> ## Documentation Index > Fetch the complete documentation index at: https://platform.atlan.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write. > The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects. > SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript. > These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces. # Dismiss an improvement run's proposals ## OpenAPI ````yaml /public-openapi.json post /eval/v1/improvements/{improvement_id}/dismiss openapi: 3.1.0 info: title: Atlan public API version: current description: >- Public HTTP API reference for Registry, Skills, Agents, outputs, files, MCP servers and tools, and OTLP telemetry ingestion. servers: - url: https://api.atlan.com description: Atlan API base URL security: - bearer: [] tags: - name: Core - name: Skill - name: Agent - name: Files - name: Knowledge - name: MCP - name: Observability - name: API proxy - name: Credentials - name: Store - name: Apps - name: Evals - name: Ontologies - name: Ontology bindings - name: Slack - name: GitHub - name: Objectives - name: Repositories paths: /eval/v1/improvements/{improvement_id}/dismiss: post: tags: - Evals summary: Dismiss an improvement run's proposals operationId: eval.dismissImprovement parameters: - name: improvement_id in: path required: true schema: type: string responses: '200': content: application/json: schema: $ref: '#/components/schemas/eval-eval-Improvement' description: HTTP 200 response. '401': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - alg_mismatch - alg_not_allowed - audience_mismatch - invalid_api_key - missing_identity - missing_org - missing_user - signature_invalid - token_expired - token_malformed - token_missing - token_not_yet_valid - token_rejected - token_service_account_unbound - unauthorized - unknown_account - unknown_key - untrusted_issuer description: HTTP 401 response. '403': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - access_denied - account_suspended - forbidden - platform_principal_refused description: HTTP 403 response. '404': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - not_found description: HTTP 404 response. '409': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - improvement_not_actionable description: HTTP 409 response. '500': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - internal_error description: HTTP 500 response. '503': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - auth_unavailable - service_overloaded - workspace_authorization_unavailable description: HTTP 503 response. '504': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - request_timeout description: HTTP 504 response. security: - bearer: [] components: schemas: eval-eval-Improvement: type: object required: - improvement_id - subject_kind - subject_id - base_version_ordinal - base_content_hash - status - params - can_apply - requested_by - created_at - updated_at properties: base_content_hash: type: string base_version_ordinal: type: integer format: int64 can_apply: type: boolean changes: type: - array - 'null' items: $ref: '#/components/schemas/eval-eval-ImprovementChange' created_at: type: string decision: type: - object - 'null' improvement_id: type: string params: $ref: '#/components/schemas/eval-eval-ImprovementParams' profile: oneOf: - $ref: '#/components/schemas/eval-eval-ImprovementProfile' - type: 'null' progress: oneOf: - $ref: '#/components/schemas/eval-eval-ImprovementProgress' - type: 'null' readiness: type: - object - 'null' requested_by: type: string run_id: type: - string - 'null' scorer_id: type: - string - 'null' scorer_version: type: - integer - 'null' format: int64 status: $ref: '#/components/schemas/eval-eval-ImprovementStatus' status_reason: type: - string - 'null' subject_id: type: string subject_kind: $ref: '#/components/schemas/eval-eval-ImprovementSubjectKind' summary: oneOf: - $ref: '#/components/schemas/eval-eval-ImprovementSummary' - type: 'null' updated_at: type: string eval-ProblemDetails: type: object required: - title - status - detail - code properties: code: type: string detail: type: string status: type: integer format: int32 minimum: 0 title: type: string trace_id: type: - string - 'null' eval-eval-ImprovementChange: type: object required: - id - op - block_id - base_sha256 - kind - rationale - evidence - diff properties: base_sha256: type: string base_text: type: - string - 'null' block_id: type: string diff: type: string evidence: $ref: '#/components/schemas/eval-eval-ImprovementChangeEvidence' id: type: string kind: $ref: '#/components/schemas/eval-eval-ImprovementChangeKind' op: $ref: '#/components/schemas/eval-eval-ImprovementBlockOp' rationale: type: string eval-eval-ImprovementParams: type: object required: - window_days - max_evidence properties: max_evidence: type: integer format: int32 minimum: 0 window_days: type: integer format: int32 minimum: 0 eval-eval-ImprovementProfile: type: object required: - kind_type - output_type - intended_use - success_criteria - out_of_scope properties: intended_use: type: string kind_type: type: string out_of_scope: type: array items: type: string output_type: $ref: '#/components/schemas/eval-eval-ImprovementProfileOutputType' success_criteria: type: array items: type: string additionalProperties: false eval-eval-ImprovementProgress: type: object required: - done - total - deadline_hit properties: deadline_hit: type: boolean done: type: integer format: int32 minimum: 0 total: type: integer format: int32 minimum: 0 eval-eval-ImprovementStatus: type: string enum: - queued - profiling - judging - proposing - ready - not_enough_evidence - failed - accepting - accepted - dismissed eval-eval-ImprovementSubjectKind: type: string enum: - skill - agent - harness - mcp eval-eval-ImprovementSummary: type: object required: - window_days - listed_count - judged_count - excluded - by_family - workspace_count - axes - outcomes - criteria - blocks - judge - top_findings properties: axes: $ref: '#/components/schemas/eval-eval-ImprovementAxes' default: efficiency: score: 0 run_count: 0 compliance: score: 0 run_count: 0 verbosity: score: 0 run_count: 0 