# US 2026/0094052 A1 · Artificial intelligence powered workload sizing for generative artificial intelligence authoring systems > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0094052 A1 - Document ID: US20260094052A1 - Status: Published application - Kind: A1 - Application number: 18/901,689 - Filed: 2024-09-30 - Published: 2026-04-02 - Earliest claimed: 2024-09-30 - Assignees: Intuit Inc. - Applicants: Intuit Inc. - Inventors: Ronnie Douglas DOUTHIT; Deepankar MOHAPATRA - Web page: https://patentgrep.com/patent/US20260094052A1 ## CPC - G06N 20/00: Machine learning - G06N 3/0475: Generative networks - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Aspects of the present disclosure relate to automatically generating artifacts. Embodiments include providing, to a machine learning model, an indication of a generative machine learning model, an indication of a type of an artifact, and an indication of a position, wherein the machine learning model is trained to predict a size for the segment of the artifact that is compliant with an input limit or a processing capacity of the generative machine learning model. Embodiments further include providing a segment of an artifact template to the generative machine learning model along with a prompt instructing the generative machine learning model to generate the segment of the artifact with the size predicted by the machine learning. Embodiments further include receiving, from the generative machine learning model, the segment of the artifact based on the segment of the artifact template and the prompt. ## Claims ### Claim 1 A method of automatically generating artifacts, comprising: providing, to a machine learning model, an indication of a generative machine learning model, an indication of a type of an artifact, and an indication of a position within the artifact of a segment of the artifact that is to be generated by the generative machine learning model, wherein the machine learning model is trained to predict a size for the segment of the artifact that is compliant with an input limit or a processing capacity of the generative machine learning model; providing a segment of an artifact template to the generative machine learning model along with a prompt instructing the generative machine learning model to generate the segment of the artifact with the size predicted by the machine learning model, wherein: the generative machine learning model has been trained to generate artifacts based on artifact templates; and the artifact template corresponds to the indicated type of the artifact; and receiving, from the generative machine learning model, the segment of the artifact based on the segment of the artifact template and the prompt. ### Claim 2 (depends on 1) The method of claim 1, further comprising generating a complete artifact based on generating multiple artifact segments. ### Claim 3 (depends on 1) The method of claim 1, wherein an additional segment of the artifact is generated based on retrieving an additional segment of the artifact template, wherein the additional segment of the artifact template is retrieved based on the size of the segment of the artifact. ### Claim 4 (depends on 1) The method of claim 1, wherein generating a given segment of the artifact fails due to a capacity of the generative machine learning model being exceeded, wherein an additional machine learning model generates an output indicating a new size for the given segment of the artifact based on results of previous attempts to generate segments of the artifact. ### Claim 5 (depends on 1) The method of claim 1, wherein the machine learning model predicts the size based on a day or time associated with generating the segment of the artifact. ### Claim 6 (depends on 1) The method of claim 1, wherein the machine learning model is trained based on historical usage data associated with the generative machine learning model. ### Claim 7 (depends on 1) The method of claim 1, wherein the input limit comprises a token limit for the generative machine learning model. ### Claim 8 (depends on 1) The method of claim 1, wherein the processing capacity comprises a usage limit for the generative machine learning model. ### Claim 9 (depends on 1) The method of claim 1, wherein a prompt generation machine learning model is trained to generate a prompt based on information associated with the segment of the artifact template that is retrieved from one or more data sources, wherein the prompt is provided to the generative machine learning model. ### Claim 10 (depends on 1) The method of claim 1, wherein a model selection machine learning model is trained to select a type of generative machine learning model based on an indicated level of complexity associated with an artifact, wherein the type of generative model is used to generate a segment of the artifact. ### Claim 11 A system for automatically generating artifacts, comprising: one or more processors; and a memory comprising instructions that, when executed by the one or more processors, cause the system to: provide, to a machine learning model, an indication of a generative machine learning model, an indication of a type of an artifact, and an indication of a position within the artifact of a segment of the artifact that is to be generated by the generative machine learning model, wherein the machine learning model is trained to predict a size for the segment of the artifact that is compliant with an input limit or a processing capacity of the generative machine learning model; provide a segment of an artifact template to the generative machine learning model along with a prompt instructing the generative machine learning model to generate the segment of the artifact with the size predicted by the machine learning model, wherein: the generative machine learning model has been trained to generate artifacts based on artifact templates; and the artifact template corresponds to the indicated type of the artifact; and receive, from the generative machine learning model, the segment of the artifact based on the segment of the artifact template and the prompt. ### Claim 12 (depends on 11) The system of claim 11, wherein the instructions further cause the system to generate a complete artifact based on generating multiple artifact segments. ### Claim 13 (depends on 11) The system of claim 11, wherein the instructions further cause the system to generate an additional segment of the artifact based on retrieving an additional segment of the artifact template, wherein the additional segment of the artifact template is retrieved based on the size of the segment of the artifact. ### Claim 14 (depends on 11) The system of claim 11, generating a given segment of the artifact fails due to a capacity of the generative machine learning model being exceeded, wherein an additional machine learning model generates an output indicating a new size for the given segment of the artifact based on results of previous attempts to generate segments of the artifact. ### Claim 15 (depends on 11) The system of claim 11, wherein the machine learning model predicts the size based on a day or time associated with generating the segment of the artifact. ### Claim 16 (depends on 11) The system of claim 11, wherein the machine learning model is trained based on historical usage data associated with the generative machine learning model. ### Claim 17 (depends on 11) The system of claim 11, wherein the input limit comprises a token limit for the generative machine learning model. ### Claim 18 (depends on 11) The system of claim 11, wherein the processing capacity comprises a usage limit for the generative machine learning model. ### Claim 19 (depends on 11) The system of claim 11, wherein a prompt generation machine learning model is trained to generate a prompt based on information associated with the segment of the artifact template that is retrieved from one or more data sources, wherein the prompt is provided to the generative machine learning model. ### Claim 20 (depends on 11) The system of claim 11, wherein a model selection machine learning model is trained to select a type of generative machine learning model based on an indicated level of complexity associated with an artifact, wherein the type of generative model is used to generate a segment of the artifact.