Humans in the loop in 2026

7 sessions

PodcastEnterprise AI Operations: The Missing PieceRani Radhakrishnan, PwC US · 41:28 · Jan 2026 · 279 views · MLOps Podcast

Pushed backThe cost of AI should not be calculated simply as replacing human workers, because review, storage, retrieval, and other operating costs must also be included.28:48

Structured Dissent Patterns for Agentic Production ReliabilityPhil Stafford, MLOps Community · 28:13 · Jan 2026 · 181 views · Agents in Production 2025

ClaimPhil Stafford says unresolved conflicts are reported as matters requiring more information, more time, or human decision-making.8:11

Stop Building AI Like Traditional SoftwareAishwarya Naresh Reganti, LevelUp Labs · 20:47 · Jan 2026 · 425 views

ClaimA customer-support system can progress from routing tickets, to suggesting resolutions for human agents, to autonomously drafting and resolving common tickets.6:46

Everything We Got Wrong About Research-Plan-ImplementDexter Horthy, HumanLayer · 26:46 · Mar 2026 · 138K views · Coding Agents Conference 2026

Pushed backDexter Horthy rejected the claim that software factories should never have humans read either the generated plan or code.24:18

2026 The Year of Agent OrchestrationZach Lloyd, Warp · 27:33 · Mar 2026 · 21K views · Coding Agents Conference 2026

ClaimZach Lloyd identifies environments, cloud hosting, visibility, human intervention, tracking, handoff, and programmability as primitives for cloud-agent systems.10:53

How to Make a Coding Agent a General Purpose AgentHarrison Chase, LangChain & Sam Partee, Arcade AI · 36:55 · Mar 2026 · 3,848 views · Coding Agents Conference 2026

ClaimLangChain is primarily concerned with abstractions and integrations, while LangGraph provides infrastructure such as durable execution, streaming, human-in-the-loop controls, and persistence.5:36

MCPs for Observability StacksDiana Todea, VictoriaMetrics · 24:28 · Aug 2026 · 101 views

ClaimThe anomaly configuration skill can suggest models and produce a draft alert configuration in YAML for human review before production use.17:17