canonical: https://jentic.com/apis/brasilseg.com.br/brasilseg # Brasilseg API Gateway - ServiceNow Bedrock Proxy The Brasilseg API Gateway runs AI prompts through an AWS Bedrock-backed Lambda for a ServiceNow integration, returning the model's response to the caller. You first authenticate against the login operation with an application name to obtain a JWT, then send a prompt to the protected execution operation. The execution operation accepts a plain prompt or a prompt with one or more file attachments, so documents can be passed in for processing alongside the text. ## For AI agents Authenticate for a JWT, then run a text prompt, optionally with file attachments, through a Bedrock-backed Lambda. Authenticates with a bearer JWT obtained from the login operation. ## Scope Does not handle insurance policies, claims processing, or customer records. Use for authenticating and running Bedrock-backed AI prompts through the gateway only. ## Capabilities - Authenticate with an application name to obtain a JWT for the gateway - Run a text prompt through the Bedrock-backed Lambda and read the response - Attach a single file or multiple files to a prompt for processing ## Use cases ### Agent Prompt Execution An AI agent connected through Jentic authenticates for a token and then sends prompts to the Bedrock-backed execution operation, so a ServiceNow workflow can call a model without wiring the login and bearer flow by hand. The agent receives the model's response directly and can pass it on to the next step. Example prompt: Authenticate with the gateway, then send the prompt 'summarize this incident report' and return the model's answer ### Document-Grounded Prompting A process attaches a file to a prompt so the model can read a document and answer against it, using the single-file or multi-file payload the execution operation accepts. This lets an agent ground its response in an uploaded PDF or image rather than text alone. Example prompt: Attach a claims PDF and ask the model to extract the policy number and incident date ### Authenticated Gateway Access An integration obtains a short-lived JWT from the login operation with its application name and then calls the protected execution operation with that bearer token, so credentials are exchanged for a token on each session rather than embedded in every request. This mirrors the ServiceNow login-then-call flow the gateway was built for. Example prompt: Call the login operation with the application name and store the returned JWT for the execution call ## Key resources - **Auth** — Authenticate with an application name and receive a JWT - **Execution** — Run a prompt, with optional file attachments, through the Bedrock-backed Lambda ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 63 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 93 / 100 - Developer Experience & Jentic Compatibility: 75 / 100 - AI-Readiness & Agent Experience: 34 / 100 - Agent Usability: 94 / 100 - Security: 75 / 100 - AI Discoverability: 88 / 100 - **View full report:** https://jentic.com/apis/brasilseg.com.br/brasilseg/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the Brasilseg API Gateway by hand means calling the login operation with an application name, holding the returned JWT, and sending it as a bearer token on every execution call. Through Jentic you install once, import the gateway from the API Directory, store the credentials once, and your agent calls it. - **Permission scoping:** The gateway has two operations, so a rule can allow just the prompt-execution operation and the login it depends on. The prompt and any files travel in the request body, so your rules bound which operations run rather than which prompt is sent. - **Credential handling:** Your Brasilseg gateway credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'run a prompt through the gateway' or 'authenticate for a token', and Jentic returns the matching Brasilseg operation with its input schema so the agent calls the right endpoint without reading the reference docs. ## Related APIs - **OpenAI API** — Direct text generation and chat completion from OpenAI models - **Anthropic API** — Claude message and chat completion endpoints for prompt-based reasoning - **Cohere API** — Text generation, chat, and embedding models from Cohere ## FAQ ### Is there a Brasilseg MCP server? You don't need an MCP server to give your agent the Brasilseg API Gateway. Jentic connects it directly from the API Directory: import it, store your credentials once, and your agent can authenticate and run prompts straight away, with no extra server to run and no tool definitions loaded into the agent's context. ### Can I limit what my agent is allowed to do with the Brasilseg API Gateway? Yes. You choose which operations your agent may call, so you can allow the prompt-execution operation and the login it depends on and nothing else, and every call it makes is logged. The prompt and any files travel in the request body, so your rules bound which operations run rather than the prompt content. ### What authentication does the Brasilseg API Gateway use? The gateway authenticates with a bearer JWT per its OpenAPI spec: you call the login operation with an application name to obtain a token, then send it in the Authorization header as a bearer token on the protected execution operation. Through Jentic the credentials are stored encrypted by your own instance and injected at call time. ### Can I send file attachments with a prompt to the Brasilseg gateway? Yes. The execution operation accepts either a single-file payload with the file's content type, base64 data, and file name, or a multi-file payload carrying an array of files, so an agent can ground a prompt in one or several uploaded documents. ### What are the rate limits for the Brasilseg API Gateway? The OpenAPI spec does not specify rate limits for the Brasilseg API Gateway. For the limits that apply to your integration, check with the Brasilseg integration team that issued your gateway credentials. ### How do I run a prompt through the Brasilseg gateway with Jentic? Import the Brasilseg API Gateway from the Jentic API Directory, then have your agent issue a request such as 'run this prompt through the gateway'. Jentic matches the intent to the execution operation and returns its input schema so the agent builds a valid request, with your stored credentials injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.