Quick facts
- Best for
- Turn cloud findings into safe remediation
- Pricing
- Freemium
- Editor rating
- 4.5 / 5
- Community saves
- 0
About Tami
Tami is an AI-based cloud security agent at the core of Tamnoon's security solutions. Its main functionality is to aggregate data, conduct deep investigations, and generate remediation to aid cloud security engineers in focusing on safe remediation. Categorized as a context-aware AI, Tami provides support for companies using a CNAPP or CDR by handling everyday security tasks. It consists of four different agents working in tandem to orchestrate and execute remediation plans. These include the 'Context Agent', 'External MCP Agent', 'Code Generation Agent', and 'Automation Retriever Agent'. Tami uses multiple Language Models (LLMs) selected for specific tasks and utilises a human CloudPros verification process for the logic and safety of proposed solutions. Tami also tackles the challenge of response formulation in the cloud security industry by automatically creating validated fixes for any risk it encounters. It's been trained on Tamnoon's playbooks, which allows it to learn from best practices and create innovative approaches to unique scenarios. It works proficiently, whether the context is single-cloud, multi-cloud, or hybrid, generating comprehensive, provider-specific remediation steps. Finally, Tami collaborates closely with expert supervision to deliver agent-led remediation scaled with AI to help teams achieve safe remediation and enhance cloud security.
Pros
- Cloud security enhancement
- Data aggregation capability
- In-depth risk investigation
- Context-aware technology
- Supports CNAPP and CDROrchestrates remediation plans
- Agent diversification
- Automated response formulation
- Human verification process
- Training on Tamnoon's playbooks
- Versatile multi-cloud support
- Flexible hybrid cloud support
- Provider-specific remediation steps
Cons
- Dependent on multiple agents
- Needs human verification process
- Trained only on Tamnoon's playbooks
- No specified support for non-CNAPP/non-CDRConsists mainly of non-generic LLMs
- Heavy reliance on expert supervision
- No clear onsite continuous learning
- Fixed, limited models utilization
- Not identifiable multi-cloud support details
- Non-disclosed solution for single-cloud context
