The AI Agent Index

Documenting the technical and safety features of deployed agentic AI systems

Lucy


Basic information

Website: https://web.archive.org/web/20241223121501/https://www.cykel.ai/

Short description: Digital worker platform for recruitment, sales and research agents [source]

Intended uses: What does the developer say it’s for? Automating repetitive tasks/”workflows” associated with recruitment, sales and research teams through their digital workers [source]

Date(s) deployed: The flagship agent named “Lucy” was announced December 5, 2024 [source]


Developer

Website: https://web.archive.org/web/20241229130924/https://h2o.ai/

Legal name: Cykel AI PLC [source]

Entity type: Public limited company (UK) [source]

Country (location of developer or first author’s first affiliation): Incorporation: England, UK (11155663) [source]. Registration: England, Wales [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? Unknown

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’? Unknown

Observation space: What is the system able to observe while ‘thinking’? Digital workers operate within the existing software environment of a company. Nonetheless, the company has to set permissions, define workflows, and can monitor all activities in real-time. Digital workers can adapt themselves to the preferences over time. Operations can be scaled up or down instantly and workflows modified whenever needed [source]

Action space/tools: What direct actions can the system take? Agents are designed to interact with all the software used by the company (extensive integration of over a hundred different tools), modify files, send emails/contact clients through their CRM and supposedly, interact with any available API.. [source]

User interface: How do users interact with the system? There is a dashboard to configure the agents and view their tasks [source]

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


Guardrails and oversight

Accessibility of components:

  • Weights: Are model parameters available? Unknown
  • Data: Is data available? Unknown
  • 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? The company/client has to set permissions, define workflows, and can monitor all activities in real-time. Operations can be scaled up or down instantly and workflows modified whenever needed [source]

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? Unknown


Evaluation

Notable benchmark evaluations: None

Bespoke testing: Demos [source]

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? They provide a sample of the most common integrations they offer and say they can be contacted for some more specific ones [source]

Usage statistics and patterns: Are there any notable observations about usage? None


Additional notes

None