code_quality: score: 0 run_count: 0 blocks: type: array items: $ref: '#/components/schemas/eval-eval-ImprovementBlockSummary' default: [] by_family: type: object default: {} additionalProperties: $ref: '#/components/schemas/eval-eval-ImprovementFamilySummary' propertyNames: type: string criteria: type: array items: $ref: '#/components/schemas/eval-eval-ImprovementCriterionSummary' default: [] excluded: $ref: '#/components/schemas/eval-eval-ImprovementSummaryExcluded' default: misattributed_count: 0 subject_not_found_count: 0 structure_only_count: 0 fetch_failed_count: 0 judge: $ref: '#/components/schemas/eval-eval-ImprovementJudgeSummary' default: request_count: 0 input_tokens: 0 judged_count: type: integer format: int32 default: 0 minimum: 0 listed_count: type: integer format: int32 default: 0 minimum: 0 outcomes: $ref: '#/components/schemas/eval-eval-ImprovementOutcomes' default: follow_up_run_count: 0 top_findings: type: array items: type: string default: [] window_days: type: integer format: int32 default: 0 minimum: 0 workspace_count: type: integer format: int32 default: 0 minimum: 0 eval-eval-ImprovementChangeEvidence: type: object properties: by_family: type: object additionalProperties: $ref: '#/components/schemas/eval-eval-ImprovementFamilyEvidence' propertyNames: type: string confidence_p50: type: - number - 'null' format: double other_run_count: type: - integer - 'null' format: int32 minimum: 0 run_count: type: integer format: int32 minimum: 0 verdicts: type: object additionalProperties: type: integer format: int32 minimum: 0 propertyNames: type: string viewer_trace_ids: type: - array - 'null' items: type: string workspace_count: type: integer format: int32 minimum: 0 eval-eval-ImprovementChangeKind: type: string enum: - hurt - misrouted - criterion_failed - skipped eval-eval-ImprovementBlockOp: oneOf: - type: object required: - id - text - op properties: id: type: string op: type: string enum: - replace_block text: type: string - type: object required: - id - heading - text - op properties: heading: type: string id: type: string op: type: string enum: - insert_after text: type: string - type: object required: - id - op properties: id: type: string op: type: string enum: - delete_block - type: object required: - text - op properties: op: type: string enum: - replace_description text: type: string eval-eval-ImprovementProfileOutputType: type: string enum: - code_change - document - structured_data - answer - external_action - none eval-eval-ImprovementAxes: type: object required: - efficiency - compliance - verbosity - code_quality properties: code_quality: $ref: '#/components/schemas/eval-eval-ImprovementAxis' default: score: 0 run_count: 0 compliance: $ref: '#/components/schemas/eval-eval-ImprovementAxis' default: score: 0 run_count: 0 efficiency: $ref: '#/components/schemas/eval-eval-ImprovementAxis' default: score: 0 run_count: 0 verbosity: $ref: '#/components/schemas/eval-eval-ImprovementAxis' default: score: 0 run_count: 0 eval-eval-ImprovementBlockSummary: allOf: - $ref: '#/components/schemas/eval-eval-ImprovementBlockCounts' - type: object required: - block_id - heading - by_family properties: block_id: type: string by_family: type: object additionalProperties: $ref: '#/components/schemas/eval-eval-ImprovementBlockCounts' propertyNames: type: string heading: type: string eval-eval-ImprovementFamilySummary: type: object required: - judged_count - axes - outcomes properties: axes: $ref: '#/components/schemas/eval-eval-ImprovementAxes' default: efficiency: score: 0 run_count: 0 compliance: score: 0 run_count: 0 verbosity: score: 0 run_count: 0 code_quality: score: 0 run_count: 0 judged_count: type: integer format: int32 default: 0 minimum: 0 outcomes: $ref: '#/components/schemas/eval-eval-ImprovementOutcomes' default: follow_up_run_count: 0 eval-eval-ImprovementCriterionSummary: type: object required: - text - run_count properties: pass_rate: type: - number - 'null' format: double run_count: type: integer format: int32 minimum: 0 text: type: string eval-eval-ImprovementSummaryExcluded: type: object required: - misattributed_count - subject_not_found_count - structure_only_count - fetch_failed_count properties: fetch_failed_count: type: integer format: int32 default: 0 minimum: 0 misattributed_count: type: integer format: int32 default: 0 minimum: 0 structure_only_count: type: integer format: int32 default: 0 minimum: 0 subject_not_found_count: type: integer format: int32 default: 0 minimum: 0 eval-eval-ImprovementJudgeSummary: type: object required: - request_count - input_tokens properties: input_tokens: type: integer format: int64 default: 0 minimum: 0 p50_ms: type: - integer - 'null' format: int64 default: null minimum: 0 request_count: type: integer format: int32 default: 0 minimum: 0 eval-eval-ImprovementOutcomes: type: object required: - follow_up_run_count properties: correct_invocation_rate: type: - number - 'null' format: double default: null follow_up_run_count: type: integer format: int32 default: 0 minimum: 0 goal_rate: type: - number - 'null' format: double default: null user_corrected_rate: type: - number - 'null' format: double default: null eval-eval-ImprovementFamilyEvidence: type: object required: - run_count - hit_count properties: hit_count: type: integer format: int32 minimum: 0 run_count: type: integer format: int32 minimum: 0 eval-eval-ImprovementAxis: type: object required: - score - run_count properties: raw: type: - number - 'null' format: double default: null run_count: type: integer format: int32 default: 0 minimum: 0 score: type: number format: double default: 0 eval-eval-ImprovementBlockCounts: type: object required: - followed - hurt - skipped - not_applicable - uncertain properties: followed: type: integer format: int32 default: 0 minimum: 0 hurt: type: integer format: int32 default: 0 minimum: 0 not_applicable: type: integer format: int32 default: 0 minimum: 0 skipped: type: integer format: int32 default: 0 minimum: 0 uncertain: type: integer format: int32 default: 0 minimum: 0 securitySchemes: bearer: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.