The AI Agent Index

Documenting the technical and safety features of deployed agentic AI systems

AIAgent.app

Basic information

Website: https://web.archive.org/web/20241223075645/https://aiagent.app/

Short description: An AI Agent which can be used for web-based tasks provided by the user [source]

Intended uses: What does the developer say it’s for? Web based tasks, including market research, travel planning, etc.

Date(s) deployed: First website archive from April 19, 2023 [source]

Developer

Website: https://web.archive.org/web/20241223075645/https://aiagent.app/

Legal name: BIG CORP LIMITED, d/b/a AiAgent [source]

Entity type: Private limited company [source]

Country (location of developer or first author’s first affiliation): Incorporation: England, UK (14438372) [source]. Registration: London, England [source]

Safety policies: What safety and/or responsibility policies are in place? Unknown

System components

Backend model: What model(s) are used to power the system? GPT 3.5 and GPT 4

Publicly available model specification: Is there formal documentation on the system’s intended uses and how it is designed to behave in them? None

Reasoning, planning, and memory implementation: How does the system ‘think’? Decomposes task into smaller tasks by creating a to-do list; then, goes through iterative cycles of creating any more tasks that seem necessary, re-prioritizing the tasks, and executing the highest priority task [source]

Observation space: What is the system able to observe while ‘thinking’? The AI agent is able to navigate on the web (text inputs) [source]

Action space/tools: What direct actions can the system take? The agent can directly perform actions on the web [source]

User interface: How do users interact with the system? Users create conversations with names, specify the language model they wish to use, and provide a goal to the AI agent [source]

Development cost and compute: What is known about the development costs? Unknown

Guardrails and oversight

Accessibility of components:

  • Weights: Are model parameters available? N/A; backends external model(s) via API
  • Data: Is data available? N/A; backends external model(s) via API
  • Code: Is code available? Closed source
  • Scaffolding: Is system scaffolding available? Closed source
  • Documentation: Is documentation available? Closed source

Controls and guardrails: What notable methods are used to protect against harmful actions? Unknown

Customer and usage restrictions: Are there know-your-customer measures or other restrictions on customers? None

Monitoring and shutdown procedures: Are there any notable methods or protocols that allow for the system to be shut down if it is observed to behave harmfully? None

Evaluation

Notable benchmark evaluations: None

Bespoke testing: None

Safety: Have safety evaluations been conducted by the developers? What were the results? None

Publicly reported external red-teaming or comparable auditing:

  • Personnel: Who were the red-teamers/auditors? None
  • Scope, scale, access, and methods: What access did red-teamers/auditors have and what actions did they take? None
  • Findings: What did the red-teamers/auditors conclude? None

Ecosystem information

Interoperability with other systems: What tools or integrations are available? None

Usage statistics and patterns: Are there any notable observations about usage? 32000+ users according to the website [source]

Additional notes

None