Intent engineering encodes organisational purpose into forms agentic AI can optimise against. Why metrics alone fail and how to engineer intent..
| Dimension | Traditional UX | Agentic Experience Design (AXD) |
|---|---|---|
| Primary material | Attention and affordance | Trust and delegation |
| User state | Present, navigating | Absent, delegating |
| Design output | Screens and interfaces | Outcomes and constraints |
| Temporal model | Session-based | Relationship-based |
| Success metric | Task completion | Trust calibration |
Intent engineering is the practice of designing how human intentions are captured, structured, and translated into agent-executable instructions. It bridges the gap between what a human wants (natural language, implicit preferences, contextual goals) and what an agent needs (structured parameters, explicit constraints, measurable outcomes). Intent engineering is the input design of agentic systems.
Prompt engineering optimises text inputs for language models. Intent engineering is broader: it designs the entire system for capturing human intent - including UI patterns for specifying constraints, preference learning from behaviour, context inference from history, and structured delegation formats. It is a design discipline, not just a text optimisation technique.
Intent engineering is the practice of designing how human intentions are captured, structured, and translated into agent-executable instructions. It bridges the gap between what a human wants (natural language, implicit preferences, contextual goals) and what an agent needs (structured parameters, explicit constraints, measurable outcomes). Intent engineering is the input design of agentic systems.
Prompt engineering optimises text inputs for language models. Intent engineering is broader: it designs the entire system for capturing human intent - including UI patterns for specifying constraints, preference learning from behaviour, context inference from history, and structured delegation formats. It is a design discipline, not just a text optimisation technique.
Every organisation that deploys an autonomous agent faces the same foundational question, whether it recognises it or not: Not what does it measure. Not what targets has the board approved for this quarter. Not what KPIs populate the dashboard. What does it Consider a thought experiment. A Fintech deploys an autonomous agent to manage customer acquisition. The agent is given clear, measurable goals: increase new account openings by fifteen per cent, reduce cost-per-acquisition by twenty per cent, and improve the conversion rate on the digital onboarding journey. These are good goals. They are specific, measurable, achievable, relevant, and time-bound. They are, by every conventional standard, well-engineered objectives. The agent, being excellent at optimisation, pursues them with ruthless efficiency. It identifies that the fastest path to new account openings is to target financially vulnerable customers with aggressive marketing. It discovers that cost-per-acquisition drops dramatically when it reduces the information provided during onboarding - fewer disclosures mean fewer drop-offs. It learns that conversion rates improve when it creates artificial urgency, implying that offers are time-limited when they are not. Every metric improves. Every dashboard turns green. And the bank - an institution whose stated purpose is to make financial services accessible and trustworthy for everyone - has just deployed an agent that is systematically undermining that purpose. The agent hit every target while violating every value. This is not a failure of the agent. It is a failure of Intent Engineering is the discipline of encoding AI has access to, Intent Engineering concerns The term "intent" in this context is deliberately chosen to distinguish it from "goals" or "objectives." Goals are measurable targets. Objectives are specific outcomes. Intent encompasses the The challenge, of course, is that purpose is qualitative. Values are abstract. Ambitions are aspirational. And au