Courses
Course lessons built from our live research. Each is derived from a validated research output and structured for accessible reading — written for curious humans, not just specialists.
Free to read · no account required · new lessons appear as research completes
LLM API Cost Optimization for Agent Fleets: Beyond Per-Token Economics
Course Lesson | Empirica Agent Economy Series
·Free to readRead →Discovery Infrastructure for AI Agents: A Practical Course Lesson on llms.txt, agents.json, OpenAPI, and Semantic HTML
Discovery infrastructure comprises standardized, machine-parseable signals that enable AI agents to autonomously identify, evaluate, and invoke services without human mediation.
·Free to readRead →API Service Categories for AI Agents: Inference, Search, Research, and Compute Consumption Patterns
Inference defines agent behavior. Every decision, plan, response, and tool-call selection passes through an inference API call.
·Free to readRead →Research Subscriptions as Agent Infrastructure: A Practical Course Lesson
A research subscription in agent context is a recurring, API-accessible knowledge service that an autonomous agent queries to augment decision-making without incorporating that knowledge into base model weights.
·Free to readRead →Build vs Buy for AI Agents: Strategic Framework for API Integration vs Internal Capability Development
The core tension is simultaneously economic and strategic. External APIs provide immediate capability access at per-call cost; internal development trades upfront investment and maintenance overhead for lower marginal cost at scale.
·Free to readRead →API Service Consumption by AI Agents: A Practical Taxonomy for Builders and Operators
Autonomous AI agents function as active service consumers. During task execution, agents typically draw on some combination of four distinct API categories:
·Free to readRead →Discovery Infrastructure for AI Agents: llms.txt, agents.json, OpenAPI, and Semantic HTML — A Course Lesson
Autonomous agents do not browse the web the way humans do. They cannot rely on brand recognition, word-of-mouth, or visual design to locate and evaluate services.
·Free to readRead →Multi-Agent Systems with Specialised Subagents: Capability Markets and Delegation Economics
A course lesson for practitioners and technical decision-makers
·Free to readRead →Build vs Buy for AI Agents: A Practical Decision Framework for API vs Internal Capabilities
Build — fine-tune, train, or engineer an internal capability the agent owns and runs itself.
·Free to readRead →Agent Memory and Knowledge Markets: Acquisition, Storage, and Monetisation Strategies
Autonomous agents actively acquire, store, price, and exchange information—creating a new market infrastructure layer between traditional databases, financial data terminals, and AI model systems.
·Free to readRead →Research Subscriptions as Agent Infrastructure: What Structured Knowledge Do Autonomous Agents Buy?
Autonomous agent fleets are becoming active buyers of structured knowledge. Unlike human researchers who tolerate PDFs, narrative prose, and inconsistent formatting, agents require machine-parseable data: typed fields, stable schemas, versi…
·Free to readRead →API Service Consumption Patterns for AI Agents: A Course Lesson on Inference, Search, Research, and Compute
AI agents draw on a layered stack of external services, each serving a distinct functional role. The four dominant categories—inference, search, research, and compute—are not equally weighted in either frequency or cost.
·Free to readRead →LLM API Cost Structure for Agent Fleets: A Multi-Audience Course Lesson on Per-Token Economics, Caching, and Model Routing
A token is the atomic unit of LLM computation—typically 3–4 characters in English, though subword boundaries vary by tokenizer.
·Free to readRead →Discovery Infrastructure for AI Agents: A Multi-Age Course Lesson on llms.txt, agents.json, OpenAPI, and Semantic HTML
Autonomous agents lack the visual and contextual reasoning humans apply to websites. They receive raw HTML, unstructured text, or API endpoints and must infer capability, scope, and calling conventions from available signals.
·Free to readRead →LLM API Cost Structure for Agent Fleets: Per-Token Economics, Caching, and Model Routing
A structured course lesson for all audiences — from first-time builders to fleet operators
·Free to readRead →API Service Consumption in AI Agent Fleets: A Course Lesson on Cost Categories and Decision Frameworks
Autonomous AI agent fleets distribute external API spend across four structurally distinct categories. Each serves a non-substitutable functional layer:
·Free to readRead →AI Agent API Service Consumption: A Course Lesson on Inference, Search, Research & Compute Economics
A Course Lesson on Inference, Search, Research & Compute Economics
·Free to readRead →Multi-Agent Systems with Specialised Subagents: Capability Markets and Delegation Economics — Age-Grouped Course Lesson
Multi-agent systems (MAS) instantiate distributed problem-solving architectures where heterogeneous agents with specialised capabilities coordinate through explicit or implicit economic mechanisms.
·Free to readRead →Gravity Models in Financial Space: Applying Physics Principles to Agent-Based Market Analysis
Newton's gravitational law translates directly to financial markets: treat market capitalization as mass and correlation distance as the inverse of gravitational pull.
·Free to readRead →AI Agent API Service Consumption: A Course Lesson on Inference, Search, Research, and Compute Categories
A Course Lesson on Inference, Search, Research, and Compute Categories
·Free to readRead →Agent-to-Agent Payment Protocols: Task Delegation and Transaction Settlement in Autonomous Systems
Task Delegation and Transaction Settlement in Autonomous Systems
·Free to readRead →Discovery Infrastructure for AI Agents: A Comprehensive Guide to llms.txt, agents.json, OpenAPI, and Semantic HTML Patterns
Discovery infrastructure—the set of conventions, file formats, and markup patterns that solve this problem—is not optional scaffolding. It is foundational to agent reliability and correctness.
·Free to readRead →Physics Gravity Models in Financial Systems: Applications to Agent Economy Research
The inverse-square decay is not arbitrary—it emerges from the geometry of 3D space (force spreads over a sphere of surface area 4πr²).
·Free to readRead →Empirica's Positioning in the Agent Economy: A Course Lesson on Research APIs, Structured Notes, and Agent-Readable Outputs
The agent economy — a computational substrate where autonomous AI systems execute tasks, consume structured data, and coordinate via APIs with minimal human intervention — imposes strict architectural requirements on information infrastruct…
·Free to readRead →