NDC Conferences

Platform Engineering in the age of Generative AI -

Published 2026-07-07 · Duration 1:02:16

Summary

The talk argues that while Generative AI tools significantly accelerate code generation and development speed, they are not a 'silver bullet.' To harness AI effectively, organizations must first establish robust platform engineering foundations. The core focus is on implementing comprehensive 'harnessing'—a system of controls (guides and sensors) that ensure consistent behavior, mitigate security vulnerabilities, and guide agents toward high-quality outcomes. Key strategies include adopting open standards like those from the Aentic AI Foundation, utilizing Spec Driven Development (SDD), and treating the entire development environment as a codified, observable artifact.

Download summary

Key takeaways

  1. Platform Engineering's Goal: Reducing Cognitive Overload 10:40

    Platform engineering should aim to make it the 'path of least resistance' for developers by building internal mechanisms and golden paths. This reduces cognitive overload, allowing teams to focus on delivering value rather than managing complex compliance, security, or deployment processes.

  2. AI is an Amplifier, Not a Solution 20:00

    Generative AI amplifies existing engineering quality. If foundational practices (like documentation and consistent tooling) are weak, AI will amplify those weaknesses, leading to basic security failures or unreliable code.

  3. The Importance of Agentic Standards 30:00

    The Aentic AI Foundation is establishing open standards (MCP servers, agent MD files, and agent skills) to standardize how agents interact with tools. MCP servers are described as a 'USB-C for AI agents,' providing a standard protocol layer.

  4. Harness Engineering: Controlling the Agent 40:00

    A robust 'harness' is the system surrounding the LLM model. It uses two types of controls: **Feed-forward guides** (anticipating and steering behavior, e.g., Agent MD files) and **Feedback sensors** (observing after action, e.g., linters, unit tests, or an 'LLM as a judge' pattern).

Technical details

  • Platform Engineering Principles 360s

    Platform engineering is about creating internal products and mechanisms that simplify development, moving beyond the idea of a simple developer portal. It focuses on making processes (like security scanning or deployment) standardized across teams.

  • Spec Driven Development (SDD) 2000s

    This workflow uses generative AI to first build specifications for features ('what' and 'why') before generating code. The process involves distinct phases: Research $\rightarrow$ Plan $\rightarrow$ Implement $\rightarrow$ Review, ensuring that artifacts are linked and consumed sequentially.

  • AI Agent Standards 1800s

    The Aentic AI Foundation is standardizing three key components: **MCP servers** (standard protocol for agent-tool interaction), **Agent MD files** (the 'readme' defining rules and architecture for agents), and **Agent Skills** (portable folders of instructions/resources providing procedural knowledge).

  • Harnessing Mechanisms 2400s

    A comprehensive harness requires both computational controls (deterministic, fast checks like type checkers and linters) and inferential controls (LLM-based reviews or 'LLM as a judge' patterns). The goal is to make the codebase more 'harnessable,' especially in brownfield projects with technical debt.

Mentioned resources

  • GitHub Copilot (AI Coding Assistant)
  • Claude/Anthropic Models (LLM Model)
  • Aentic AI Foundation (Industry Standard Body)
  • MCP servers (Standard Protocol/API)
  • Agent MD files (Documentation Standard)
  • Agent Skills (Procedural Knowledge Package)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.