Registry 02 / Agents
Research agents.
Agents for urban analysis, evidence synthesis, scenario exploration, and planning workflows. An agent enters this registry with its tools, decision boundaries, and evaluation stated.
Entries
Released agents.
No public entries yet.
Agents are listed here once a release meets the standard. Follow the repository for releases, or propose an entry through an issue.
Agent card
What an agent entry documents.
Every agent entry answers the following. The name in code is the key used in the registry data and in the proposal form.
- Urban question
urban_question - The city problem the work addresses, and who is meant to use the result.
- Task & workflow
task_workflow - The research or planning task, the steps the agent performs, and where the workflow starts and stops.
- Tools & data access
data_provenance - Models, datasets, APIs, and documents the agent can call or read, with their licences.
- Decision boundaries
decision_boundaries - What the agent may decide alone, what requires a human, and how its outputs are reviewed.
- Evaluation protocol
evaluation - Success criteria, reliability across runs, comparison with human performance, and reproducibility.
- Failure modes
failure_modes - Observed errors, fabrication risks, bias in retrieved evidence, and misuse scenarios.
- Traceability
traceability - Logs, intermediate outputs, and citations the agent produces so that results can be audited.
- Geographic validity
geographic_validity - Cities tested, and whether claims are local or supported by cross-city evidence.
- Usage constraints
usage_constraints - Intended users, settings where the agent must not be used, and cost or rate considerations.
- Artifacts & citation
versionlicenselinkscitation - Code, prompts or policies, configuration, version, licence, and citation.