Improving AI Assisted Development with Minko Gechev

Improving AI Assisted Development with Minko Gechev

From Modern Web by Modern Web

June 5, 2026 · 38 min

About this episode

Rob Ocel interviews Minko Gechev about advancements in AI-assisted development and the complexities of skills and workflows.

Rob Ocel sits down with Minko Gechev to unpack one of the fastest-evolving areas in AI-assisted development: skills, agent workflows, and the growing complexity of AI harnesses.Explore AI skills, how they differ from rules and MCPs, and why developers are increasingly treating skills as structured, executable instructions rather than traditional documentation. Minko explains how modern agents operate under the hood, how skills are lazy-loaded into context windows, and why poorly designed skills can create context rot, unnecessary token usage, and degraded performance over time. Rob and Minko also dig into one of the most important but misunderstood topics in AI engineering today: evals. They break down how teams can evaluate AI workflows, measure pass rates, test deterministic versus non-deterministic outputs, and optimize skills for reliability, token efficiency, and execution quality across evolving models and harnesses. Also learn about prompt structure, workflow orchestration, context compression, state-machine agents, React loops, and why many teams are accumulating rules and skills faster than they are pruning them. What you will learn: • Learn how engineering teams are…

People in this episode

Host: Rob Ocel

Guest: Minko Gechev

Topics covered

  • AI-assisted development
  • skills
  • agent workflows
  • AI engineering
  • reliability
  • automation

Keywords

  • AI skills
  • context windows
  • evals
  • workflow orchestration
  • context compression
  • state-machine agents
  • token efficiency

Mentioned in this episode

Organizations: AI, React

More episodes of Modern Web

Explore listener stats, chart rankings, contacts and more on the Modern Web podcast page.