# AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlack

## Executive summary

The talk argues that in AI-native organizations, organizational know-how resides primarily within 'skills.' While skills offer deterministic outcomes for complex workflows, ungoverned skills quickly accumulate as a form of technical debt due to duplication and quality decay. To scale effectively, organizations must adopt governance principles—borrowing from the microservices era—by implementing a centralized skills platform that provides metadata, search, versioning, access control, and clear ownership.

## Key takeaways

- Skills are the core of organizational know-how: The agentic software stack relies heavily on 'skills' (the deterministic component) within its outer workflow loop. If skills are unstructured, the resulting workflow is not truly deterministic.
- Governance prevents technical debt: Without governance, teams repeatedly build similar skills (duplication), quality degrades because skills aren't retested against new models, and ownership is unclear. This creates a new class of technical debt.
- A centralized platform is mandatory for scale: Scaling requires a central skills catalog with metadata, dependency mapping, versioning (to pull the current release), access control, and named human owners across architecture, infrastructure, and security.

## Technical details

- Agentic Software Stack Architecture: The stack has two loops: the inner loop (code/agents harness) includes components like context manager, tools, MCPs, memories, states, and skills loader. The outer loop (workflows) utilizes skills, sub-agents, MCP servers, and hooks. Enabling components include an environment sandbox, an MCP gateway, a model gateway (for managing LMS), a graph knowledge graph (abstracting core systems/skills registry), and a workflow marketplace.
- Skill Design Principles: Skills must adhere to microservices design principles: they need to be reusable, modular, discoverable (portable across different harnesses/workflows), specialized (defining one specific task), and composable. Consistency and deterministic outcomes are key.
- Workflow Lifecycle Complexity: The end-to-end product lifecycle is far more complex than the simple 'Specify -> Plan -> Task -> Implement' model. It includes defining product strategy, market research, competitive analysis, discovery (problem statements/user stories), data preparation/cataloging, platform engineering ops, and continuous optimization.

## Practical implications

- Implement a structured skills catalog that serves as the single source of truth for all organizational know-how.
- Treat skill development like microservices: enforce modularity, versioning, and clear ownership to ensure composability and maintain quality.
- Establish governance policies (involving architects, engineering leads, etc.) to manage access control and validate skills against regulatory standards (e.g., GDPR) before deployment.
- Focus on building workflows that leverage specialized, composable skills rather than relying solely on general-purpose agents.

## Topics

AI Agents, Skills Governance, Microservices Architecture, Technical Debt, Workflow Automation, DevOps/Platform Engineering, Skills Registry, MCP Gateway

Source: https://www.youtube.com/watch?v=M05vON8i0aI