Machine Learning into Production podcast, interview style
Episodes
19 Jun 2026
The text examines "Harness" componentsprompts, tools, and feedback systemsthat balance AI agent autonomy with control through adaptive strategies, human oversight, and iterative testing to improve reliability and alignment with human judgment in dynamic tasks.
Open episode16 Jun 2026
Gateways as proxies for AI via MCP address security, traffic control, and cost management while tackling server development challenges, optimization of tool calls, microservices scaling, protocol tracing limitations, ownership shifts, and the need for unbiased evaluations and agent-driven usability assessments.
Open episode
12 Jun 2026
Recommended: Multiplayer Bots as a Action Paradigm
The integration of AI into work practices shifts toward collaborative "multiplayer" systems using flocking-inspired dynamics, addressing challenges like limited AI time horizons, technical tools for shared collaboration, balancing human-AI roles, infrastructure scaling, and the need for adaptive governance and futureproofing.
Open episode
9 Jun 2026
AI agent infrastructure and governance require control planes for security, compliance, and risk mitigation, addressing operational challenges, productivity gains, and the need for standardized frameworks, modular designs, and transparent collaboration.
Open episode5 Jun 2026
iFood Pago leverages AI-driven tools like ChatBank to automate financial services for Brazilian restaurants, balancing automation with personalization while addressing challenges in scaling AI, risk management, and the impact of declining training costs on software accessibility.
Open episode2 Jun 2026
The text explores using genetic Pareto principles for parallel agent optimization and introduces Sazabi, an AI-native observability platform that replaces traditional telemetry with log-based analysis, natural language queries, and AI-driven alerts, emphasizing log-centric simplicity and secure, dynamic agent testing.
Open episode
29 May 2026
AI reshapes software engineering by shifting to AI-integrated workflows, demanding balance between efficiency and productivity, maintaining code quality, mastering new tools like RocketRide, ensuring observability, and managing integration complexities across models and pipelines.
Open episode28 May 2026
Modern AI architecture, infrastructure challenges, open-source vs. proprietary models, and safety-critical conversational agents for mental health via Bell and Kids Help Phone's hackathon, alongside GPU efficiency, scalable frameworks, and balancing innovation with control in deployment.
Open episode28 May 2026
The MLOps community is forming the Agentic AI Foundation under the Linux Foundation to govern open-source projects like MCP and agents.md, maintain existing community activities, launch an ambassador program, and rebrand the podcast as "Agentic Conversations."
Open episode26 May 2026
Just Eat Takeaway evolves through AI-driven innovation, voice interfaces, and wearables, focusing on agentic commerce agents, super apps, and no-app models while addressing privacy, device continuity, and logistics challenges like autonomous delivery.
Open episode