AI CAPABILITY • IMPLEMENTATION
Agents & Orchestration
One agent, infinite expertise
In 30 Seconds
The paradigm has shifted. We no longer build separate agents for each domain. We build skills – packaged expertise that one general-purpose agent can load on demand.
Skills are simple: organised folders containing instructions, scripts, and reference materials. Version them in Git. Share them across teams. Anyone – human or AI – can create them.
Why it matters: Every skill you build compounds. Enterprise knowledge becomes reusable capability – extending AI effectiveness across your organisation without rebuilding from scratch.
The Paradigm Shift
Old thinking: Build a separate agent for each domain. A finance agent, a legal agent, a research agent – each with its own scaffolding.
New thinking: One general-purpose agent runtime + a library of skills. The agent loads relevant skills on demand, gaining domain expertise instantly.
As Anthropic put it: “After we built Claude Code, we realized that Claude Code is actually a general purpose agent.”
Multi-Agent Approach
Separate agent per domain
Each needs its own tools and scaffolding
Coordination complexity grows exponentially
Hard to share learnings across agents
Skills-Based Approach
One agent + library of skills
Skills loaded at runtime when needed
Expertise compounds across the organisation
Anyone (human or AI) can create new skills
What Are Skills?
Packaged procedural knowledge that agents can load on demand.
Skills are deliberately simple: organised folders containing instructions, scripts, and reference materials. Version them in Git. Share them across teams. Anyone – human or AI – can create them.
Foundational Skills
New capabilities the agent didn't have before. Document creation, data analysis, scientific research – domain expertise packaged for reuse.
Platform Skills
Help agents work better with specific tools. Browser automation, workspace integration, API orchestration – built by platform providers.
Enterprise Skills
Organisation-specific knowledge. Internal processes, coding standards, compliance requirements – institutional knowledge made actionable.
Skills + MCP: The Complete Picture
Skills provide expertise. MCP (Model Context Protocol) provides connectivity. Together, they make agents genuinely capable.
Skills = Expertise
What: Procedural knowledge, best practices, domain expertise
How: Loaded into context when the agent decides to use them
Example: Financial reporting skill, compliance checking skill
MCP = Connectivity
What: Tools and data from external systems
How: Standardised protocol for connecting to outside world
Example: Database queries, API calls, file system access
Skills often orchestrate multiple MCP tools – they provide the “how” while MCP provides the “with what.”
The Computing Analogy
Skills are to AI what applications are to computers
Applications = Skills
Domain expertise, unique capabilities
Operating System = Agent Runtime
Context management, tool execution
Processor = Model
Intelligence, reasoning capability
A few companies build processors and operating systems. Millions build applications. Skills open this layer to everyone.
Orchestration Patterns
How skills and subagents coordinate to get work done
Chaining
Sequential handoffs
Task flows through skills in sequence. Research skill feeds analysis skill feeds reporting skill. Best for linear workflows with clear stages.
Routing
Smart direction
Classify requests and load the right skill. Customer support, technical queries, sales questions – each triggers the relevant expertise.
Parallelisation
Simultaneous work
Spawn subagents to tackle different aspects at once. Research, analysis, and drafting happen simultaneously, then results are synthesised.
Orchestrator-Workers
Dynamic delegation
The main agent breaks down tasks and spawns workers with relevant skills. Flexible – subtasks aren't predetermined, but discovered.
Evaluator-Optimizer
Iterative refinement
Generate with one skill, evaluate with another. Loop until quality threshold is met. Like a writer and editor working together.
Human + Agent Collaboration
Agents don't replace humans. They extend human capability. The question is: how much autonomy, and where does human judgment stay essential?
The Autonomy Spectrum
Human approves each step. Maximum oversight. Best for high-stakes decisions.
Agents work, human monitors. Intervention when needed. Best for routine work with exceptions.
Full automation with guardrails. Human review of outcomes. Best for well-defined, low-risk processes.
Most organisations in 2025-26 will operate “in the loop” or “on the loop”
Success depends on knowing where on this spectrum each task belongs.
Three Principles We Follow
From Anthropic's guidance on building effective agents
Simplicity
Start with the simplest solution that works. Add complexity only when it demonstrably improves outcomes.
Transparency
Show the agent's planning and reasoning. Humans should understand what's happening and why.
Tool Design
Agent-Computer Interfaces need as much care as Human-Computer Interfaces. Well-designed tools make agents reliable.
Related Capabilities
Agents and orchestration connect to other layers of the AI capability stack.
Context Engineering
Skills are powered by context. Learn how to build the knowledge architecture that feeds them.
Learn more →Strategy & Governance
Skills-based systems need governance. How to manage autonomy, risk, and accountability.
Learn more →Skills & Fluency
Building AI fluency in teams – so they can create skills and work effectively with agents.
Learn more →Expertise That Compounds
Whether you're exploring how skills could extend your AI capability, designing your organisation's knowledge architecture, or need hands-on implementation – we can help build expertise that compounds.