> ## Documentation Index > Fetch the complete documentation index at: https://docs.costgraph.ai/llms.txt > Use this file to discover all available pages before exploring further. # Ask an agent to rewrite a tag key's rules > Queues one costgraph-ai run that rewrites the rules under the given tag keys. A tenant runs one proposal at a time, so a request made while a run is in flight answers that run rather than starting a second one, from each key's description, the saved suggestion context and the billing fields the tenant actually has spend on. Pass one key_id to recompile a single key. guidance is layered on top of each key's description rather than replacing it, unless the key has no description, in which case it becomes the whole brief. The run is asynchronous and writes nothing to any key: poll it with the returned id, and on done read the new suggestion group of kind regenerate from /virtual-tag-suggestions, which a person applies or ignores. Rules a person wrote by hand are never proposed over and never removed. Repeat presses for the same key set inside the same minute collapse into the run already in flight, which is what queued=false reports; the id still points at that run. ## OpenAPI ````yaml /api-reference/costgraph/openapi.json post /api/v1/tenant/virtual-tag-regenerations openapi: 3.0.0 info: description: Read and manage your CostGraph organization, spend, alerts, and settings. title: CostGraph API contact: {} version: '1.0' servers: - url: https://api.costgraph.ai security: [] tags: - name: ai x-group: AI - name: ai-serving x-group: AI serving - name: anomalies x-group: Anomalies - name: auth x-group: Auth - name: billing x-group: Billing - name: billing-export x-group: Billing export - name: budgets x-group: Budgets - name: ci x-group: CI - name: compute-recommendations x-group: Compute recommendations - name: config x-group: Config - name: cost x-group: Cost - name: gpus x-group: GPUs - name: graphai x-group: Graph AI - name: infracost x-group: Infracost - name: integrations x-group: Integrations - name: invitations x-group: Invitations - name: kubernetes-clusters x-group: Kubernetes clusters - name: marketplace x-group: Marketplace - name: network-requests x-group: Network requests - name: notifications x-group: Notifications - name: oauth x-group: OAuth - name: oauth-clients x-group: OAuth clients - name: opencost x-group: OpenCost - name: organization x-group: Audit log - name: organizations x-group: Organizations - name: placement-alternatives x-group: Placement alternatives - name: reports x-group: Reports - name: service-map x-group: Service map - name: settings x-group: Settings - name: sso x-group: Single sign-on - name: tenants x-group: Tenants - name: user x-group: Users - name: virtual-machines x-group: Virtual machines - name: virtual-tags x-group: Virtual tags - name: workflows x-group: Workflows paths: /api/v1/tenant/virtual-tag-regenerations: post: tags: - virtual-tags summary: Ask an agent to rewrite a tag key's rules description: >- Queues one costgraph-ai run that rewrites the rules under the given tag keys. A tenant runs one proposal at a time, so a request made while a run is in flight answers that run rather than starting a second one, from each key's description, the saved suggestion context and the billing fields the tenant actually has spend on. Pass one key_id to recompile a single key. guidance is layered on top of each key's description rather than replacing it, unless the key has no description, in which case it becomes the whole brief. The run is asynchronous and writes nothing to any key: poll it with the returned id, and on done read the new suggestion group of kind regenerate from /virtual-tag-suggestions, which a person applies or ignores. Rules a person wrote by hand are never proposed over and never removed. Repeat presses for the same key set inside the same minute collapse into the run already in flight, which is what queued=false reports; the id still points at that run. parameters: - description: Tenant ID name: X-CostGraph-Tenant-ID in: header required: true schema: type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/virtualtag.RegenerateKeysRequest' description: Tag keys to rewrite required: true responses: '202': description: Accepted content: application/json: schema: allOf: - $ref: '#/components/schemas/responses.SuccessResponse' - type: object properties: data: $ref: '#/components/schemas/virtualtag.RegenerationRun' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/responses.ErrorResponse' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/responses.ErrorResponse' security: - BearerAuth: [] components: schemas: virtualtag.RegenerateKeysRequest: type: object properties: guidance: type: string key_ids: type: array items: type: string responses.SuccessResponse: type: object required: - message - status properties: data: {} message: type: string example: some message status: type: string example: success virtualtag.RegenerationRun: type: object properties: id: type: string keys: type: array items: type: string queued: type: boolean responses.ErrorResponse: type: object required: - message - status properties: message: type: string example: some message status: type: string example: error securitySchemes: BearerAuth: description: Enter "Bearer {token}" type: apiKey name: Authorization in: header ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.