diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0d6d0fe..27403a0 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,305 +1,205 @@
 # [0.6.0](https://github.com/forcedotcom/agents/compare/0.5.11...0.6.0) (2025-01-16)
 
-
 ### Bug Fixes
 
-* modify structure, order, and types ([5f75c87](https://github.com/forcedotcom/agents/commit/5f75c878a19a15123bb3cbc37e8424e2b5b27834))
-* update test ([e22b460](https://github.com/forcedotcom/agents/commit/e22b4606793a70b51d1321a4a232295c64bd03b2))
-
+- modify structure, order, and types ([5f75c87](https://github.com/forcedotcom/agents/commit/5f75c878a19a15123bb3cbc37e8424e2b5b27834))
+- update test ([e22b460](https://github.com/forcedotcom/agents/commit/e22b4606793a70b51d1321a4a232295c64bd03b2))
 
 ### Features
 
-* add agentCreate v2 API and mock ([333f8cb](https://github.com/forcedotcom/agents/commit/333f8cb58e6633348af035b757e404dd276db0c0))
-
-
+- add agentCreate v2 API and mock ([333f8cb](https://github.com/forcedotcom/agents/commit/333f8cb58e6633348af035b757e404dd276db0c0))
 
 ## [0.5.11](https://github.com/forcedotcom/agents/compare/0.5.10...0.5.11) (2025-01-11)
 
-
 ### Bug Fixes
 
-* **deps:** bump ansis from 3.5.2 to 3.8.1 ([8721e95](https://github.com/forcedotcom/agents/commit/8721e95b6f08f158dd57df90cfed992ab74ee7a7))
-
-
+- **deps:** bump ansis from 3.5.2 to 3.8.1 ([8721e95](https://github.com/forcedotcom/agents/commit/8721e95b6f08f158dd57df90cfed992ab74ee7a7))
 
 ## [0.5.10](https://github.com/forcedotcom/agents/compare/0.5.9...0.5.10) (2025-01-11)
 
-
 ### Bug Fixes
 
-* **deps:** bump @salesforce/source-deploy-retrieve ([3d67921](https://github.com/forcedotcom/agents/commit/3d679210bd7f969d9d9b88cbb042a1c232c7db4e))
-
-
+- **deps:** bump @salesforce/source-deploy-retrieve ([3d67921](https://github.com/forcedotcom/agents/commit/3d679210bd7f969d9d9b88cbb042a1c232c7db4e))
 
 ## [0.5.9](https://github.com/forcedotcom/agents/compare/0.5.8...0.5.9) (2025-01-06)
 
-
 ### Bug Fixes
 
-* fixed column widths ([13b661f](https://github.com/forcedotcom/agents/commit/13b661f6d97a233a213bf266b187624b72d4d389))
-
-
+- fixed column widths ([13b661f](https://github.com/forcedotcom/agents/commit/13b661f6d97a233a213bf266b187624b72d4d389))
 
 ## [0.5.8](https://github.com/forcedotcom/agents/compare/0.5.7...0.5.8) (2025-01-06)
 
-
 ### Bug Fixes
 
-* bump oclif table ([7ed9d30](https://github.com/forcedotcom/agents/commit/7ed9d30263fef2243bf087d2c7d5777f47a2c032))
-
-
+- bump oclif table ([7ed9d30](https://github.com/forcedotcom/agents/commit/7ed9d30263fef2243bf087d2c7d5777f47a2c032))
 
 ## [0.5.7](https://github.com/forcedotcom/agents/compare/0.5.6...0.5.7) (2025-01-04)
 
-
 ### Bug Fixes
 
-* **deps:** bump @salesforce/source-deploy-retrieve ([3213bf5](https://github.com/forcedotcom/agents/commit/3213bf548beffca94eb69262607eaff1aeb3d3a3))
-
-
+- **deps:** bump @salesforce/source-deploy-retrieve ([3213bf5](https://github.com/forcedotcom/agents/commit/3213bf548beffca94eb69262607eaff1aeb3d3a3))
 
 ## [0.5.6](https://github.com/forcedotcom/agents/compare/0.5.5...0.5.6) (2024-12-28)
 
-
 ### Bug Fixes
 
-* **deps:** bump ansis from 3.4.0 to 3.5.2 ([88b8163](https://github.com/forcedotcom/agents/commit/88b81635731983297d11a8de896e3e170bb58a51))
-
-
+- **deps:** bump ansis from 3.4.0 to 3.5.2 ([88b8163](https://github.com/forcedotcom/agents/commit/88b81635731983297d11a8de896e3e170bb58a51))
 
 ## [0.5.5](https://github.com/forcedotcom/agents/compare/0.5.4...0.5.5) (2024-12-21)
 
-
 ### Bug Fixes
 
-* **deps:** bump @oclif/table from 0.3.7 to 0.3.9 ([a6fe6df](https://github.com/forcedotcom/agents/commit/a6fe6dfcfbb88a61940d15e762fc58587731d54e))
-
-
+- **deps:** bump @oclif/table from 0.3.7 to 0.3.9 ([a6fe6df](https://github.com/forcedotcom/agents/commit/a6fe6dfcfbb88a61940d15e762fc58587731d54e))
 
 ## [0.5.4](https://github.com/forcedotcom/agents/compare/0.5.3...0.5.4) (2024-12-21)
 
-
 ### Bug Fixes
 
-* **deps:** bump fast-xml-parser from 4.5.0 to 4.5.1 ([20dde46](https://github.com/forcedotcom/agents/commit/20dde46762d9fa143d9512f2aac24afc77f16f18))
-
-
+- **deps:** bump fast-xml-parser from 4.5.0 to 4.5.1 ([20dde46](https://github.com/forcedotcom/agents/commit/20dde46762d9fa143d9512f2aac24afc77f16f18))
 
