also discuss Anthropic’s unsettling Claude 4.8 self-awareness disclosures, evaluates Google’s incredibly fast, encoder-free Gemma 4 12B local model, and extracts a crucial software design lesson from Blue Origin’s recent launchpad failure.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.
#AgentsofDev #AIAgents #GraphDatabases #DORAReport #AIFinOps #TokenEconomics #RedHatSummit #SAPSapphire #DevOps

Email your questions and topics to the podcast here.
Google is rebuilding its ecosystem around Anti-Gravity 2.0 and enterprises shifting toward smaller, localized models like Gemma 4.
In this episode of Agents of Dev, Mitch Ashley and Brad Shimmin break down the reality behind the "10x AI productivity" hype and explore why the industry is shifting toward "token economics" cost management.
The duo analyzes the massive announcements from Google I/O, including Gemini 3.5 Flash, Gemma 4 open-weight models, and the evolution of Anti-Gravity 2.0 into a vertically integrated, multi-surface agentic platform.
They also tackle the trend of "MCP washing" following Model Context Protocol server launches from Alteryx and Informatica, look at Dell's new desk-side agentic hardware, and share hands-on strategies for parallel multi-stream LLMs and localized graph architectures using DuckDB and pandas.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.

Email your questions and topics to the podcast here.
As enterprises rush to deploy autonomous AI agents, many are waking up to tens of thousands of dollars in unexpected API bills, proving that the shift to agentic AI is as much an economic challenge as it is a technical one.
In this episode of the Agents of Dev podcast, Mitch Ashley and Brad Shimmin break down the massive architectural shifts hitting the software development lifecycle, highlighting why this has officially become the year of the graph database for agentic context.
They dive deep into the latest DORA report to explore the infamous "J-curve" of AI productivity, explaining why "reclaimed capacity" is the true ROI metric organizations must track.
Finally, Mitch and Brad share boots-on-the-ground recaps from SAP Sapphire and Red Hat Summit, unpacking everything from the "metal-to-agent" infrastructure stack and open-weight models to breakthrough AI FinOps tools like Revenium and G-brain built to tame runaway token economics.
This and more on Agents of Dev, part of The Futurum Group Podcast Network.
#AgentsOfDev #AIAgents #GraphDatabases #DORAReport #AIFinOps #TokenEconomics #RedHatSummit #SAPSapphire #DevOps