Education
An environment provides activities, resources, constraints, and evaluation criteria. A student's agent helps them complete the activity, while an instructor's agent can evaluate submissions using a shared contract.
Experimental open pattern for agent-portable experiences
Bring your agent.
Enter the experience.
Do the work.
BYOAg allows people to bring their own AI agent into an external environment where the experience provides the context, artifacts, tools, rules, and interaction contract. People retain continuity with their chosen agent while providers can offer a bounded experience without owning a general-purpose customer agent.
User-owned agent
Carries continuity, preferences, and working style.
BYOAg entry point
Publishes context, rules, artifacts, tools, and a contract.
Submission Feedback Evidence Continuation
Traditional AI integrations bring data, tools, and context into an agent-controlled environment.
BYOAg allows an agent to enter an environment-controlled experience. The agent remains the user's agent. The environment defines the work.
The core model
Four roles, one interaction contract
BYOAg separates who brings intelligence from who defines the experience, artifacts, and rules.
01
Human
Chooses the agent and authorizes the work.
02
Personal agent
Interprets the package and assists the user.
03
BYOAg environment
Publishes the work surface and evaluates results.
04
Artifacts, tools, rules, and contracts
Constrain, explain, and record the interaction.
How it works
A small lifecycle for agent entry
- 1 The environment publishes an entry point.
- 2 The user gives the entry point to their agent.
- 3 The agent retrieves a Prompt Package or Agentic Contract.
- 4 The agent performs the work and submits a result, receives feedback, or continues to the next interaction.
Why BYOAg
A more practical path to agent-enabled services
BYOAg explores how providers can participate in agent-mediated experiences without assuming they must first build and operate a complete customer-facing agent platform.
Why now
A useful, reliable AI experience can require data preparation, retrieval, evaluation, permissions, security, observability, and safe execution. Building and operating that foundation can keep many businesses waiting.
BYOAg can shift the starting point. Instead of requiring every provider to own all of the intelligence layer, it lets them focus on the capabilities, data, policies, and experience that are specific to their service.
The future BYOAg is exploring
Personal agents may become a common service interface.
This is a directional hypothesis, not a prediction. As personal agents take on more comparison, coordination, and delegated work, human attention, judgment, and authorization may become the real constraint.
BYOAg explores how a provider could collaborate with the agent a person already chose while keeping the person at the center of the relationship.
BYOAg does not remove a provider's responsibility for secure systems, data quality, authorization, or operations. It makes the work surface and its boundaries more explicit for people, agents, and environments.
Initial use cases
Places where the pattern can be explored first
Entertainment and games
An agent enters a game, trivia session, simulation, or branching story. Each submission can produce feedback, scoring, or the next scene.
Healthcare care navigation
A care provider can help a person prepare for an appointment, understand available services, and route questions to an appropriate clinician. It does not replace medical judgment or clinical care.
Commerce
A service can present relevant products, availability, policies, and next steps while a person's agent helps compare options and requests approval before a consequential action.
Experimental status
BYOAg is currently an experimental pattern.
It is being developed through prototypes, working examples, architectural discussion, and an evolving draft specification. Developers, researchers, product designers, educators, and agent builders are invited to explore, question, and contribute.
Learning through participation
Learn BYOAg by using BYOAg
BYOAg is easier to understand when you experience it directly. We are developing short learning paths that combine architectural explanations, working examples, and hands-on challenges in BYOAg Arena.
Bring your own agent, participate in a guided experience, and learn how Prompt Packages, structured submissions, feedback, evidence, and continuation work together. BYOAg Arena is being explored as both a practical learning environment and a reference implementation of the pattern.
BYOAg Academy and BYOAg Arena are currently under development.
Design partners
Exploring BYOAg for your organization?
We are looking for early design partners interested in exploring agent-portable experiences for education, entertainment, care navigation, commerce, enterprise processes, and asynchronous agent interactions.
BYOAg is an open architectural pattern. Organizations may still need support identifying suitable use cases, designing interaction contracts, implementing secure integrations, and validating compatibility. The pattern is intended to help providers focus on their own service rather than require a general-purpose customer agent from day one.