 ## [0.5.3](https://github.com/forcedotcom/agents/compare/0.5.2...0.5.3) (2024-12-20)
 
-
 ### Bug Fixes
 
-* add env var for polling ([4a20d50](https://github.com/forcedotcom/agents/commit/4a20d50d68352c25509c4a1f32c2dce1286d6882))
-
-
+- add env var for polling ([4a20d50](https://github.com/forcedotcom/agents/commit/4a20d50d68352c25509c4a1f32c2dce1286d6882))
 
 ## [0.5.2](https://github.com/forcedotcom/agents/compare/0.5.1...0.5.2) (2024-12-18)
 
-
 ### Bug Fixes
 
-* update HRO ([accc6a1](https://github.com/forcedotcom/agents/commit/accc6a109295b7b8ca4ae6d6410e761cabd5ccc7))
-
-
+- update HRO ([accc6a1](https://github.com/forcedotcom/agents/commit/accc6a109295b7b8ca4ae6d6410e761cabd5ccc7))
 
 ## [0.5.1](https://github.com/forcedotcom/agents/compare/0.5.0...0.5.1) (2024-12-16)
 
-
 ### Bug Fixes
 
-* update expected response from details API ([49a19fd](https://github.com/forcedotcom/agents/commit/49a19fd8032a0d47d4256c554b48eb6f47c95bae))
-
-
+- update expected response from details API ([49a19fd](https://github.com/forcedotcom/agents/commit/49a19fd8032a0d47d4256c554b48eb6f47c95bae))
 
 # [0.5.0](https://github.com/forcedotcom/agents/compare/0.4.5...0.5.0) (2024-12-16)
 
-
 ### Features
 
-* support TAP format for test results ([f48cb12](https://github.com/forcedotcom/agents/commit/f48cb1218a197b5c8b1f8a9bff7025c435781d96))
-
-
+- support TAP format for test results ([f48cb12](https://github.com/forcedotcom/agents/commit/f48cb1218a197b5c8b1f8a9bff7025c435781d96))
 
 ## [0.4.5](https://github.com/forcedotcom/agents/compare/0.4.4...0.4.5) (2024-12-14)
 
-
 ### Bug Fixes
 
-* **deps:** bump @salesforce/source-deploy-retrieve ([a282749](https://github.com/forcedotcom/agents/commit/a28274962414ee576e9da3e3ba8df21eab3ab9ad))
-
-
+- **deps:** bump @salesforce/source-deploy-retrieve ([a282749](https://github.com/forcedotcom/agents/commit/a28274962414ee576e9da3e3ba8df21eab3ab9ad))
 
 ## [0.4.4](https://github.com/forcedotcom/agents/compare/0.4.3...0.4.4) (2024-12-13)
 
-
-
 ## [0.4.3](https://github.com/forcedotcom/agents/compare/0.4.2...0.4.3) (2024-12-13)
 
-
-
 ## [0.4.2](https://github.com/forcedotcom/agents/compare/0.4.1...0.4.2) (2024-12-10)
 
-
 ### Bug Fixes
 
-* retrieve GenAiPlugins too ([1d461a2](https://github.com/forcedotcom/agents/commit/1d461a27a713212bb2f033046a71d47d3be21204))
-
-
+- retrieve GenAiPlugins too ([1d461a2](https://github.com/forcedotcom/agents/commit/1d461a27a713212bb2f033046a71d47d3be21204))
 
 ## [0.4.1](https://github.com/forcedotcom/agents/compare/0.4.0...0.4.1) (2024-12-10)
 
-
 ### Bug Fixes
 
-* agent create working ([1a57a90](https://github.com/forcedotcom/agents/commit/1a57a90630a043ad6294a9895145fa4fd7442330))
-* agent.create WIP ([836f6db](https://github.com/forcedotcom/agents/commit/836f6db06cd529d0482b9fa9630b9314892b799f))
-* emit lifecycle events ([c3bba31](https://github.com/forcedotcom/agents/commit/c3bba3100f953a320efb4542f0ecc031a5d41179))
-
-
+- agent create working ([1a57a90](https://github.com/forcedotcom/agents/commit/1a57a90630a043ad6294a9895145fa4fd7442330))
+- agent.create WIP ([836f6db](https://github.com/forcedotcom/agents/commit/836f6db06cd529d0482b9fa9630b9314892b799f))
+- emit lifecycle events ([c3bba31](https://github.com/forcedotcom/agents/commit/c3bba3100f953a320efb4542f0ecc031a5d41179))
 
 # [0.4.0](https://github.com/forcedotcom/agents/compare/0.3.1...0.4.0) (2024-12-10)
 
-
 ### Features
 
-* junit result formatter ([42ff64b](https://github.com/forcedotcom/agents/commit/42ff64bd855d4de5e4f6585ab5c141816d1bccf3))
-
-
+- junit result formatter ([42ff64b](https://github.com/forcedotcom/agents/commit/42ff64bd855d4de5e4f6585ab5c141816d1bccf3))
 
 ## [0.3.1](https://github.com/forcedotcom/agents/compare/0.3.0...0.3.1) (2024-12-07)
 
-
 ### Bug Fixes
 
-* **deps:** bump @oclif/table from 0.3.3 to 0.3.5 ([49ce6d5](https://github.com/forcedotcom/agents/commit/49ce6d58fe3a433a14bad20d38240180aaff864f))
-
-
+- **deps:** bump @oclif/table from 0.3.3 to 0.3.5 ([49ce6d5](https://github.com/forcedotcom/agents/commit/49ce6d58fe3a433a14bad20d38240180aaff864f))
 
