Clarification Before Execution: Interaction Design for Trustworthy Conversational Business Intelligence

Conversational business intelligence promises to let people explore organizational data without mastering query languages, but its central design problem is not translation. It is the management of ambiguity before an irreversible interpretation becomes an authoritative result or a production data artifact. This conceptual analysis examines clarification as a control mechanism across two levels of analytics work. SiriusBI places semantic completion, knowledge-guided clarification, and proactive querying inside a deployed BI architecture; SiriusDeliver extends agentic assistance into warehouse delivery, where ambiguity can affect workflow configuration, transformation code, and platform submission. Their relationship suggests that clarification must be treated as a lifecycle capability rather than a chat feature. Drawing on conversational text-to-SQL, interactive correction, schema linking, constrained decoding, retrieval, human-AI interaction, and documentation research, the article develops a framework for deciding when to ask, what to ask, and how to carry the answer into executable artifacts. It argues for minimum-regret questions, visible commitments, progressive authorization, and persistent decision records. The goal is not maximal dialogue. It is the smallest amount of well-timed interaction that prevents costly semantic and operational errors while preserving user agency.

1. Jiang, J., Xie, H., Yang, J., Shen, S., Wang, Z., Zheng, Y., ... & Jiang, J. (2024). Siriusbi: A comprehensive llm-powered solution for data analytics in business intelligence. *arXiv preprint arXiv:2411.06102*.
2. Xie, H., Zhou, X., Yang, J., Shen, S., Wang, Z., Zheng, Y., ... & Jiang, J. (2026). SiriusDeliver: Automating Data Warehouse Delivery at Tencent. *arXiv preprint arXiv:2608.09185*.
3. Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., et al. (2019). Guidelines for human-AI interaction. In *Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems* (pp. 1-13). https://doi.org/10.1145/3290605.3300233 DOI
4. Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daume III, H., & Crawford, K. (2021). Datasheets for datasets. *Communications of the ACM, 64*(12), 86-92. https://doi.org/10.1145/3458723 DOI
5. Guo, J., Zhan, Z., Gao, Y., Xiao, Y., Lou, J. G., Liu, T., & Zhang, D. (2019). Towards complex text-to-SQL in cross-domain database with intermediate representation. In *Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics* (pp. 4524-4535). https://doi.org/10.18653/v1/P19-1444 DOI
6. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. *Advances in Neural Information Processing Systems, 33*.
7. Li, Y., Chen, B., Liu, Q., Gao, Y., Lou, J. G., Zhang, Y., & Zhang, D. (2020). What do you mean by that? A parser-independent interactive approach for enhancing text-to-SQL. In *Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing* (pp. 8351-8361). https://doi.org/10.18653/v1/2020.emnlp-main.561 DOI
8. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., et al. (2019). Model cards for model reporting. In *Proceedings of the Conference on Fairness, Accountability, and Transparency* (pp. 220-229). https://doi.org/10.1145/3287560.3287596 DOI
9. Scholak, T., Schucher, N., & Bahdanau, D. (2021). PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. In *Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing* (pp. 9895-9901). https://doi.org/10.18653/v1/2021.emnlp-main.779 DOI
10. Wang, B., Shin, R., Liu, X., Polozov, O., & Richardson, M. (2020). RAT-SQL: Relation-aware schema encoding and linking for text-to-SQL parsers. In *Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics* (pp. 7567-7578). https://doi.org/10.18653/v1/2020.acl-main.677 DOI
11. Yu, T., Zhang, R., Er, H., Li, S., Xue, E., Pang, B., et al. (2019). CoSQL: A conversational text-to-SQL challenge towards cross-domain natural language interfaces to databases. In *Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing* (pp. 1962-1979). https://doi.org/10.18653/v1/D19-1204 DOI
12. Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., et al. (2018). Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. In *Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing* (pp. 3911-3921). https://doi.org/10.18653/v1/D18-1425 DOI
13. Zeng, J., Lin, X. V., Hoi, S. C. H., Socher, R., Xiong, C., Lyu, M., & King, I. (2020). Photon: A robust cross-domain text-to-SQL system. In *Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations* (pp. 204-214). https://aclanthology.org/2020.acl-demos.24/