canonical: https://jentic.com/apis/datasense.media/datasense # Datasense Media API de Classificacao de Noticias - DataSense The DataSense News Classification API categorises news text using AI models. It exposes a token endpoint that exchanges credentials for an access token and a classification endpoint that returns a predicted category for a supplied article, with additional options to tune the request. It is built so natural-language processing can be dropped into applications that analyse journalistic text. ## For AI agents Classify news text with AI models: exchange credentials for an access token, then send article text and options to get a predicted category. Suited to automating news categorisation in a content pipeline. ## Scope Does not handle article sourcing, translation, or summarisation. Use for classifying news text with AI models only. ## Capabilities - Classify a news article using AI models with additional options - Obtain an OAuth 2.0 access token from basic credentials - Return a predicted category for journalistic text - Categorise incoming news text for downstream processing ## Use cases ### Agent-Driven News Classification An AI agent connected through Jentic can label news text without a developer wiring the two-step auth: it exchanges credentials for an access token and then sends an article's text to the classification endpoint, which returns the predicted category from its AI model. The agent can use the category to route, tag, or summarise the story. Example prompt: Obtain an access token, then classify a news article's text and return its predicted category ### Content Pipeline Categorisation Publishers and aggregators categorise a stream of incoming stories to route them to the right section. The DataSense classification endpoint takes each article's text and returns its predicted class, which a pipeline can use to sort headlines into topic queues. Options on the request let callers tune the classification for their taxonomy. Example prompt: Classify a batch of incoming headlines one by one and route each to a topic queue by its predicted class ### Editorial Tagging Assistant Editors use automatic classification to suggest where a draft belongs before publishing. An agent sends a draft article to the classification endpoint and proposes the matching section from the returned category. This keeps tagging consistent without a manual pass on every story. Example prompt: Classify a draft article and suggest the matching section based on the returned category ## Key resources - **Authentication** — Exchange basic credentials for an OAuth 2.0 bearer token. - **Classification** — Classify news text and return a predicted category. ## 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:** 56 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 46 / 100 - Developer Experience & Jentic Compatibility: 81 / 100 - AI-Readiness & Agent Experience: 42 / 100 - Agent Usability: 94 / 100 - Security: 43 / 100 - AI Discoverability: 69 / 100 - **View full report:** https://jentic.com/apis/datasense.media/datasense/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 DataSense News Classification API by hand means handling its two-step auth: HTTP basic credentials to the token endpoint, then an OAuth 2.0 bearer token on the classification call, across separate auth and API hosts. Through Jentic you install once, import DataSense from the API Directory, store the credentials once, and your agent calls it. - **Permission scoping:** The API has just two operations, token exchange and classification, so a rule bounds your agent to exactly those. Because the article content travels in the request body, rules bound which operation runs rather than which text is classified. - **Credential handling:** Your DataSense 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 'classify a news story', and Jentic returns the matching DataSense operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Tisane** — Natural-language analysis for sentiment, abuse, and content classification. - **Amazon Comprehend** — Managed NLP for entity recognition, sentiment, and custom text classification. - **APITube News API** — News content API that supplies the articles a classifier can label. ## FAQ ### What authentication does the DataSense News Classification API use? The API uses two schemes per its OpenAPI spec: the token endpoint authenticates with HTTP basic credentials, and the classification endpoint then requires an OAuth 2.0 bearer token (a JWT) in the Authorization header. Through Jentic both credentials are stored once, encrypted, by your own Jentic One instance and injected at call time. ### Can I classify a news article with the DataSense News Classification API? Yes. After obtaining an access token, you send the article text and any additional options to the classification endpoint, which returns the predicted category from its AI model. The classification call is the core operation of the API. ### What are the rate limits for the DataSense News Classification API? The OpenAPI spec does not define rate limits for the DataSense News Classification API. Check the DataSense documentation at https://datasense.media for current limits. ### Is there a DataSense MCP server? You don't need an MCP server to connect your agent to the DataSense News Classification API. Jentic imports it directly from the API Directory: store your credentials once and your agent obtains a token and classifies news text. Operations are discovered on demand without loading another server's tool definitions into context. ### Can I limit what my agent is allowed to do with the DataSense News Classification API? Yes. The API exposes only a token-exchange and a classification operation, so a rule can allow just those two and nothing else. Because the article text travels in the request body, rules bound which operation runs rather than which article is sent. Every call the agent makes is logged. ### How do I classify a news article with the DataSense News Classification API through Jentic? Search Jentic for 'classify a news article', and it returns the matching DataSense operations with their input schemas. Your agent obtains an access token and sends the article text to the classification endpoint. To run it on your own infrastructure, install Jentic One from its GitHub repo.