 # [0.3.0](https://github.com/forcedotcom/agents/compare/0.2.4...0.3.0) (2024-12-05)
 
-
 ### Features
 
-* export test formatters ([b5f26df](https://github.com/forcedotcom/agents/commit/b5f26df835c3a08e9065f327afc4a6bc1997c9ab))
-
-
+- export test formatters ([b5f26df](https://github.com/forcedotcom/agents/commit/b5f26df835c3a08e9065f327afc4a6bc1997c9ab))
 
 ## [0.2.4](https://github.com/forcedotcom/agents/compare/0.2.3...0.2.4) (2024-12-03)
 
-
 ### Bug Fixes
 
-* add doc for agent class ([5208345](https://github.com/forcedotcom/agents/commit/52083450e7eff71e1cc3caf570abd18939317d9a))
-
-
+- add doc for agent class ([5208345](https://github.com/forcedotcom/agents/commit/52083450e7eff71e1cc3caf570abd18939317d9a))
 
 ## [0.2.3](https://github.com/forcedotcom/agents/compare/0.2.2...0.2.3) (2024-12-03)
 
-
-
 ## [0.2.2](https://github.com/forcedotcom/agents/compare/0.2.1...0.2.2) (2024-12-02)
 
-
 ### Bug Fixes
 
-* export more types ([0a1d408](https://github.com/forcedotcom/agents/commit/0a1d408dd0d815b36509d5b5fe343e7e0817d1a2))
-
-
+- export more types ([0a1d408](https://github.com/forcedotcom/agents/commit/0a1d408dd0d815b36509d5b5fe343e7e0817d1a2))
 
 ## [0.2.1](https://github.com/forcedotcom/agents/compare/0.2.0...0.2.1) (2024-12-02)
 
-
 ### Bug Fixes
 
-* update return type on start ([c14e8c4](https://github.com/forcedotcom/agents/commit/c14e8c41c3180dad1df807a3531e944b89cce229))
-
-
+- update return type on start ([c14e8c4](https://github.com/forcedotcom/agents/commit/c14e8c41c3180dad1df807a3531e944b89cce229))
 
 # [0.2.0](https://github.com/forcedotcom/agents/compare/0.1.6...0.2.0) (2024-12-02)
 
-
 ### Bug Fixes
 
-* add polling lifecycle events ([695fd08](https://github.com/forcedotcom/agents/commit/695fd086865c60850d53aa2753686ea5aeef2d4a))
-* use sf-plugins-core for making table ([97eaa63](https://github.com/forcedotcom/agents/commit/97eaa633fd739c214029ce0fb1dbd521f220c5ae))
-
+- add polling lifecycle events ([695fd08](https://github.com/forcedotcom/agents/commit/695fd086865c60850d53aa2753686ea5aeef2d4a))
+- use sf-plugins-core for making table ([97eaa63](https://github.com/forcedotcom/agents/commit/97eaa633fd739c214029ce0fb1dbd521f220c5ae))
 
 ### Features
 
-* add cancel method ([8371f9f](https://github.com/forcedotcom/agents/commit/8371f9fd735bfd7e12dd4a95419e321bb34cf465))
-* mock agent testing ([8df61a9](https://github.com/forcedotcom/agents/commit/8df61a9fba8005d0823bba5ce5f14d3ab5a5c12e))
-* mocked agent testing ([334988d](https://github.com/forcedotcom/agents/commit/334988d753f942fbfecdaa776e2285c51b81ebf5))
-* poll both status and details ([61b03dc](https://github.com/forcedotcom/agents/commit/61b03dcba132ed07df194953c850595771f3ccff))
-
-
+- add cancel method ([8371f9f](https://github.com/forcedotcom/agents/commit/8371f9fd735bfd7e12dd4a95419e321bb34cf465))
+- mock agent testing ([8df61a9](https://github.com/forcedotcom/agents/commit/8df61a9fba8005d0823bba5ce5f14d3ab5a5c12e))
+- mocked agent testing ([334988d](https://github.com/forcedotcom/agents/commit/334988d753f942fbfecdaa776e2285c51b81ebf5))
+- poll both status and details ([61b03dc](https://github.com/forcedotcom/agents/commit/61b03dcba132ed07df194953c850595771f3ccff))
 
 ## [0.1.6](https://github.com/forcedotcom/agents/compare/0.1.5...0.1.6) (2024-11-16)
 
-
 ### Bug Fixes
 
-* **deps:** bump cross-spawn from 7.0.3 to 7.0.5 ([7f43cc7](https://github.com/forcedotcom/agents/commit/7f43cc706b848fd54c88d04bee2c0b7b632d7e76))
-
-
+- **deps:** bump cross-spawn from 7.0.3 to 7.0.5 ([7f43cc7](https://github.com/forcedotcom/agents/commit/7f43cc706b848fd54c88d04bee2c0b7b632d7e76))
 
 ## [0.1.5](https://github.com/forcedotcom/agents/compare/0.1.4...0.1.5) (2024-11-16)
 
-
 ### Bug Fixes
 
-* **deps:** bump @salesforce/core from 8.6.3 to 8.8.0 ([193237b](https://github.com/forcedotcom/agents/commit/193237b5dbbe7ce1ee596a3b7305b5602d0883f8))
-
-
+- **deps:** bump @salesforce/core from 8.6.3 to 8.8.0 ([193237b](https://github.com/forcedotcom/agents/commit/193237b5dbbe7ce1ee596a3b7305b5602d0883f8))
 
 ## [0.1.4](https://github.com/forcedotcom/agents/compare/0.1.3...0.1.4) (2024-11-12)
 
-
 ### Bug Fixes
 
-* do not append spec in name ([284d5d5](https://github.com/forcedotcom/agents/commit/284d5d56ed99c67b93a65904a00fdb00a2552a0e))
-
-
+- do not append spec in name ([284d5d5](https://github.com/forcedotcom/agents/commit/284d5d56ed99c67b93a65904a00fdb00a2552a0e))
 
