liveBook · Manning

Cognitive axis

As explained in Designing AI Agents

A dimension of the book's design framework that organizes agent cognitive functions.

The cognitive axis organizes agent functions within a shared coordinate system for system design. Its functions draw on established models, while their arrangement alongside other design dimensions is an organizing proposal. section 2.3.4

The axis extends a familiar sequence:

  • Perception → Memory → Reasoning → Action, extended with Reflection, Collaboration, and Governance. section 2.3.4
  • The map does not include autonomy, trust boundaries, failure modes, cost, latency, or data sensitivity; suitability also depends on workload, budgets, and uncertainty. section 2.3.4

How Designing AI Agents covers it

How deep it goes
Extends the perception–memory–reasoning–action sequence with reflection, collaboration, and governance, while leaving other design constraints outside the map.
What you can do after
Evaluate agent-system designs by using cognitive-function placement as a design tool.
How it connects
Connects perception, memory, reasoning, action, reflection, collaboration, and governance to ACT-R and Belief-Desire-Intention models.

This explainer was generated by Manning's knowledge graph from the text of Designing AI Agents. The section links point to the parts of the book it draws on.