Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop

@article{Cranshaw2017CalendarhelpDA,
  title={Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop},
  author={Justin Cranshaw and Emad Elwany and Todd Newman and Rafal Kocielnik and Bowen Yu and Sandeep Soni and J. Teevan and A. Monroy-Hern{\'a}ndez},
  journal={Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems},
  year={2017}
}
Although we may complain about meetings, they are an essential part of an information worker's work life. Consequently, busy people spend a significant amount of time scheduling meetings. We present Calendar.help, a system that provides fast, efficient scheduling through structured workflows. Users interact with the system via email, delegating their scheduling needs to the system as if it were a human personal assistant. Common scheduling scenarios are broken down using well-defined workflows… Expand
Workflow Complexity for Collaborative Interactions: Where are the Metrics? - A Challenge
TLDR
The problem of denoting and deriving the complexity of workflows in collaborative, planner-assisted settings where humans and agents are trying to jointly solve a task is introduced. Expand
Human-Centered Decision Support for Agenda Scheduling
TLDR
This work presents a novel heuristic for adding tasks to agendas that targets rescheduling to clusters of appointments that are spatio-temporally near the new task and shows that this heuristic approach always finds the optimal solution, while greatly reducing rescheduled time. Expand
Iris: A Conversational Agent for Complex Tasks
TLDR
This paper presents a new approach to designing conversational agents inspired by linguistic theory, where agents can execute complex requests interactively by combining commands through nested conversations in Iris, an agent that can perform open-ended data science tasks such as lexical analysis and predictive modeling. Expand
Microtask Detection
TLDR
This article introduces the novel challenge of microtask detection, and it presents machine-learned models for automatically determining which tasks are actionable and which of these actionable tasks are microtasks, which have implications for the design of systems to help people make the most of their time. Expand
Design and evaluation of intelligent agent prototypes for assistance with focus and productivity at work
TLDR
A productivity agent which helps users schedule and block out time on their calendar to focus on important tasks, monitor and intervene with distractions, and reflect on their daily mood and goals in a single, standalone application is presented. Expand
Creating Better Action Plans for Writing Tasks via Vocabulary-Based Planning
TLDR
This work introduces a vocabulary-a finite set of functions pertaining to writing tasks-as a cognitive scaffold that enables people with necessary context to generate action plans for others, and shows that using a vocabulary reduces planning time and effort and improves plan quality compared to unstructured planning. Expand
Learning User Preferences and Understanding Calendar Contexts for Event Scheduling
TLDR
This paper proposes Neural Event Scheduling Assistant (NESA), which learns user preferences and understands calendar contexts, directly from raw online calendars for fully automated and highly effective event scheduling. Expand
State Machine Based Human-Bot Conversation Model and Services
TLDR
The idea of leveraging Conversational State Machine to make it a core part of chatbots’ conversation engine by formulating conversations as a sequence of states is proposed, which allows chatbots to manage tangled conversation situations where most existing chatbot technologies fail. Expand
Petri Net-based Combination and Integration of Agents and Workflows
TLDR
This thesis researches, develops and provides a combination and integration of agents and workflows that enables the strengths for both structure and behaviour simultaneously and creates novel and beneficial synergies. Expand
AutoDS: Towards Human-Centered Automation of Data Science
TLDR
The goal is to offer a systematic investigation of user interaction and perceptions of using an AutoDS system in solving a data science task, and to reflect on the findings by presenting design implications for incorporating automation techniques into human work in the data science lifecycle. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
A Formal Study of Distributed Meeting Scheduling
TLDR
It is argued that meeting scheduling is an inherently distributed process, and that negotiating over meetings can be viewed as a distributed search process, which provides a springboard into deeper investigations of important issues in distributed artificial intelligence. Expand
An Intelligent Personal Assistant for Task and Time Management
TLDR
An intelligent personal assistant that has been developed to aid a busy knowledge worker in managing time commitments and performing tasks and is highly user centric in its support for human needs, responsiveness to human inputs, and adaptivity to user working style and preferences. Expand
Chronos: A multi-agent system for distributed automatic meeting scheduling
TLDR
Chronos is described, a multi-agent system for helping users in organizing their meetings that assigns an intelligent Organizer Agent to each user and learns from its user's preferences and from negotiations with other agents, to provide better and more accurate assistance. Expand
Agents that reduce work and information overload
TLDR
Results from several prototype agents that have been built using an approach to building interface agents are presented, including agents that provide personalized assistance with meeting scheduling, email handling, electronic news filtering, and selection of entertainment. Expand
Experience with a learning personal assistant
TLDR
The design of one particular learning assistant is described: a calendar manager, called CAP (Calendar APprentice), that learns user scheduling preferences from experience and suggests that machine learning methods may play an important role in future personal software assistants. Expand
groupTime: preference based group scheduling
TLDR
This paper presents a lightweight interaction model for GS that can extend its reach beyond users of current group calendaring solutions and proposes an ontology that enables us to model user preferences with machine learning, predicting user responses to further lower cognitive load. Expand
Expert crowdsourcing with flash teams
TLDR
It is demonstrated that Foundry and flash teams enable crowdsourcing of a broad class of goals including design prototyping, course development, and film animation, in half the work time of traditional self-managed teams. Expand
Meeting scheduling across heterogeneous calendars and organizations utilizing mobile devices and cloud services
TLDR
Design science is employed to study how meetings can be scheduled over organizational and calendar system boundaries and utilizes heterogeneous calendar data from the mobile devices and the cloud calendars to aid the organizer in making better decisions regarding the meeting times. Expand
Human computation tasks with global constraints
TLDR
This paper focuses on the crowdsourcing of itinerary planning as a case study of constraint-based human computation tasks and introduces a collaborative planning system called Mobi that illustrates a novel crowdware paradigm. Expand
Assistance: the work practices of human administrative assistants and their implications for it and organizations
TLDR
A study of assistants, and their principals and managers, lays out a model of their work, the skills and competencies they need to function effectively, and reflects on implications for the design of systems and organizations. Expand
...
1
2
3
4
5
...