 ## [0.1.3](https://github.com/forcedotcom/agents/compare/0.1.2...0.1.3) (2024-11-12)
 
-
 ### Bug Fixes
 
-* use latest ([92ecbba](https://github.com/forcedotcom/agents/commit/92ecbbabc403fe57bf4069f9928b029d23db7a16))
-
-
+- use latest ([92ecbba](https://github.com/forcedotcom/agents/commit/92ecbbabc403fe57bf4069f9928b029d23db7a16))
 
 ## [0.1.2](https://github.com/forcedotcom/agents/compare/0.1.1...0.1.2) (2024-11-12)
 
-
 ### Bug Fixes
 
-* publish to preview ([3f5ccb6](https://github.com/forcedotcom/agents/commit/3f5ccb687017186eb29b8b18c7fdce33daee1f70))
-
-
+- publish to preview ([3f5ccb6](https://github.com/forcedotcom/agents/commit/3f5ccb687017186eb29b8b18c7fdce33daee1f70))
 
 ## [0.1.1](https://github.com/forcedotcom/agents/compare/0.1.0...0.1.1) (2024-11-10)
 
-
 ### Bug Fixes
 
-* export Agent class ([6c42b63](https://github.com/forcedotcom/agents/commit/6c42b63bbe9a5a5cf6fa0cea8f5649d07aaa6adc))
-
-
+- export Agent class ([6c42b63](https://github.com/forcedotcom/agents/commit/6c42b63bbe9a5a5cf6fa0cea8f5649d07aaa6adc))
 
 # [0.1.0](https://github.com/forcedotcom/agents/compare/0c5d8d6ab9e9a8470c7192a56350567882a3017b...0.1.0) (2024-11-09)
 
-
 ### Bug Fixes
 
-* improve types and linting ([d5a6cb3](https://github.com/forcedotcom/agents/commit/d5a6cb3348e63d52e10540e99cf509be64a26649))
-* revise readme and version ([f690b7f](https://github.com/forcedotcom/agents/commit/f690b7f8a911315f467f00f5f533e22e92c69a9e))
-
+- improve types and linting ([d5a6cb3](https://github.com/forcedotcom/agents/commit/d5a6cb3348e63d52e10540e99cf509be64a26649))
+- revise readme and version ([f690b7f](https://github.com/forcedotcom/agents/commit/f690b7f8a911315f467f00f5f533e22e92c69a9e))
 
 ### Features
 
-* add initial agent job spec create and mock ([0c5d8d6](https://github.com/forcedotcom/agents/commit/0c5d8d6ab9e9a8470c7192a56350567882a3017b))
-
-
-
+- add initial agent job spec create and mock ([0c5d8d6](https://github.com/forcedotcom/agents/commit/0c5d8d6ab9e9a8470c7192a56350567882a3017b))
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index a257f13..5f994e9 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -2,15 +2,15 @@
 
 1. Familiarize yourself with the codebase by reading the docs, in
    particular the [developing](./developing.md) doc.
-1. Create a new issue before starting your project so that we can keep track of
+2. Create a new issue before starting your project so that we can keep track of
    what you're trying to add/fix. That way, we can also offer suggestions or
    let you know if there is already an effort in progress.
-1. Fork this repository.
-1. Set up your environment using the information in the [developing](./developing.md) doc.
-1. Create a _topic_ branch in your fork based on the correct branch (usually the **develop** branch, see [Branches section](./developing.md)). Note: this step is recommended but technically not required if contributing using a fork.
-1. Edit the code in your fork.
-1. Sign the CLA (see [CLA](#cla)).
-1. Send us a pull request when you're done. We'll review your code, suggest any
+3. Fork this repository.
+4. Set up your environment using the information in the [developing](./developing.md) doc.
+5. Create a _topic_ branch in your fork based on the correct branch (usually the **develop** branch, see [Branches section](./developing.md)). Note: this step is recommended but technically not required if contributing using a fork.
+6. Edit the code in your fork.
+7. Sign the CLA (see [CLA](#cla)).
+8. Send us a pull request when you're done. We'll review your code, suggest any
    needed changes, and merge it in.
 
 ## Pull Requests
@@ -31,7 +31,3 @@ Agreement. You can do so by going to <https://cla.salesforce.com/sign-cla>.
 ### Merging Pull Requests
 
 Pull request merging is restricted to squash and merge only.
-
-## Helpful Resources
-
-- [developing](./developing.md) doc.
diff --git a/src/agentTester.ts b/src/agentTester.ts
index 41c9dd6..dcfdc79 100644
--- a/src/agentTester.ts
+++ b/src/agentTester.ts
@@ -9,7 +9,7 @@ import { Duration, env } from '@salesforce/kit';
 import ansis from 'ansis';
 import { MaybeMock } from './maybe-mock';
 
-export type TestStatus = 'NEW' | 'IN_PROGRESS' | 'COMPLETED' | 'ERROR';
+export type TestStatus = 'New' | 'InProgress' | 'Completed' | 'Error';
 
 export type AgentTestStartResponse = {
   aiEvaluationId: string;
@@ -25,14 +25,13 @@ export type AgentTestStatusResponse = {
 
 export type TestCaseResult = {
   status: TestStatus;
-  number: string;
   utterance: string;
   startTime: string;
   endTime?: string;
   generatedData: {
     type: 'AGENT';
     actionsSequence: string[];
-    outcome: 'Success' | 'Failure';
+    outcome: string;
     topic: string;
     inputTokensCount: string;
     outputTokensCount: string;
@@ -42,7 +41,7 @@ export type TestCaseResult = {
     actualValue: string;
     expectedValue: string;
     score: number;
-    result: 'Passed' | 'Failed';
+    result: 'PASS' | 'FAILURE';
     metricLabel: 'Accuracy' | 'Precision';
     metricExplainability: string;
     status: TestStatus;
@@ -53,7 +52,7 @@ export type TestCaseResult = {
   }>;
 };
 
