Agency plus automation: Designing artificial intelligence into interactive systems
Open accessAbstract
Much contemporary rhetoric regards the prospects and pitfalls of using artificial intelligence techniques to automate an increasing range of tasks, especially those once considered the purview of people alone. These accounts are often wildly optimistic, understating outstanding challenges while turning a blind eye to the human labor that undergirds and sustains ostensibly “automated” services. This long-standing focus on purely automated methods unnecessarily cedes a promising design space: one in which computational assistance augments and enriches, rather than replaces, people’s intellectual work. This tension between human agency and machine automation poses vital challenges for design and engineering. In this work, we consider the design of systems that enable rich, adaptive interaction between people and algorithms. We seek to balance the often-complementary strengths and weaknesses of each, while promoting human control and skillful action. We share case studies of interactive systems we have developed in three arenas—data wrangling, exploratory analysis, and natural language translation—that integrate proactive computational support into interactive systems. To improve outcomes and support learning by both people and machines, we describe the use of shared representations of tasks augmented with predictive models of human capabilities and actions. We conclude with a discussion of future prospects and scientific frontiers for intelligence augmentation research.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The Parable of Google Flu: Traps in Big Data Analysis
Lazer, D., Kennedy, R., King, G., & Vespignani, A. (2014) · Science · doi:10.1126/science.1248506 · Cited by 2,523 · see citing works
Direct manipulation vs. interface agents
Shneiderman, B., & Maes, P. (1997) · Interactions · doi:10.1145/267505.267514 · Cited by 518 · see citing works
Flagged first, then by citations
Research works printed but not linked: 18
- [8]Shneiderman B (2007) Creativity support tools: Accelerating discovery and innovation. Commun ACM 50:20 -32.
- [9]Terry M, Mynatt ED, Nakakoji K, Yamamoto Y (2004) Variation in element and action: Supporting simultaneous development of alternative solutions. Proceedings of the ACM Human Factors in Computing Systems (CHI) (Association for Computing Machinery, New York), pp 711 -718.
- [10]Jacobs J, Brandt J, Mech R, Resnick M (2018) Extending manual drawing practices with artist-centric programming tools. Proceedings of the ACM Human Factors in Computing Systems (CHI) (Association for Computing Machinery, New York), vol 590, pp 1 -13.
- [11]Horvitz E (1999) Principles of mixed-initiative user interfaces. Proceedings of the ACM Human Factors in Computing Systems (CHI) (Association for Computing Machinery, New York), pp 159 -166.
- [12]Kandel S, Paepcke A, Hellerstein JM, Heer J (2012) Enterprise data analysis and visualization: An interview study. IEEE Trans Vis Comput Graph 18:2917 -2926.
- [13]Kandel S, Paepcke A, Hellerstein JM, Heer J (2011) Wrangler: Interactive visual specification of data transformation scripts. Proceedings of the ACM Human Factors in Computing Systems (CHI) (Association for Computing Machinery, New York), pp 3363 -3372.
- [14]Guo PJ, Kandel S, Hellerstein JM, Heer J (2011) Proactive wrangling: Mixed-initiative end-user programming of data transformation scripts. Proceedings of the ACM User Interface Software & Technology (UIST) (Association for Computing Machinery, New York), pp 65 -74.
- [15]Heer J, Hellerstein JM, Kandel S (2015) Predictive interaction for data transformation. Proceedings of the Seventh Biennial Conference on Innovative Data Systems Research (CIDR) . Available at cidrdb.org/cidr2015/Papers/CIDR15\_Paper27.pdf. Accessed November 29, 2018.
- [16]Wongsuphasawat K, et al. (2016) Voyager: Exploratory analysis via faceted browsing of visualization recommendations. IEEE Trans Vis Comput Graph 22:649 -658.
- [17]Wongsuphasawat K, et al. (2017) Voyager 2: Augmenting visual analysis with partial view specifications. Proceedings of the ACM Human Factors in Computing Systems (CHI) (Association for Computing Machinery, New York), pp 2648 -2659.
- [18]Satyanarayan A, Moritz D, Wongsuphasawat K, Heer J (2017) Vega-lite: A grammar of interactive graphics. IEEE Trans Vis Comput Graph 23:341 -350.
- [19]Moritz D, et al. (August 20, 2018) Formalizing visualization design knowledge as constraints: Actionable and extensible models in Draco. IEEE Trans Vis Comput Graph , 10.1109/TVCG.2018.2865240. · DOI
- [20]Green S, Heer J, Manning CD (2015) Natural language translation at the intersection of AI and HCI. Commun ACM 58:46 -53.
- [21]Green S, Chuang J, Heer J, Manning CD (2014) Predictive translation memory: A mixed-initiative system for human language translation. Proceedings of the ACM User Interface Software and Technology (UIST) (Association for Computing Machinery, New York), pp 177 -187.
- [22]Green S, et al. (2014) Human effort and machine learnability in computer aided translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Association for Computational Linguistics, Stroudsburg, PA), pp 1225 -1236.
- [23]Green S, Heer J, Manning CD (2013) The efficacy of human post-editing for language translation. Proceedings of the ACM Human Factors in Computing Systems (CHI) (Association for Computing Machinery, New York), pp 439 -448.
- [24]Pennington J, Socher R, Manning CD (2014) GloVe: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Association for Computational Linguistics, Stroudsburg, PA), pp 1532 -1543.
- [25]Carter S, Nielsen M (2017) Using artificial intelligence to augment human intelligence. Distill . Available at https://distill.pub/2017/aia/. Accessed May 22, 2018.
