The United States Patent Office recently released Google’s follow-up to a patent for a search system that detects when there is no satisfactory answer to a query and waits to automatically provide the answer when it becomes available.
Research and AI Assistant
The patent, published in February 2026, is a continuation of an older patent, with the main changes being to apply this patent in the context of an AI assistant. The invention describes solving the problem of answering a question when no actual answer is available at the time a user makes the query. What it does is wait until there is a satisfactory answer, after which it returns to the user with the answer, without them having to ask again.
The patent is titled “Autonomously providing post-facto search results, including in an assistant context.” Although the patent mentions quality thresholds, these thresholds are defined in the sense that the response meets the user’s needs.
The patent describes six scenarios that would trigger the invention:
- When no search results meet defined quality or authoritative answer criteria.
- When results exist but fail to provide a definitive or authoritative answer that meets these criteria.
- When no results meet the quality criteria because the information is not yet available.
- When a query is looking for a specific answer and no results meet the required criteria.
- When a resource later meets the defined criteria after previously lacking required information.
- When a previously available resource is refined or updated so that it now meets the criteria.
Useful and complete answers
Google’s patent states that the invention is a solution for times when there are no useful or complete answers because the information does not yet exist or is not good enough, forcing users to keep searching repeatedly.
The system checks whether the results are compliant:
- A quality standard
- Authority standard
- Or a standard of completeness.
If current responses do not meet these standards, the system will store the query and monitor for new or updated information. Once available, it will send the results to the user later without them searching again.
Follow-up questions are not necessary
What is new about the invention is that it allows for subsequent transmission of results after the original query without requiring new follow-up questions. It also displays search results proactively in notifications or Assistant conversations.
Subsequently, when new or updated information that meets the criteria becomes available, the system proactively provides this information to the user. This transmission may take place via notifications, in an unrelated interaction, or in a subsequent conversation with an automated assistant.
The system can also optionally inform the user that no good results are currently available and ask if they would like to be notified when better results appear.
This system transforms searching from a one-time user-initiated action into a persistent, ongoing process in which the system continues to operate in the background and updates the user when meaningful information becomes available.
Continuity between devices
An interesting feature of this invention is that it can reach the user on multiple devices.
Here’s where it’s described:
(0012) In some implementations, the request is received on an additional computing device in addition to the computing device for which the content is provided for presentation to the user.
This ability is highlighted again in section (0067):
“For example, the content may be provided to be presented to the user through the same computing device that the user used to submit the query and/or through a separate computing device.”
It may also be delivered to multiple devices as visual and/or audio output across devices and as an automated assistant, and may present the information as the user interacts with the automated assistant in a different context, describing an “ecosystem” of devices.
Finally, the patent explains that the information can appear when the user interfaces with the automated assistant in a completely different context:
(0040)”…the content may be provided for presentation to the user via the same computing device used by the user to submit the query and/or via a separate computing device. The content may be provided for presentation in a variety of forms. For example, the content may be provided as a visual and/or audible push notification on a mobile computing device of the user, and may appear regardless of whether the user resubmits the query and/or another query.
Additionally, for example, the content may be presented as visual and/or audio output of an automated assistant during a dialog session between the user and the automated assistant, where the dialog session is not related to the query and/or another query seeking similar information.
Takeaways
The patent (Autonomously provide search results a posteriori, including in the context of a wizard) is in line with Google’s vision of agentic, task-based search, in which AI assistants help users accomplish things. This patent could be applied to an AI agent who is asked for tickets to an event when the tickets are not yet available. Or this could be applied to restaurant reservations when reservations are open. These two scenarios are related to task-based agentic search (TBAS)
Here are seven points to remember:
- The system stores user-associated data on unresolved queries, allowing it to track unanswered information needs over time rather than treating each search as a one-time event.
- It delivers results during future interactions, including non-Assistant conversations, not just through standalone notifications.
- Notifications can occur across an ecosystem of devices.
- A lack of results is defined by failure to meet quality criteria, which can be information is missing, the answer is not yet available, or the answer is not available from authoritative sources.
- The system focuses on queries that seek specific answers, rather than general information searches.
- It supports cross-device continuity, allowing a query on one device to be executed later on another.
- The design reduces repeated searches by eliminating the need for users to navigate back and then navigate back autonomously when information is available.
Featured image by Shutterstock/uyabdami