-export type AgentTestDetailsResponse = {
+export type AgentTestResultsResponse = {
   status: TestStatus;
   startTime: string;
   endTime?: string;
@@ -106,7 +105,7 @@ export class AgentTester {
    *
    * @param {string} jobId
    * @param {Duration} timeout
-   * @returns {Promise<AgentTestDetailsResponse>}
+   * @returns {Promise<AgentTestResultsResponse>}
    */
   public async poll(
     jobId: string,
@@ -117,57 +116,63 @@ export class AgentTester {
     } = {
       timeout: Duration.minutes(5),
     }
-  ): Promise<AgentTestDetailsResponse> {
+  ): Promise<AgentTestResultsResponse> {
     const frequency = env.getNumber('SF_AGENT_TEST_POLLING_FREQUENCY_MS', 1000);
     const lifecycle = Lifecycle.getInstance();
     const client = await PollingClient.create({
       poll: async (): Promise<StatusResult> => {
-        // NOTE: we don't actually need to call the status API here since all the same information is present on the
-        // details API. We could just call the details API and check the status there.
-        const [detailsResponse, statusResponse] = await Promise.all([this.details(jobId), this.status(jobId)]);
-        const totalTestCases = detailsResponse.testSet.testCases.length;
-        const failingTestCases = detailsResponse.testSet.testCases.filter((tc) => tc.status === 'ERROR').length;
-        const passingTestCases = detailsResponse.testSet.testCases.filter(
-          (tc) => tc.status === 'COMPLETED' && tc.expectationResults.every((r) => r.result === 'Passed')
-        ).length;
-
-        if (statusResponse.status.toLowerCase() === 'completed') {
+        const statusResponse = await this.status(jobId);
+        if (statusResponse.status.toLowerCase() !== 'new') {
+          const resultsResponse = await this.results(jobId);
+          const totalTestCases = resultsResponse.testSet.testCases.length;
+          const passingTestCases = resultsResponse.testSet.testCases.filter(
+            (tc) => tc.status.toLowerCase() === 'completed' && tc.expectationResults.every((r) => r.result === 'PASS')
+          ).length;
+          const failingTestCases = resultsResponse.testSet.testCases.filter(
+            (tc) =>
+              ['error', 'completed'].includes(tc.status.toLowerCase()) &&
+              tc.expectationResults.some((r) => r.result === 'FAILURE')
+          ).length;
+
+          if (resultsResponse.status.toLowerCase() === 'completed') {
+            await lifecycle.emit('AGENT_TEST_POLLING_EVENT', {
+              jobId,
+              status: resultsResponse.status,
+              totalTestCases,
+              failingTestCases,
+              passingTestCases,
+            });
+            return { payload: resultsResponse, completed: true };
+          }
+
           await lifecycle.emit('AGENT_TEST_POLLING_EVENT', {
             jobId,
-            status: statusResponse.status,
+            status: resultsResponse.status,
             totalTestCases,
             failingTestCases,
             passingTestCases,
           });
-          return { payload: detailsResponse, completed: true };
         }
 
-        await lifecycle.emit('AGENT_TEST_POLLING_EVENT', {
-          jobId,
-          status: statusResponse.status,
-          totalTestCases,
-          failingTestCases,
-          passingTestCases,
-        });
         return { completed: false };
       },
       frequency: Duration.milliseconds(frequency),
       timeout,
     });
 
-    return client.subscribe<AgentTestDetailsResponse>();
+    return client.subscribe<AgentTestResultsResponse>();
   }
 
   /**
    * Request test run details
    *
    * @param {string} jobId
-   * @returns {Promise<AgentTestDetailsResponse>}
+   * @returns {Promise<AgentTestResultsResponse>}
    */
-  public async details(jobId: string): Promise<AgentTestDetailsResponse> {
-    const url = `/einstein/ai-evaluations/runs/${jobId}/details`;
+  public async results(jobId: string): Promise<AgentTestResultsResponse> {
+    const url = `/einstein/ai-evaluations/runs/${jobId}/results`;
 
-    return this.maybeMock.request<AgentTestDetailsResponse>('GET', url);
+    return this.maybeMock.request<AgentTestResultsResponse>('GET', url);
   }
 
   /**
@@ -246,19 +251,38 @@ function makeSimpleTable(data: Record<string, string>, title: string): string {
   return `${title}\n${table}`;
 }
 
-export async function humanFormat(details: AgentTestDetailsResponse): Promise<string> {
+export async function convertTestResultsToFormat(
+  results: AgentTestResultsResponse,
+  format: 'human' | 'json' | 'junit' | 'tap'
+): Promise<string> {
+  switch (format) {
+    case 'human':
+      return humanFormat(results);
+    case 'json':
+      return jsonFormat(results);
+    case 'junit':
+      return junitFormat(results);
+    case 'tap':
+      return tapFormat(results);
+    default:
+      throw new Error(`Unsupported format: ${format as string}`);
+  }
+}
+
+async function humanFormat(details: AgentTestResultsResponse): Promise<string> {
   const { Ux } = await import('@salesforce/sf-plugins-core');
   const ux = new Ux();
 