Cited by
Sorted by citations
Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Shneiderman, B. (2020) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2020.1741118 · Cited by 1,743 · see citing works
Shneiderman, B. (2020) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3419764 · Cited by 768 · see citing works
Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI
Wang, D., Weisz, J. D., Muller, M., Ram, P., Geyer, W., Dugan, C., Tausczik, Y., Samulowitz, H., & Gray, A. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359313 · Cited by 342 · see citing works
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 244 · see citing works
“These agents are defined by their ability to perceive structured or unstructured inputs [46], to reason over contextual information [47,48], and to initiate actions toward achieving specific objectives, often acting as surrogates for human users or subsystems [49].”
Humans as Creativity Gatekeepers: Are We Biased Against AI Creativity?
Magni, F., Park, J., & Chao, M. M. (2024) · Journal of Business and Psychology · doi:10.1007/s10869-023-09910-x · Cited by 201 · see citing works
Holstein, K., McLaren, B. M., & Aleven, V. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-23204-7_14 · Cited by 189 · see citing works
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186 · see citing works
From explainable to interactive AI: A literature review on current trends in human-AI interaction
Raees, M., Meijerink, I., Lykourentzou, I., Khan, V.-J., & Papangelis, K. (2024) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2024.103301 · Cited by 180 · see citing works
DeepThInk: Designing and probing human-AI co-creation in digital art therapy
Du, X., An, P., Leung, J., Li, A., Chapman, L. E., & Zhao, J. (2024) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2023.103139 · Cited by 95 · see citing works
The sense of agency in emerging technologies for human–computer integration: A review
Cornelio, P., Haggard, P., Hornbaek, K., Georgiou, O., Bergström, J., Subramanian, S., & Obrist, M. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.949138 · Cited by 75 · see citing works
Levy, A., Agrawal, M., Satyanarayan, A., & Sontag, D. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445522 · Cited by 73 · see citing works
The TA Framework: Designing Real-time Teaching Augmentation for K-12 Classrooms
An, P., Holstein, K., d'Anjou, B., Eggen, B., & Bakker, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376277 · Cited by 69 · see citing works
“Given these trade-offs, it is critical to understand the roles teachers prefer to perform in particular educational contexts, and where automation may help more than hurt [28, 47, 52, 76].”
BackgroundInfluentialA User-centered Framework for Human-AI Co-creativity
Moruzzi, C., & Margarido, S. (2024) · Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613905.3650929 · Cited by 68 · see citing works
The use of AI in mental health services to support decision-making: scoping review
Auf, H., Svedberg, P., Nygren, J., Nair, M., & Lundgren, L. E. (2025) · Journal of Medical Internet Research · doi:10.2196/63548 · Cited by 56 · see citing works
Artist Support Networks: Implications for Future Creativity Support Tools
Chung, J. J. Y., He, S., & Adar, E. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533505 · Cited by 46 · see citing works
AI-Assisted Human Labeling: Batching for Efficiency without Overreliance
Ashktorab, Z., Desmond, M., Andres, J., Muller, M., Joshi, N. N., Brachman, M., Sharma, A., Brimijoin, K., Pan, Q., Wolf, C. T., et al. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3449163 · Cited by 45 · see citing works
Galsgaard, A., Doorschodt, T., Holten, A.-L., Müller, F. C., Ploug Boesen, M., & Maas, M. (2022) · European Journal of Radiology · doi:10.1016/j.ejrad.2022.110231 · Cited by 38 · see citing works
MetaWriter: Exploring the Potential and Perils of AI Writing Support in Scientific Peer Review
Sun, L., Tao, S., Hu, J., & Dow, S. P. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637371 · Cited by 37 · see citing works
Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents
Huang, Z., Gutierrez, S., Kamana, H., & Macneil, S. (2023) · Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586182.3615796 · Cited by 34 · see citing works
Data Playwright: Authoring Data Videos With Annotated Narration
Shen, L., Li, H., Wang, Y., Luo, T., Luo, Y., & Qu, H. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3477926 · Cited by 21 · see citing works
How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
Tang, Y., Zhou, J., Li, H., Xie, X., Ma, X., & Qu, H. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790300 · Cited by 5 · see citing works
“In human–AI collaboration, Heer [28] examined how human con-trol is balanced with automation, while Méndez et al. [45] described agency as the degree to which the user or the system drives visualization creation.”
Li, H., Wang, Y., & Qu, H. (2025) · arXiv · doi:10.48550/arxiv.2503.02631
“Next, an interface, or “shared representation” [13] is required to support the communication among AI collaborators in different stages and even between AI and humans [21], e.g. , chart or insight specification.”
How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
Tang, Y., Zhou, J., Li, H., Xie, X., Ma, X., & Qu, H. (2026) · arXiv · Cited by 5
- Authors
- Heer, J.
- Affiliations
- University of Washington (US)
- Corresponding author
- Heer, Jeffrey
- ORCID
- Heer, Jeffrey
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2019-02-04
- Volume
- 116
- Issue
- 6
- Pages
- 1844-1850
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC6369770
- OpenAlex
- W2911396267
- Cited by
- 279
- References
- 2
- Citations by year
- 2026: 50 · 2025: 50 · 2024: 47 · 2023: 31 · 2022: 33 · 2021: 33 · 2020: 24 · 2019: 11
- FWCI
- 22.68
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion)
- Europe PMC (PubMed Central) (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Data Visualization and Analytics
- Social Sciences › Psychology › Social Psychology › Human-Automation Interaction and Safety
- Keywords
- intelligence enhancement, human agency, machine automation, human-computer interaction, interactive system design, data wrangling, exploratory data analysis, natural language translation, human control
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
