Observe.AI Evaluations API
Evaluations API can be used to pull all the Evaluations(Manual and Auto QA) done on Observe AI platform.Please note - Allow 24 hrs to pass before pulling Evaluations. ie., For Evaluations completed on 14-Janby 12:00AM PST, they would be available via APIs by 15-Jan by 12:00AM PST. You can pull Evaluations for 90 days at a time i.e., the duration between the end_date andthe start_date should not exceed 90 days. There is no limit as to how far back in the past you want to go for pulling Evaluations.You can go back to the first ever evaluation on the platform unless data retention limits have been set. All the Evaluations that were Submitted, Edited and Deleted in the date-range will be availablein the API response. Lets take an example to explain it further - when you pull Evaluations for 15 days(sayfor start_date - 15-Jan and end_date 30-Jan) on 15-Feb via an API call, you get all Evaluations that were - submitted between 15-jan and 30-jan with "status": "SUBMITTED" submitted before 15-jan but modified/deleted between 15-jan and 30-jan with "status"="EDITED"/ "status"="DELETED" submitted between 15-jan and 30-jan but modified after 30-jan until the pull date(15-Feb)with "status"="EDITED" The S3 URL obtained in the API response (with the evaluations) is valid for 24 hours. If you have been using Basic Auth for the APIs, we request you to switch to OAuth2.0 basedAuth for the APIs by 31-Dec-2022. Detailed instructions to create API Credentials and make the switch to OAuth are documented here. Please reach out to your CSM for more details.
Observe.AI Evaluations API is one of 7 APIs that Observe.AI publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
This API exposes 16 JSON Schema definitions.
Tagged areas include Evaluations. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, a getting-started guide, authentication docs, rate-limit docs, and 16 JSON Schemas.
This API exposes 2 operations across 2 paths, and defines 5 schemas. It is described by OpenAPI 3.2.0.
Requests are made against a single base URL, https://{base_url}.
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 5
Observe.AI Evaluations API declares
5 security schemes
for authenticating requests.
It accepts HTTP bearer tokens (JWT) (bearerAuth).
It defines a object scheme (DsrDeleteRequest).
It defines a object scheme (DsrRule).
It defines a object scheme (DsrDeleteResponse).
It defines a object scheme (DsrStatusResponse).
Paths & Operations 2
Across 2 paths, the API surfaces 2 operations — 1 GET, 1 POST. Each is listed below with its method, path, parameters, and response codes.
Evaluations API can be used to pull all the Evaluations(Manual and Auto QA) done on Observe AI platform. Please note - Allow 24 hrs to pass before pulling Evaluations. ie., For Ev…
Schemas 5
The contract defines 5 schemas that model the data the API accepts and returns. The most detailed are GetJobResponse (4 properties), PostJobResponse (4 properties), RawJobRequest (3 properties), ErrorMessage (2 properties). Each schema is shown below with its type and property counts.
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Observe.AI 6
Other APIs Observe.AI publishes across the network.
This is an independent, third-party profile of Observe.AI Evaluations API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.