# US 2026/0300755 A1 · Process and ai agent optimization for agentic automation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0300755 A1
- Document ID: US20260300755A1
- Status: Published application
- Kind: A1
- Application number: 19/094,509
- Filed: 2025-03-28
- Published: 2026-10-01
- Earliest claimed: 2025-03-28
- Assignees: UiPath, Inc.
- Applicants: UiPath, Inc.
- Inventors: Raja Charu Vikram KAKUMANI; Gong ZHANG; Salvatore NUZIALE
- Web page: https://patentgrep.com/patent/US20260300755A1

## CPC

- G06N 3/10: Interfaces, programming languages or software development kits, e.g. for simulating neural networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for optimizing at least one of a process or an AI (artificial intelligence) agent are provided. The process and the AI agent are executed on one or more computing systems for performing a task. A visual representation of the execution of the process and the AI agent is generated. At least one of the process or the AI agent is optimized based on the visual representation. The optimized at least one of the process or the AI agent is output.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving execution data of a process executing on one or more computing systems for performing a task, the process comprising one or more activities executed by one or more AI (artificial intelligence) agents;
generating a visual representation of the execution of the process and the one or more AI agents based on the execution data;
optimizing at least one of the process or the one or more AI agents based on the visual representation; and
outputting the optimized at least one of the process or the one or more AI agents.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises:
optimizing the at least one of the process or the one or more AI agents using an optimization agent, the optimization agent receiving as input the visual representation and generating as output one or more actions for optimizing the at least one of the process or the one or more AI agents.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein optimizing the at least one of the process or the one or more AI agents using an optimization agent comprises:
performing the one or more actions by the optimization agent to optimize the at least one of the process or the one or more AI agents.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein the optimization agent further receives as input one or more of errors, logs, documentation, or conversations between users.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises:
presenting a step-by-step visual representation of the execution of the process or the one or more AI agents to a user via a display device; and
receiving input from the user debugging the at least one of the process or the AI agent based on the presentation of the step-by-step visual representation.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein generating a visual representation of the execution of the process and the one or more AI agents comprises:
generating a BPMN (business process model and notation) model of the execution of the process and the one or more AI agents.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the process comprises one or more RPA (robotic process automation) activities executed by one or more RPA robots executing on the one or more computing systems.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more AI agents comprise at least one of a native AI agent designed and executed on native systems, a third-party AI agent designed by a third party and executed on the native systems, or a third-party AI agent designed by a third party and executed on third-party systems.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises at least one of:
debugging the at least one of the process or the one or more AI agents;
updating variables of the at least one of the process or the one or more AI agents;
inserting a retry operation to retry an activity in the at least one of the process or the one or more AI agents;
inserting a goto operation to skip the execution of the process to a later point in the process;
pausing, resuming, canceling, or terminating the execution of the at least one of the process or the one or more AI agents; or
applying an upgrade operation to the at least one of the process or the one or more AI agents.

### Claim 10

A system comprising:
at least one processor; and
a memory storing computer instructions, which when executed by the at least one processor, cause the system to perform operations comprising:
receiving execution data of a process executing on one or more computing systems for performing a task, the process comprising one or more activities executed by one or more AI (artificial intelligence) agents;
generating a visual representation of the execution of the process and the one or more AI agents based on the execution data;
optimizing at least one of the process or the one or more AI agents based on the visual representation; and
outputting the optimized at least one of the process or the one or more AI agents.

### Claim 11 (depends on 10)

The system of claim 10, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises:
optimizing the at least one of the process or the AI agent using an optimization agent, the optimization agent receiving as input the visual representation and generating as output one or more actions for optimizing the at least one of the process or the AI agent.

### Claim 12 (depends on 11)

The system of claim 11, wherein optimizing the at least one of the process or the AI agent using an optimization agent comprises:
performing the one or more actions by the optimization agent to optimize the at least one of the process or the AI agent.

### Claim 13 (depends on 11)

The system of claim 11, wherein the optimization agent further receives as input one or more of errors, logs, documentation, or conversations between users.

### Claim 14 (depends on 10)

The system of claim 10, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises:
presenting a step-by-step visual representation of the execution of the process or the one or more AI agents to a user via a display device; and
receiving input from the user debugging the at least one of the process or the AI agent based on the presentation of the step-by-step visual representation.

### Claim 15

A non-transitory computer-readable medium storing computer program instructions, when executed on at least one processor, cause the at least one processor to perform operations comprising:
receiving execution data of a process executing on one or more computing systems for performing a task, the process comprising one or more activities executed by one or more AI (artificial intelligence) agents;
generating a visual representation of the execution of the process and the one or more AI agents based on the execution data;
optimizing at least one of the process or the one or more AI agents based on the visual representation; and
outputting the optimized at least one of the process or the one or more AI agents.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises:
optimizing the at least one of the process or the one or more AI agents using an optimization agent, the optimization agent receiving as input the visual representation and generating as output one or more actions for optimizing the at least one of the process or the AI agent.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein generating a visual representation of the execution of the process and the one or more AI agents comprises:
generating a BPMN (business process model and notation) model of the execution of the process and the one or more AI agents.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the process comprises one or more RPA (robotic process automation) activities executed by one or more RPA robots executing on the one or more computing systems.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more AI agents comprise at least one of a native AI agent designed and executed on native systems, a third-party AI agent designed by a third party and executed on the native systems, or a third-party AI agent designed by a third party and executed on third-party systems.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein optimizing at least one of the process or the one or more AI agents based on the visual representation comprises at least one of:
debugging the at least one of the process or the one or more AI agents;
updating variables of the at least one of the process or the one or more AI agents;
inserting a retry operation to retry an activity in the at least one of the process or the one or more AI agents;
inserting a goto operation to skip the execution of the process to a later point in the process;
pausing, resuming, canceling, or terminating the execution of the at least one of the process or the one or more AI agents; or
applying an upgrade operation to the at least one of the process or the one or more AI agents.
