Affirm, Inc.

Manhattan Engineering Incorporated

Daniel Hung

Adam Douglas Smith

Juan Lozano

Tarak Upadhyaya

A system and method may provide assistance to programmers during programming to reduce the number of routine tasks that must be performed. In some aspects, the system may provide for searching a corpus of source code based on keyword or natural language search input. Search results including code entities and snippets of code that are described by the search input are then provided as search results. Some embodiments relate to using a neural network encoder to generate tensor embeddings of source code and related text in a joint tensor space. Relatedness between embeddings in this joint tensor space for text and associated source code is used in some embodiments to facilitate code search.

Code search and code navigation

A smart assistant is disclosed that provides for interfaces to capture requirements for a technical assistance request and then execute actions responsive to the technical assistance request. Example embodiments relate to parsing natural language input defining a technical assistance request to determine a series of instructions responsive to the technical assistance request. The smart assistant may also automatically detect a condition and generate a technical assistance request responsive to the condition. One or more driver applications may control or command one or more computing systems to respond to the technical assistance request.

Advanced machine learning interfaces

A system and method may provide assistance to programmers during programming to reduce the number of routine tasks that must be performed. In some aspects, the system may suggest one or more code snippets that comprise code completions. The code snippets may be single or multi-token. In some aspects, the system may provide predictive editing or predictive navigation, where the system may predict edits or navigation actions based on a programmer's actions. In some aspects, the system is based on machine learning methods and is trained on past actions of programmers in a code editor.

Code completion

A system and method may provide assistance to programmers related to the creation of documentation. In some aspects, the system may automatically generate documentation-related text in source code. In other aspects, the system may automatically detect the need for the programmer to edit long-from documentation when changes are detected in code. Moreover, the system may provide for the aggregation or creation of documentation content based on one or more data sources, such as by embedding links to those data sources into documentation. In some aspects, some components of the system are based on machine learning methods and are trained on collected data.

Automatic generation of documentation and aggregation of community content

Disclosed systems and methods relate to a knowledge sharing system for aggregating and disseminating knowledge related to programming. The knowledge system for aggregating and disseminating knowledge related to programming may organize or index knowledge according to topics. A topic may be any kind of transferrable piece of knowledge that may be shared. In some embodiments, knowledge organized under a topic may be comprised of a record of interactions with computing systems, and in some embodiments, knowledge organized under a topic may be comprised of text documents, code samples, documentation, web sites, records of discussions, or other kinds of reference materials.

Team knowledge sharing

A system and method may be provided for performing code analysis on a system of remote computer nodes. Input data may be collected on a local computer system along with a request for code analysis. The input data and request may be transmitted to a network of remote nodes. The network of remote nodes may perform the code analysis task using the input data. The results of the analysis may be returned back to the local computer.

Deployment models

A system and method may provide assistance to programmer during programming to detect and predict the existence of errors in code and, in some aspects, predict fixes for erroneous code. In some aspects, the system and method may use artificial intelligence to learn based on edits made by programmers, by observing code changes that cause errors and code changes that fix errors, or based on other data.

Growing community of inventors

San Francisco, CA, United States of America

Daniel Hung