   const tables: string[] = [];
   for (const testCase of details.testSet.testCases) {
+    const number = details.testSet.testCases.indexOf(testCase) + 1;
     const table = ux.makeTable({
-      title: `${ansis.bold(`Test Case #${testCase.number}`)}\n${ansis.dim('Utterance')}: ${testCase.utterance}`,
+      title: `${ansis.bold(`Test Case #${number}`)}\n${ansis.dim('Utterance')}: ${testCase.utterance}`,
       overflow: 'wrap',
       columns: ['test', 'result', { key: 'expected', width: '40%' }, { key: 'actual', width: '40%' }],
       data: testCase.expectationResults.map((r) => ({
         test: humanFriendlyName(r.name),
-        result: r.result === 'Passed' ? ansis.green('Pass') : ansis.red('Fail'),
+        result: r.result === 'PASS' ? ansis.green('Pass') : ansis.red('Fail'),
         expected: r.expectedValue,
         actual: r.actualValue,
       })),
@@ -269,19 +293,19 @@ export async function humanFormat(details: AgentTestDetailsResponse): Promise<st
 
   const topicPassCount = details.testSet.testCases.reduce((acc, tc) => {
     const topic = tc.expectationResults.find((r) => r.name === 'topic_sequence_match');
-    return topic?.result === 'Passed' ? acc + 1 : acc;
+    return topic?.result === 'PASS' ? acc + 1 : acc;
   }, 0);
   const topicPassPercent = (topicPassCount / details.testSet.testCases.length) * 100;
 
   const actionPassCount = details.testSet.testCases.reduce((acc, tc) => {
     const action = tc.expectationResults.find((r) => r.name === 'action_sequence_match');
-    return action?.result === 'Passed' ? acc + 1 : acc;
+    return action?.result === 'PASS' ? acc + 1 : acc;
   }, 0);
   const actionPassPercent = (actionPassCount / details.testSet.testCases.length) * 100;
 
   const outcomePassCount = details.testSet.testCases.reduce((acc, tc) => {
     const outcome = tc.expectationResults.find((r) => r.name === 'bot_response_rating');
-    return outcome?.result === 'Passed' ? acc + 1 : acc;
+    return outcome?.result === 'PASS' ? acc + 1 : acc;
   }, 0);
   const outcomePassPercent = (outcomePassCount / details.testSet.testCases.length) * 100;
 
@@ -297,12 +321,12 @@ export async function humanFormat(details: AgentTestDetailsResponse): Promise<st
 
   const resultsTable = makeSimpleTable(results, ansis.bold.blue('Test Results'));
 
-  const failedTestCases = details.testSet.testCases.filter((tc) => tc.status === 'ERROR');
+  const failedTestCases = details.testSet.testCases.filter((tc) => tc.status.toLowerCase() === 'error');
   const failedTestCasesObj = Object.fromEntries(
     Object.entries(failedTestCases).map(([, tc]) => [
-      `Test Case #${tc.number}`,
+      `Test Case #${failedTestCases.indexOf(tc) + 1}`,
       tc.expectationResults
-        .filter((r) => r.result === 'Failed')
+        .filter((r) => r.result === 'FAILURE')
         .map((r) => humanFriendlyName(r.name))
         .join(', '),
     ])
@@ -312,11 +336,11 @@ export async function humanFormat(details: AgentTestDetailsResponse): Promise<st
   return tables.join('\n') + `\n${resultsTable}\n\n${failedTestCasesTable}\n`;
 }
 
-export async function jsonFormat(details: AgentTestDetailsResponse): Promise<string> {
-  return Promise.resolve(JSON.stringify(details, null, 2));
+async function jsonFormat(results: AgentTestResultsResponse): Promise<string> {
+  return Promise.resolve(JSON.stringify(results, null, 2));
 }
 
-export async function junitFormat(details: AgentTestDetailsResponse): Promise<string> {
+async function junitFormat(results: AgentTestResultsResponse): Promise<string> {
   // eslint-disable-next-line import/no-extraneous-dependencies
   const { XMLBuilder } = await import('fast-xml-parser');
   const builder = new XMLBuilder({
@@ -325,9 +349,13 @@ export async function junitFormat(details: AgentTestDetailsResponse): Promise<st
     ignoreAttributes: false,
   });
 
-  const testCount = details.testSet.testCases.length;
-  const failureCount = details.testSet.testCases.filter((tc) => tc.status === 'ERROR').length;
-  const time = details.testSet.testCases.reduce((acc, tc) => {
+  const testCount = results.testSet.testCases.length;
+  const failureCount = results.testSet.testCases.filter(
+    (tc) =>
+      ['error', 'completed'].includes(tc.status.toLowerCase()) &&
+      tc.expectationResults.some((r) => r.result === 'FAILURE')
+  ).length;
+  const time = results.testSet.testCases.reduce((acc, tc) => {
     if (tc.endTime && tc.startTime) {
       return acc + new Date(tc.endTime).getTime() - new Date(tc.startTime).getTime();
     }
@@ -336,27 +364,27 @@ export async function junitFormat(details: AgentTestDetailsResponse): Promise<st
 
   const suites = builder.build({
     testsuites: {
-      $name: details.subjectName,
+      $name: results.subjectName,
       $tests: testCount,
       $failures: failureCount,
       $time: time,
       property: [
-        { $name: 'status', $value: details.status },
-        { $name: 'start-time', $value: details.startTime },
-        { $name: 'end-time', $value: details.endTime },
+        { $name: 'status', $value: results.status },
+        { $name: 'start-time', $value: results.startTime },
+        { $name: 'end-time', $value: results.endTime },
       ],
-      testsuite: details.testSet.testCases.map((testCase) => {
+      testsuite: results.testSet.testCases.map((testCase) => {
         const testCaseTime = testCase.endTime
           ? new Date(testCase.endTime).getTime() - new Date(testCase.startTime).getTime()
           : 0;
 
         return {
-          $name: `${details.testSet.name}.${testCase.number}`,
+          $name: `${results.testSet.name}.${results.testSet.testCases.indexOf(testCase) + 1}`,
           $time: testCaseTime,
           $assertions: testCase.expectationResults.length,
           failure: testCase.expectationResults
             .map((r) => {
-              if (r.result === 'Failed') {
+              if (r.result === 'FAILURE') {
                 return { $message: r.errorMessage ?? 'Unknown error', $name: r.name };
               }
             })
@@ -369,14 +397,16 @@ export async function junitFormat(details: AgentTestDetailsResponse): Promise<st
   return `<?xml version="1.0" encoding="UTF-8"?>\n${suites}`.trim();
 }
 
