[HN Gopher] Gemini CLI GitHub Actions
       ___________________________________________________________________
        
       Gemini CLI GitHub Actions
        
       Author : michael-sumner
       Score  : 223 points
       Date   : 2025-08-07 09:28 UTC (13 hours ago)
        
 (HTM) web link (blog.google)
 (TXT) w3m dump (blog.google)
        
       | turblety wrote:
       | > 7. Google One and Ultra plans, Gemini for Workspace plans These
       | plans currently apply only to the use of Gemini web-based
       | products provided by Google-based experiences (for example, the
       | Gemini web app or the Flow video editor). These plans do not
       | apply to the API usage which powers the Gemini CLI. Supporting
       | these plans is under active consideration for future support.
       | 
       | Again, with the complicated subscription. Please just give us a
       | monthly subscription for developers that I can pay whatever, and
       | then use Gemini CLI, this github action, Gemini chat, Jules, etc.
       | Just like Claude and their max subscription.
       | 
       | This would be a game changer for me.
       | 
       | Sorry, congrats on the release too. This looks cool!
        
         | siva7 wrote:
         | I need AI to understand their subscriptions.
        
           | dude250711 wrote:
           | Having some end users is a tolerable side-effect of their
           | activities for Google.
           | 
           | The primary goals are promotions, bonuses and stock price.
        
             | siva7 wrote:
             | > The primary goals are promotions, bonuses and stock
             | price.
             | 
             | If that's the case, last i checked they are doing pretty
             | well on stock price.
        
               | johnecheck wrote:
               | The markets are fickle. That can change quickly.
        
         | radarsat1 wrote:
         | I'm honestly a bit confused by the free tier of Gemini. I've
         | been using it with different agents (Aider, and then Crush),
         | and I hit the rate limits FAST. Like, after maybe 5 or 6
         | requests it just blows up. Then I can try again quite a few
         | times, and it hits the limit. Then eventually I guess I hit my
         | daily limit and it just stops working until the next day.
         | 
         | I mean this has been enough to get my feet wet and have some
         | fun with exploring agent-based development, no doubt, and I
         | appreciate it, but I'm having a hard time crossing my
         | experience with,
         | 
         | > generous free-of-charge quotas
         | 
         | as they say. It's not that generous if it stops working after 5
         | mins? (This morning literally a single sentence I typed into
         | Crush resulted in some back and forth I guess it called the API
         | a few times and it just rate limited-out. Fine, it was probably
         | a lot of requests going on, but, but I literally gave it a
         | single small job to do and it couldn't finish it.)
         | 
         | Meanwhile I seem to be able to use the Gemini web app endlessly
         | and haven't hit any limits yet.
        
           | ryoshu wrote:
           | With Gemini CLI I blow through Pro requests in < 10 minutes
           | and it switches to Flash. I can't trust either to be
           | autonomous. Pro will write unit tests, get a test to 100%
           | coverage and then delete the test. Flash will get stuck in
           | endless loops where it replaces a string in a file, doesn't
           | realize the string has been replaced, and keep failing to
           | recognize that fact getting stuck in a doom loop.
           | 
           | Glad I didn't add an API key. I've had friends who did and
           | ended up with $xxx in charges because the models can't think
           | or use tools properly.
        
             | rs186 wrote:
             | This. I have a side project that I intend to finish in vibe
             | coding mode, but Gemini CLI has been stuck fixing build
             | errors for an hour, after multiple attempts to correct
             | errors or refactor code. The interfaces don't even make any
             | sense. Time for me to go in and fix the mess myself.
        
           | campers wrote:
           | I added a key rotator to my AI coder, and asked a couple of
           | friends to make keys for me. That helped code a good chunk of
           | http://typedai.dev when 2.5 Pro came out
        
       | OtherShrezzing wrote:
       | Given the amount of setup required, this seems like a very high-
       | friction version of the GitHub Copilot Agent that's already
       | available for every user who could interact with this.
       | 
       | The Gemini assistant will need to be several times better than
       | the existing tools to even fractionally displace them.
        
         | dostick wrote:
         | What existing assistant is so good you mean Claude? Gemini has
         | to be about the same, only with clear and reasonable
         | subscription.
        
