- Home
- AI Agent Security Software
- Pangea AI Guard
Pangea AI Guard
636 Ramona St, Palo Alto, CA 94301
What it is
Pangea AI Guard protects data and interactions in applications that use large language models. Its detectors cover prompt injection, malicious entities, PII, confidential data, secrets, language, code, competitors, custom entities, and restricted topics, with image and prompt-hardening features listed as early access. Recipes combine detectors and can report, block, redact, encrypt, or defang detected content. Teams can assign unlimited recipes to prompts, retrieval-augmented-generation ingestion, model responses, and agent tool inputs or outputs. Applications connect through APIs, SDKs, gateway extensions, or plugins, with SDKs for Python, Node.js, Go, Java, and C#. Documented gateway integrations include Portkey, Kong, and LiteLLM. SaaS, Edge, and Private Cloud deployment models are available; Edge and Private Cloud keep processing within the customer cloud boundary. Enabling AI Guard activates an Activity Log recording service calls, inputs, outputs, detections, and context. The current version processes up to 20 KiB per request.
For and against
For
- Free account available
- Detects prompt injection and PII
- Configurable report, block, and redact actions
- Supports five SDK languages
- Automatic activity logging
Against
- Requests are limited to 20 KiB
- Image and prompt-hardening features are early access
- Kong streaming responses are not currently supported
The verdict
Pangea AI Guard combines configurable threat detection, content handling, and audit logging for AI applications. Its deployment choices and integrations support varied architectures, while request-size and gateway limitations should be checked first.
Who it suits
It suits teams protecting direct LLM interactions, agent exchanges, or RAG pipelines. Developers can use APIs, SDKs, or documented gateway integrations and start with a free Pangea account.
On the record
- Alerts
- Users can configure webhooks and link them to specific detections to receive activity notifications and take action.pangea.cloud · read 2 Oct 2026
- Audit logging
- When AI Guard is enabled, its Activity Log is automatically activated and records service-call details including input, output, detections, and contextual information.pangea.cloud · read 2 Oct 2026
- Audit trail
- AI Guard automatically activates an Activity Log that records service calls, inputs, outputs, detections, and contextual information in the project audit trail.pangea.cloud · read 3 Oct 2026
- Company
- Pangea’s company page lists its address as 636 Ramona St, Palo Alto, CA 94301.pangea.cloud · read 2 Oct 2026
- Configurable actions
- Recipes combine configurable detectors that can report, block, redact, encrypt, or defang detected content.pangea.cloud · read 2 Oct 2026
- Deployment
- Pangea lists SaaS, Edge, and Private Cloud deployment models; Private Cloud runs data and control planes in the customer's infrastructure and is marked early access.pangea.cloud · read 3 Oct 2026
- Detection
- Its detectors cover prompt injection, malicious entities, PII and confidential data, secrets, language, code, competitors, custom entities, restricted topics, and early access image and prompt-hardening features.pangea.cloud · read 2 Oct 2026
- Detection and sanitization
- It detects prompt injection and other threats, filters content, and can redact or encrypt sensitive information in submitted text.pangea.cloud · read 3 Oct 2026
- Detection methods
- Threat and sensitive-data detection uses heuristics, machine-learning classifiers, and fine-tuned LLMs.pangea.cloud · read 2 Oct 2026
- Detector coverage
- Available detectors cover malicious prompts and entities, PII and confidential data, secrets, language, code, competitors, custom entities, restricted topics, and early-access image and prompt-hardening features.pangea.cloud · read 3 Oct 2026
- Free account
- Pangea’s getting-started guide says a free Pangea account is sufficient to enable AI Guard and start using its APIs.pangea.cloud · read 2 Oct 2026
- Gateway integrations
- Documented AI and API gateway integrations include Portkey, Kong, and LiteLLM.pangea.cloud · read 2 Oct 2026
- Input limit
- The current version supports processing up to 20 KiB of text.pangea.cloud · read 2 Oct 2026
- Integration
- Applications can connect through APIs or SDKs, and AI Guard documents SDKs for Python, JavaScript (Node.js), Go, Java, and C# through its integration options.pangea.cloud · read 2 Oct 2026
- Integrations
- AI Guard can be integrated through APIs and SDKs or through gateway extensions and plugins for Portkey, Kong, and LiteLLM.pangea.cloud · read 3 Oct 2026
- Intended users
- Pangea describes AI Guard as protection for AI-powered applications, including direct LLM interactions, agent data exchanges, and RAG data ingestion and retrieval.pangea.cloud · read 3 Oct 2026
- Pricing model
- Pangea’s billing page lists AI Guard pricing details by data scanned, but the opened page showed only “Loading billing information...” and no price amount.pangea.cloud · read 2 Oct 2026
- Purpose
- AI Guard protects data and interactions with LLMs in AI-powered applications by safeguarding sensitive information, blocking malicious content, and recording application events.pangea.cloud · read 3 Oct 2026
