The Agent Taxonomy: Shopping, Negotiation, Budget, and Discovery Agents

What is The Agent Taxonomy?

Tony Wood classifies the five primary types of commerce agent: comparison, negotiation, budget, subscription, and purchasing. Each with distinct delegation patterns and trust requirements..

What is I. The Comparison Agent?

What is II. The Negotiation Agent?

What is III. The Budget Agent?

What is IV. The Subscription Agent?

Key concepts in The Agent Taxonomy

How do the agent taxonomy relate to agentic commerce?

  1. Agency requires intentional delegation — every agentic system begins with a designed act of delegation
  2. Trust is the primary material — AXD works in trust rather than attention
  3. Absence is the primary use state — the most consequential experiences happen when no one is watching
  4. Relationships have temporality — agentic experiences accumulate history over time
  5. Outcomes replace outputs — AXD designers specify results, not interfaces
DimensionTraditional UXAgentic Experience Design (AXD)
Primary materialAttention and affordanceTrust and delegation
User statePresent, navigatingAbsent, delegating
Design outputScreens and interfacesOutcomes and constraints
Temporal modelSession-basedRelationship-based
Success metricTask completionTrust calibration

Frequently Asked Questions

What are the main types of commerce agents?

The AXD Institute identifies five primary categories of commerce agent, each defined by its function, delegation pattern, and trust requirement. The comparison agent evaluates options across merchants against a principal's criteria. The negotiation agent engages in price and terms negotiation on behalf of the principal. The budget agent manages spending within defined financial constraints. The subscription agent maintains ongoing purchasing relationships. The purchasing agent executes end-to-en

What is a comparison agent in agentic commerce?

A comparison agent evaluates products, services, or merchants across the market against criteria specified in the human principal's mandate. Unlike a human comparison shopper who browses, reads reviews, and forms subjective impressions, a comparison agent processes structured data systematically: price, specifications, availability, return policies, trust credentials, and fulfilment reliability. The comparison agent's delegation is narrow (evaluate and recommend, do not purchase) but its trust r

How does a negotiation agent work?

A negotiation agent engages in price and terms negotiation with merchants on behalf of the human principal. This is one of the most complex agent types because negotiation requires dynamic interaction, strategic reasoning, and the ability to make binding commitments within the principal's constraints. The delegation design for a negotiation agent must specify: the acceptable price range, the terms that can be conceded, the terms that are non-negotiable, and the conditions under which the agent m

What is a budget agent?

A budget agent manages the human principal's spending within defined financial constraints. It operates across multiple transactions and multiple merchants, maintaining a running total of expenditure against the principal's budget. The budget agent's delegation is financial: spend up to this amount, across these categories, within this time period. Its trust requirement is primarily internal - it must accurately track spending and enforce constraints - but it also requires trust in merchant pric

Key Takeaways

Not all agents are the same. The term "AI agent" has become a catch-all for any autonomous system that acts on behalf of a human, but this conflation obscures the critical differences between agent types - differences in function, in This essay proposes a taxonomy of commerce agents - a classification system that maps the primary agent types by their function, their delegation design, and their trust architecture requirements. The taxonomy is not exhaustive. New agent types will emerge as The delegation pattern for a comparison agent is narrow but information-intensive. The principal specifies: what to compare (product category, service type), the criteria for comparison (price, quality, delivery speed, return policy, sustainability credentials), the weighting of those criteria (price matters more than delivery speed, or vice versa), and the scope of the comparison (specific merchants, or the entire market). The agent operates within these constraints, processing structured data from merchants and returning a recommendation. The trust requirement for a comparison agent is primarily external - it must trust the data it evaluates. A comparison agent that cannot verify whether a merchant's price is current, whether the product specifications are accurate, or whether the return policy is as stated cannot fulfil its mandate. This makes the comparison agent the most sensitive to merchant data quality. Merchants with structured, verified, machine-readable product data are visible to comparison agents. Merchants with unstructured, unverified, or human-only data are invisible. The comparison agent also faces a trust challenge that is unique to its function: the risk of biased evaluation. If the comparison agent is provided by a platform that also sells advertising or preferred placement, the agent's recommendations may be influenced by commercial relationships rather than the principal's criteria. The delegation pattern for a negotiation agent is the most detailed of any age

References and Citations

Gartner: Machine Customers as Strategic Technology Trend Stanford HAI: Human-Centered AI Research NIST AI Risk Management Framework About the AXD Institute Contact Us Email the AXD Institute Tony Wood on LinkedIn Tony Wood on X (Twitter)