Google identifies top 10 Gemini app issues after 1,400 user feedback responses
Google collected over 1,400 feedback responses in 12 hours from Gemini app users. Gemini lead Josh Woodward published a prioritized list of the top 10 requested improvements, with Google Workspace integration reliability ranking as the clear number one concern.
Google identifies top 10 Gemini app issues after 1,400 user feedback responses
Google collected over 1,400 feedback responses in 12 hours from Gemini app users. Gemini lead Josh Woodward published a prioritized list of the top 10 requested improvements, with Google Workspace integration reliability ranking as the clear number one concern.
The feedback collection follows Google's Neural Expressive redesign launched in May 2026. This marks at least the second time Woodward has solicited direct user input on the Gemini app.
Priority fixes and feature requests
The top-ranked issue is Google Workspace integration reliability. According to Woodward, "some improvements went into Gemini Spark recently, but this needs to be much better across the entire app."
Tool calling reliability ranks second. Google states users "should expect to see noticeable gains soon," suggesting underlying model improvements are coming.
Users also requested Projects and folder organization for chats. While Google recently added Notebooks, Woodward acknowledged "Notebooks have been a positive step, but not enough" and promised to "rethink this UX."
Other confirmed development priorities include:
- Expanded MCP (Model Context Protocol) and custom skills support beyond the early Gemini Spark implementation
- Deep Research export to NotebookLM and model switching within chats
- Message editing throughout chat history while preserving existing branching features
- In-app voice dictation accuracy improvements
- Mobile scrolling bug fixes
Google confirmed it will adjust watermarks on Nano Banana while navigating varying AI regulations by country. The company declined to modify "Celebrity Likeness" guardrails, stating they "plan to keep this as-is right now."
Recent integrations
Google recently launched third-party integrations including Canva, Dropbox, Instacart, OpenTable, and Zillow for Gemini Spark.
What this means
Google's public feedback process signals an attempt to address persistent user experience issues in the Gemini app rather than focusing solely on model capabilities. The emphasis on Workspace integration reliability as the top concern indicates enterprise users are experiencing significant friction with Google's own productivity suite. The promised "noticeable gains soon" for tool calling suggests Google has identified specific model or infrastructure bottlenecks causing reliability issues. The company's willingness to publicly acknowledge and prioritize these problems contrasts with typical AI company communication focused on capabilities rather than limitations.
Related Articles
Google rolls out computer use in the Gemini app for Mac for multi-step desktop tasks
Google announced on November 19, 2026 that computer use is rolling out in the Gemini app for Mac. Gemini can carry out multi-step work across local files, desktop applications and websites, working in an isolated background window with a live preview in the chat.
Google builds isolated 'Mirror Dimension' web to train and test Chrome AI agents
Google's Chrome team built the Mirror Dimension, an isolated web ecosystem it fully controls, to train and test Gemini-based browsing agents without exposing them to the open internet. Google is detailing the project in a blog post, according to Wired.
Tunix agentic GRPO lifts Gemma 4 E2B from 9.4% to 95% win rate in Plane Strike
Google's developer blog details how Tunix's agentic GRPO pipeline trained Gemma 4 E2B to play Plane Strike with tool calls. The win rate on held-out boards rose from 9.4% to 95% after 100 steps on a single Cloud TPU v6e-8 host.
Google previews Tool Retrieval in Gemini Interactions API to load tool schemas only when needed
Google announced Tool Retrieval on November 19, 2026, available in preview in the Gemini Interactions API. Agents can keep large tool libraries on standby and load full parameter schemas only when the current task needs them.
Comments
Loading...