> ## Documentation Index > Fetch the complete documentation index at: https://docs.revring.ai/llms.txt > Use this file to discover all available pages before exploring further. # Suggest a Fix for a Run > Ask for one prompt change that would make every failed test in a run pass. Requesting a fix per attempt produces separate prompts that do not know about each other, and applying one can undo another. This endpoint analyzes all of the run's failed attempts together and returns a single corrected prompt with a per-attempt breakdown, so failures that share a root cause get one coherent edit. The wait, polling, and reuse behavior is identical to the per-attempt Suggest a Fix: the request waits up to 105 seconds, `wait=0` returns `status: running` immediately for polling with Get Suggested Fix for a Run, asking again joins a preparation already in progress, and a suggestion prepared within the last 10 minutes is returned instantly. The run must be finished and must contain at least one failed attempt. On runs with more than 12 failures, the most recent 12 are analyzed and the rest are listed in `result.skippedAttemptIds`. ## OpenAPI ````yaml POST /test-suites/{id}/runs/{runId}/suggest-fix openapi: 3.1.0 info: title: RevRing Voice AI API description: >- RevRing Voice AI platform API for managing AI voice agents, phone calls, SIP trunks, and analytics. Build intelligent voice applications that can handle inbound and outbound phone calls with AI-powered conversational agents. version: 1.0.0 contact: name: RevRing Support url: https://revring.ai servers: - url: https://api.revring.ai/v1 description: Production API security: - apiKeyAuth: [] tags: - name: Messaging Connections description: Connect messaging providers so agents can send text messages - name: Messages description: Send text messages and read your message log - name: Conversations description: List and clear managed conversation threads - name: SIP Trunks description: Manage SIP trunks for connecting agents to the phone network - name: Agents description: Manage AI voice agents and their configuration - name: Agent Folders description: Organize agents into folders for dashboard navigation - name: Calls description: Manage and query phone calls - name: Analytics description: Get analytics and metrics about your calls - name: Knowledge Bases description: >- Manage knowledge bases and sources for agent retrieval-augmented generation - name: Test Suites description: Manage test suites, test cases, and test runs for agent evaluation - name: Voices description: Browse the voices available to your organization for agent speech paths: /test-suites/{id}/runs/{runId}/suggest-fix: parameters: - name: id in: path required: true description: Test suite ID schema: type: string format: uuid - name: runId in: path required: true description: Test run ID schema: type: string format: uuid post: tags: - Test Suites summary: Suggest a Fix for a Run description: >- Ask for one prompt change that would make every failed test in a run pass. Requesting a fix per attempt produces separate prompts that do not know about each other, and applying one can undo another. This endpoint analyzes all of the run's failed attempts together and returns a single corrected prompt with a per-attempt breakdown, so failures that share a root cause get one coherent edit. The wait, polling, and reuse behavior is identical to the per-attempt Suggest a Fix: the request waits up to 105 seconds, `wait=0` returns `status: running` immediately for polling with Get Suggested Fix for a Run, asking again joins a preparation already in progress, and a suggestion prepared within the last 10 minutes is returned instantly. The run must be finished and must contain at least one failed attempt. On runs with more than 12 failures, the most recent 12 are analyzed and the rest are listed in `result.skippedAttemptIds`. operationId: suggestRunFix parameters: - name: wait in: query required: false description: >- Set to `0` to return immediately instead of waiting for the suggestion. schema: type: string enum: - '0' responses: '200': description: >- The suggestion, when it was ready in time. The suggestion fields are also present at the top level of `data`. content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/RunSuggestedFix' '202': description: >- The suggestion is being prepared. Poll Get Suggested Fix for a Run until `status` is `ready`. content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/RunSuggestedFix' '400': description: >- The run has not finished yet, or it has no failed attempts to analyze '401': $ref: '#/components/responses/UnauthorizedError' '404': $ref: '#/components/responses/NotFoundError' components: schemas: RunSuggestedFix: type: object description: A proposed prompt change covering every failed attempt in a test run. properties: status: type: string enum: - idle - running - ready - failed description: >- `idle` = none requested for this run. `running` = being prepared. `ready` = `result` holds the suggestion. `failed` = could not be prepared, request another. result: type: object nullable: true description: The suggestion. Present when `status` is `ready`, otherwise null. properties: analysis: type: string description: >- Overall diagnosis across the run's failures, leading with a shared root cause when there is one changesSummary: type: array items: type: string description: Plain-language summary of what was changed suggestedPrompt: type: string description: The complete corrected prompt, ready to save to the agent currentPrompt: type: string description: >- The agent prompt the suggestion was written against, for comparison rubricIssues: type: array items: type: string description: Problems found in the test's pass criteria, if any perAttempt: type: array description: >- One entry per failed attempt analyzed, in the order the attempts ran items: type: object properties: attemptId: type: string description: The failed attempt testCaseName: type: string description: Name of the test that failed analysis: type: string description: >- Why this test failed and which part of the edit addresses it skippedAttemptIds: type: array items: type: string description: >- Present only on very large runs: the oldest failed attempts beyond the most recent 12, which were not analyzed stale: type: boolean description: >- Present when `status` is `ready`. `true` means the agent's prompt has changed since this suggestion was written, so saving `suggestedPrompt` would overwrite those newer edits; request a fresh suggestion instead. responses: UnauthorizedError: description: Authentication required or API key invalid content: application/json: schema: type: object properties: error: type: string example: unauthorized NotFoundError: description: Resource not found content: application/json: schema: type: object properties: error: type: string example: not_found securitySchemes: apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key for authentication. Generate API keys from the RevRing dashboard. ````