-export async function tapFormat(details: AgentTestDetailsResponse): Promise<string> {
+async function tapFormat(results: AgentTestResultsResponse): Promise<string> {
   const lines: string[] = [];
   let expectationCount = 0;
-  for (const testCase of details.testSet.testCases) {
+  for (const testCase of results.testSet.testCases) {
     for (const result of testCase.expectationResults) {
-      const status = result.result === 'Passed' ? 'ok' : 'not ok';
+      const status = result.result === 'PASS' ? 'ok' : 'not ok';
       expectationCount++;
-      lines.push(`${status} ${expectationCount} ${details.testSet.name}.${testCase.number}`);
+      lines.push(
+        `${status} ${expectationCount} ${results.testSet.name}.${results.testSet.testCases.indexOf(testCase) + 1}`
+      );
       if (status === 'not ok') {
         lines.push('  ---');
         lines.push(`  message: ${result.errorMessage ?? 'Unknown error'}`);
diff --git a/src/index.ts b/src/index.ts
index 5d05bdc..c8fe293 100644
--- a/src/index.ts
+++ b/src/index.ts
@@ -21,11 +21,8 @@ export {
 export { Agent, AgentCreateLifecycleStages } from './agent';
 export {
   AgentTester,
-  humanFormat,
-  jsonFormat,
-  junitFormat,
-  tapFormat,
-  type AgentTestDetailsResponse,
+  convertTestResultsToFormat,
+  type AgentTestResultsResponse,
   type AgentTestStartResponse,
   type AgentTestStatusResponse,
   type TestCaseResult,
diff --git a/src/maybe-mock.ts b/src/maybe-mock.ts
index 1f8d053..602d515 100644
--- a/src/maybe-mock.ts
+++ b/src/maybe-mock.ts
@@ -164,7 +164,7 @@ export class MaybeMock {
     this.logger.debug(`Making ${method} request to ${url}`);
     switch (method) {
       case 'GET':
-        return this.connection.requestGet<T>(url, { retry: { maxRetries: 3 } });
+        return this.connection.requestGet<T>(url, { retry: { maxRetries: 10 } });
       case 'POST':
         if (!body) {
           throw SfError.create({
diff --git a/test/agentTester.test.ts b/test/agentTester.test.ts
index 205a780..1a8ac4b 100644
--- a/test/agentTester.test.ts
+++ b/test/agentTester.test.ts
@@ -8,7 +8,7 @@ import { readFile } from 'node:fs/promises';
 import { expect } from 'chai';
 import { MockTestOrgData, TestContext } from '@salesforce/core/testSetup';
 import { Connection } from '@salesforce/core';
-import { AgentTestDetailsResponse, AgentTester, humanFormat, junitFormat, tapFormat } from '../src/agentTester';
+import { AgentTestResultsResponse, AgentTester, convertTestResultsToFormat } from '../src/agentTester';
 
 describe('AgentTester', () => {
   const $$ = new TestContext();
@@ -45,7 +45,7 @@ describe('AgentTester', () => {
       const output = await tester.status('4KBSM000000003F4AQ');
       expect(output).to.be.ok;
       expect(output).to.deep.equal({
-        status: 'IN_PROGRESS',
+        status: 'InProgress',
         startTime: '2024-11-13T15:00:00.000Z',
       });
     });
@@ -62,11 +62,11 @@ describe('AgentTester', () => {
     });
   });
 
-  describe('details', () => {
-    it('should return details of completed test run', async () => {
+  describe('results', () => {
+    it('should return results of completed test run', async () => {
       const tester = new AgentTester(connection);
       await tester.start('suiteId');
-      const output = await tester.details('4KBSM000000003F4AQ');
+      const output = await tester.results('4KBSM000000003F4AQ');
       // TODO: make this assertion more meaningful
       expect(output).to.be.ok;
     });
@@ -82,23 +82,23 @@ describe('AgentTester', () => {
   });
 });
 
-describe('humanFormat', () => {
+describe('human format', () => {
   it('should transform test results to human readable format', async () => {
-    const raw = await readFile('./test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_details.json', 'utf8');
-    const input = JSON.parse(raw) as AgentTestDetailsResponse;
-    const output = await humanFormat(input);
+    const raw = await readFile('./test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_results.json', 'utf8');
+    const input = JSON.parse(raw) as AgentTestResultsResponse;
+    const output = await convertTestResultsToFormat(input, 'human');
     expect(output).to.be.ok;
   });
 });
 
