Developer customers, AI skills, and durable product judgment with Ben Ilegbodu

Key takeaways

Internal tools are a form of product engineering and should be treated with similar discipline, focusing on delivering value to developer users.
Durable skills such as decision making, system thinking, spec writing, and verification will outlast specific tools or AI capabilities and are essential for future-proofing engineering work.
Building effective agentic workflows requires closing feedback loops, creating reusable skills from repetitive prompts, and continuously refining processes based on real-world usage.
Measuring success in internal tooling and AI enablement involves observability, usage metrics, and observing the silence—recognizing when tools are working smoothly without direct feedback.
AI adoption challenges include managing workflow churn, providing proper training, and building infrastructure to connect different phases of development seamlessly.

Summary

The Evolution of AI Enablement in Developer Workflows

Ben Ilegbodu discusses his transition from React development to focusing on AI enablement at Netflix, mainly on building tools that enhance developer productivity. Emphasis is placed on training engineers to adopt agentic workflows and insulate teams from rapid technological changes. They explore the significance of providing the right context, data access, and infrastructure to maximize AI’s utility while minimizing churn in workflows.

Internal Tools as Product Engineering

A key theme is that internal tools are essentially a form of product engineering, with the end users being other developers. Measuring success in this context becomes about observability, usage, and impact rather than direct monetary metrics. Ben advocates for viewing the development of internal tools with the same care as consumer-facing products, emphasizing the importance of good documentation, specs, and verification processes.

Challenges with AI Adoption and Optimizing Developer Workflows

Ben talks about the difficulties in AI adoption within teams, including the need to understand workflow gaps, ensure proper training, and prevent churn. He highlights the importance of building systems that support team developers by connecting tools and connecting the dots between different development phases. He also shares real-world scenarios at Netflix, such as closing the agent loop for TV UI development, and how understanding and improving agent workflows can significantly boost productivity.

Durable Skills for the Future of Development with AI

Ben emphasizes that certain core skills—like deciding what to build, writing detailed specifications, verification, and systems thinking—are durable and will remain relevant even as AI agents grow more capable. He points out that the essence of good engineering is decision making and system design, which AI cannot replace. The conversation underscores that these foundational skills will be critical in future development beyond coding tasks.

Agent Workflows, Feedback, and Continuous Improvement

The episode delves into how developers can improve agent performance by turning repetitive prompts and workflows into reusable skills, a process that accelerates development. Feedback mechanisms like retrospective commands help identify gaps and refine pipeline processes. The conversation advocates for building systems that support ongoing, incremental learning and system improvements driven by real usage insights.

Show notes

If you build internal tools, AI enablement, or platform work, this episode is for you. Kent talks with Ben Ilegbodu about treating developers as customers, measuring success without a checkout funnel, and the durable skills that still matter when agents write more of the code.

They cover agentic workflows and skills at Netflix, closing the agent loop for TV UI development, verification and harness engineering, and why deciding what to build beats shipping three times more features.

(00:00) - Meet Ben Ilegbodu
(01:06) - From React speaking to Netflix AI enablement
(02:56) - Training engineers for agentic workflows
(04:17) - Skills, context, and insulating teams from churn
(08:41) - Product engineering for internal tools
(10:06) - How to measure success without a checkout funnel
(12:07) - Closing the agent loop for TV UI
(18:34) - Durable skills: what to build, specs, verification
(23:45) - Harness builders and agent experience
(26:33) - Agent-to-agent PR review
(28:21) - Intent docs and harness engineering
(29:36) - Do users want 3x more features?
(32:00) - Retrospective skills that improve the system
(36:56) - AI is here to stay
(39:11) - Homework: turn repeated prompts into skills

Ben Ilegbodu has spent years helping other engineers move faster - first through React education and UI tooling, and now on Netflix's TV UI productivity team focused on AI enablement. In this conversation, he and Kent talk about what product engineering looks like when your customers are other developers, not the people paying for Netflix.

A major theme is that internal tooling still needs product judgment. Ben argues the product is what you deliver to developers, and that feedback can be even more direct than consumer product work because your users Slack you when something breaks. Measuring success means observability, usage, and silence that is not always golden. On the AI side, they dig into skills as reusable context for agents, the hard problem of closing agent loops for TV apps that are not web browsers, and why durable skills like deciding what to build, writing specs, and verification will outlast any particular harness.

They also talk about agent-to-agent workflows, retrospective skills that improve the system from real usage, and the temptation to turn 3x throughput into 3x feature spam. Ben's homework is practical: notice the prompts and workflows you repeat while developing with an agent, and turn those into skills so you stop retyping the same guidance every session.

Homework

While you develop with an agent, notice the prompts or workflows you repeat over and over.
Turn one of those repeated instructions into a skill (or part of a larger skill) so the agent can reuse it.
Run with that skill on your next task and notice what details you can stop retyping every session.

Resources

Guest: Ben Ilegbodu

Host: Kent C. Dodds

See on Epic Product Engineer