The AI-powered Chatbot in Traceable enables you to query the data shown on the Traceable platform using natural language. Instead of navigating to multiple filters and dashboards, you can use this chatbot to answer queries such as "Show me APIs with no authentication”.
Currently, the chatbot is based on read-only use cases within the following pages in the Catalog module:
To use the chatbot, you can click Ask AI in the bottom right corner of any of the above pages. You can use the chatbot to explore and extract insights from sources such as APIs, services, domains, backends, and sensitive data flows.
.png)
AI Chatbot
Note
The chatbot supports read-only queries; it does not allow updating configurations or triggering scans.
Data Sources
The chatbot queries and extracts data from the following sources in the Catalog module:
API Inventory — Provides a detailed catalog of all discovered APIs, including their endpoints, authentication requirements, exposure levels (internal or external), ownership information, and traffic visibility. For more information, see Inventory.
Services — Provides a logical grouping of APIs that help you understand which APIs belong to which service and the associated risk. For more information, see Services.
Domains — Provides information on internal and external domains connected to the environments, highlighting which domains are public-facing, internal-only, or linked to third parties. For more information, see Domains.
Backends — Provides information on connected backend systems and services that receive traffic from APIs, allowing you to identify dependencies, traffic volume, and data sensitivity within backend connections. For more information, see Backends.
Sensitive Data — Provides information on API endpoints that process sensitive data, such as Personally Identifiable Information (PII), Social Security Numbers (SSN), or authentication tokens. This helps you identify risks associated with data privacy. For more information, see Sensitive Data.
Sample Questions
The following are some examples of the types of questions you can ask the chatbot:
Entity-based Queries
Show endpoints with no authentication.
List services with failed validations or errors.
Which backends received traffic in the past 24 hours?
Sensitive Data Queries
Which APIs have sensitive data exposure?
Show domains tagged as external, having PII exposure.
Contextual Queries
Which APIs changed in the past week?
Summarize the endpoints with risk above 6, discovered this month.
Ownership Queries
Which services do not have any assigned owners?
How do I download the list of unauthenticated public endpoints?
Feedback
You can provide feedback to each chatbot response using the following options:
Thumbs Up — Considers positive feedback.
Thumbs Down — Enables you to provide additional comments on how the chatbot should improve.
Traceable uses this feedback to improve future versions of the chatbot.
Caveats
By default, the chatbot displays up to 10 results per query for quick readability. For larger datasets, you can refine your query to view results according to your requirements.
Traceable chatbot preserves session context for follow-up questions within a single session. A session remains active until closed or after 15 minutes of inactivity, after which it automatically restarts.