-describe('junitFormatter', () => {
+describe('junit formatter', () => {
   it('should transform test results to JUnit format', async () => {
-    const raw = await readFile('./test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_details.json', 'utf8');
-    const input = JSON.parse(raw) as AgentTestDetailsResponse;
-    const output = await junitFormat(input);
+    const raw = await readFile('./test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_results.json', 'utf8');
+    const input = JSON.parse(raw) as AgentTestResultsResponse;
+    const output = await convertTestResultsToFormat(input, 'junit');
     expect(output).to.deep.equal(`<?xml version="1.0" encoding="UTF-8"?>
 <testsuites name="Copilot_for_Salesforce" tests="2" failures="1" time="20000">
-  <property name="status" value="COMPLETED"></property>
+  <property name="status" value="Completed"></property>
   <property name="start-time" value="2024-11-28T12:00:00Z"></property>
   <property name="end-time" value="2024-11-28T12:00:48.56Z"></property>
   <testsuite name="CRM_Sanity_v1.1" time="10000" assertions="3"></testsuite>
@@ -110,11 +110,11 @@ describe('junitFormatter', () => {
   });
 });
 
-describe('tapFormatter', () => {
+describe('tap formatter', () => {
   it('should transform test results to TAP format', async () => {
-    const raw = await readFile('./test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_details.json', 'utf8');
-    const input = JSON.parse(raw) as AgentTestDetailsResponse;
-    const output = await tapFormat(input);
+    const raw = await readFile('./test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_results.json', 'utf8');
+    const input = JSON.parse(raw) as AgentTestResultsResponse;
+    const output = await convertTestResultsToFormat(input, 'tap');
     expect(output).to.deep.equal(`Tap Version 14
 1..6
 ok 1 CRM_Sanity_v1.1
diff --git a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/1.json b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/1.json
index daf2bbc..58716da 100644
--- a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/1.json
+++ b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/1.json
@@ -1,4 +1,4 @@
 {
-  "status": "IN_PROGRESS",
+  "status": "InProgress",
   "startTime": "2024-11-13T15:00:00.000Z"
 }
diff --git a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/2.json b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/2.json
index daf2bbc..58716da 100644
--- a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/2.json
+++ b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/2.json
@@ -1,4 +1,4 @@
 {
-  "status": "IN_PROGRESS",
+  "status": "InProgress",
   "startTime": "2024-11-13T15:00:00.000Z"
 }
diff --git a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/3.json b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/3.json
index d4f6503..88bd062 100644
--- a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/3.json
+++ b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ/3.json
@@ -1,4 +1,4 @@
 {
-  "status": "COMPLETED",
+  "status": "Completed",
   "startTime": "2024-11-13T15:00:00.000Z"
 }
diff --git a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_details.json b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_results.json
similarity index 94%
rename from test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_details.json
rename to test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_results.json
index b84e3ed..704b480 100644
--- a/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_details.json
+++ b/test/mocks/einstein_ai-evaluations_runs_4KBSM000000003F4AQ_results.json
@@ -1,5 +1,5 @@
 {
-  "status": "COMPLETED",
+  "status": "Completed",
   "startTime": "2024-11-28T12:00:00Z",
   "endTime": "2024-11-28T12:00:48.56Z",
   "errorMessage": null,
@@ -9,7 +9,6 @@
     "testCases": [
       {
         "status": "COMPLETED",
-        "number": 1,
         "utterance": "Summarize account Acme",
         "startTime": "2024-11-28T12:00:10Z",
         "endTime": "2024-11-28T12:00:20Z",
@@ -27,7 +26,7 @@
             "actualValue": "GeneralCRM",
             "expectedValue": "GeneralCRM",
             "score": 1.0,
-            "result": "Passed",
+            "result": "PASS",
             "metricLabel": "Accuracy",
             "metricExplainability": "Measures the correctness of the result.",
             "status": "Completed",
@@ -41,7 +40,7 @@
             "actualValue": "[\"IdentifyRecordByName\",\"SummarizeRecord\"]",
             "expectedValue": "[\"IdentifyRecordByName\",\"SummarizeRecord\"]",
             "score": 1.0,
-            "result": "Passed",
+            "result": "PASS",
             "metricLabel": "Precision",
             "metricExplainability": "Measures the precision of the result.",
             "status": "Completed",
@@ -55,7 +54,7 @@
             "actualValue": "Here is the summary of the account Acme. How else can I assist you? Acme is a customer since 2019. They have 3 open opportunities and 2 open cases.",
             "expectedValue": "Summary of account details are shown",
             "score": 0.9,
-            "result": "Passed",
+            "result": "PASS",
             "metricLabel": "Precision",
             "metricExplainability": "Measures the precision of the result.",
             "status": "Completed",
@@ -67,8 +66,7 @@
         ]
       },
       {
-        "status": "ERROR",
-        "number": 2,
+        "status": "COMPLETED",
         "startTime": "2024-11-28T12:00:30Z",
         "utterance": "Summarize the open cases and Activities of acme from sep to nov 2024",
         "endTime": "2024-11-28T12:00:40Z",
@@ -86,7 +84,7 @@
             "actualValue": "GeneralCRM",
             "expectedValue": "GeneralCRM",
             "score": 1,
-            "result": "Passed",
+            "result": "PASS",
             "metricLabel": "Accuracy",
             "metricExplainability": "Measures the correctness of the result.",
             "status": "Completed",
@@ -100,7 +98,7 @@
             "actualValue": "[\"IdentifyRecordByName\",\"QueryRecords\"]",
             "expectedValue": "[\"IdentifyRecordByName\",\"QueryRecords\",\"GetActivitiesTimeline\"]",
             "score": 0.5,
-            "result": "Failed",
+            "result": "FAILURE",
             "metricLabel": "Precision",
             "metricExplainability": "Measures the precision of the result.",
             "status": "Completed",
@@ -114,7 +112,7 @@
             "actualValue": "It looks like I am unable to find the information you are looking for due to access restrictions. How else can I assist you?",
             "expectedValue": "Summary of open cases and activities associated with timeline",
             "score": 0.1,
-            "result": "Failed",
+            "result": "FAILURE",
             "metricLabel": "Precision",
             "metricExplainability": "Measures the precision of the result.",
             "status": "Completed",