I desperately wish Google would focus on improving the Gemini capabilities that are built-in to their office suite (docs, slides, etc.). The current built-in Gemini is terrible, and if I could use e.g. Claude natively with those products my workday would be an order of magnitude more productive.
I'm shocked that they don't seem to be investing in agentic capabilities there at all.
Gemini in Google Docs products is embarrassingly bad. Like Microsoft Copilot-levels of "shove AI into everything even if it's dumber or more limited than than GPT-3".
Every time I'm in google docs and want to do something with AI I try Gemini only to get frustrated that basic things are completely beyond its ability. I'm better off opening Claude's extension to do the work.
I avoid gemini because it's always been trash IMHO but I am forced to use a version of it via Siri now and I don't know if it's Apple's AI incompetence (of which there is plenty) or Google's trash model that causes Siri to still be shit. The fact I don't hear Android users raving (or taking at all) about gemini on their phones makes me think the model is just bad.
Instead they fire the person that made Google Workspace CLI and focus on things that are flashy for demos. You can generate a cat balancing on a ball into your Slide if you want!
I built https://smalldocs.org / https://github.com/espressoplease/smalldocs basically for this. It lets any agent you want create rich documents - word, slides, spreadsheets, mermaid diagrams, rich code rendering, etc. About to launch a cloud first version of it, so what's on the site now will evolve soon.