# Input mid-processing

**URL:** <https://community.perplexity.ai/t/input-mid-processing/1594>\
**Category:** Feature Requests\
**Tags:** sonar-api\
**Created:** [September 26, 2025, 3:48am UTC](https://community.perplexity.ai/t/input-mid-processing/1594 "2025-09-26T03:48:17Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Aarsan](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/aarsan/32/1104_2.png) [@Aarsan](https://community.perplexity.ai/u/Aarsan)\
**Post date:** [September 26, 2025, 3:48am UTC](https://community.perplexity.ai/t/input-mid-processing/1594/1 "2025-09-26T03:48:17Z")

</div>

🚀 **Feature Request**  
Enable a **mid-input system** for AI Browser tasks, allowing users to provide additional data or guidance _during_ multi-step automations (e.g., form filling, checkout flows), rather than only before or after the entire process.

🔍 **Problem Statement**  
Currently, if Perplexity AI needs information (like age, email, or a selection) during a task, it exits and asks the user to restart with the missing data. This disrupts the workflow and makes complex automations (multi-page forms, registrations, stepwise tasks) cumbersome. Users can’t clarify or correct entries in real time.

💡 **Proposed Solution**  
Implement a live interaction feature where the AI:

- Pauses and prompts for input whenever a data field or choice is encountered.

- Allows users to reply instantly (“Enter my age: 15”) and the agent continues the process without starting over.  
**Example Use Case:**

1. User instructs: “Fill out this registration form for me.”

2. AI begins task, then asks: “What should I enter for your birthdate?”

3. User replies: “August 4, 2009.”

4. AI continues to next page, asks for address, user replies, process remains uninterrupted.

📌 **API Impact**

- Component: Likely affects the _chat completions_ and _browser control_ APIs.

- Model: Impacts any model with browser-agent automation (e.g., Sonar Deep Research).

- Change: Would require new session management capabilities and possibly a streaming/mid-action messaging protocol to enable real-time user input.

🔄 **Alternatives Considered**  
The current workaround is replying to failed prompts when the AI agent exits (e.g., “What should I enter for X?” then manually restarting the task). This is inefficient for multi-field workflows and loses context.

📎 **Additional Context**

- Improves user experience for lengthy forms, registrations, and stepwise automation.

- Bridges gap between single-turn automation and true interactive collaboration.

- Would make Perplexity’s AI agent feel more like a live assistant.