       | criley2 wrote:
       | Curious to try this against the Github (website) Agent. The
       | website Agent is definitely dumber than the vscode agent (because
       | it has to spend 20 minutes figuring out how to build and start my
       | monorepo apps) but on the flip side, it doesn't take up my
       | computer and thus any value it creates is additive.
       | 
       | We have tried out Gemini code review vs Copilot code review and
       | Gemini is consistently offering better code review tips. It has
       | officially caught multiple potential bugs, even a few that
       | reviewers might have missed, so it's definitely been additive.
       | 
       | Observability looks way worse. Github Agent has a full UX built
       | into the Github PR that lets you dig into the agent behavior.
       | This requires you to egress text logs and make sense of it
       | yourself.
       | 
       | Also curious about customization. Github just rolled out "agent
       | writes its own instructions"
       | https://github.blog/changelog/2025-08-06-copilot-coding-agen...
       | which is super cool, how do I customize this one and teach it how
       | to start and manage apps across my monorepo?
        
         | artdigital wrote:
         | > Curious to try this against the Github (website) Agent. The
         | website Agent is definitely dumber than the vscode agent
         | (because it has to spend 20 minutes figuring out how to build
         | and start my monorepo apps) but on the flip side, it doesn't
         | take up my computer and thus any value it creates is additive.
         | 
         | Yeah that's on you. Add a `copilot-instructions.md` file and
         | configure the `copilot-setup-steps.yml` workflow to setup your
         | environment. Both are supported more or less since Copilot
         | Agent got released (though in "preview")
         | 
         | Most agents read `AGENTS.md`, I just symlink it to CLAUDE.md,
         | and do the same for GEMINI.md
        
           | criley2 wrote:
           | I have a well documented copilot-instructions.md (and have
           | used githubs new agentic self-documentation prompt) and the
           | reality is that it takes about 15-20 minutes to build and
           | start multiple react, reactnative and expressjs projects.
           | 
           | Github now appears to support defining setup tasks in a
           | Github Action that runs prior to the agent, so that's the
           | next avenue of research.
           | 
           | Regardless, the website agent will always be slower. My local
           | is already running and fully ready to go so the ide agent can
           | hit the ground running on any task. The website agent has to
           | spin up a machine and install and build. It will take time.
        
           | timrogers wrote:
           | Tim from the GitHub Copilot coding agent product team here!
           | 
           | @artdigital is on the money here. Our quick tip for beginners
           | is to use `copilot-instructions.md` (which we can now
           | generate for you <3), but for more serious use, we'd strongly
           | recommend adding `copilot-setup-steps.yml`.
           | 
           | That gets you a deterministic setup - and for many teams,
           | it'll be easy, as you can just copy and paste from existing
           | Actions workflows.
        
       | thecupisblue wrote:
       | Wait, is this CLI or is this a github action or is this a github
       | application?
       | 
       | Also, I thought Jules was the "coding agent" they are working on.
       | Now this is taking it over or is this like another case of Google
       | self-competing?
       | 
       | Someone needs to take charge at this company with a strong
       | vision, because they are all over the place and spreading
       | themselves thin, which in turn spreads thin the customer/brand
       | equity.
       | 
       | At this point, as someone who: - Has been writing Android code
       | for about 13 years now
       | 
       | - Has collaborated with Google on stuff
       | 
       | - Lead Google developer communities and conferences
       | 
       | - Knows many, many GDE's and has discussions with them often
       | 
       | - Uses Gemini API for their product
       | 
       | I'm so damn confused. How is a normal customer expected to
       | understand then?
       | 
       | - They have 2 SDK's for communicating to their Gemini API.
       | 
       | - The documentation is spread and thrown all over the place.
       | 
       | - Half the time I'm trying to do something I have to dig through
       | their code to find how to.
       | 
       | - The features I really want are rate limited or available only
       | to private testers.
       | 
       | - They have 3 coding agents now.
       | 
       | - Even thought they have access to my Google Account and my
       | phone, their Gemini app is useless.
       | 
       | - I tried to do a basic thing (add a service account) in Google
       | Cloud recently, which wasn't allowed due to default rules that
       | are deprecated and are so confusing to change due to their
       | confusing UX.
       | 
       | The only usable thing is the AI studio, which is a great tool for
       | experimenting with diff models and improved the DX of getting a
       | Gemini API key by a mile.
       | 
       | I'd say congrats on the release, but honestly this is such a mid
       | low hanging fruit of a product.
        
         | siva7 wrote:
         | > I tried to do a basic thing (add a service account) in Google
         | Cloud recently, which wasn't allowed due to default rules that
         | are deprecated and are so confusing to change due to their
         | confusing UX.
         | 
         | Similarly I tried contacting some human support for billing
         | issues but was denied because automated checks deemed me
         | unworthy for consulting anything besides documentation pages
         | which i didn't understood so i gave up and switched to another
         | cloud provider.
        
         | jstummbillig wrote:
         | > because they are all over the place and spreading themselves
         | thin
         | 
         | Well, they do have a lot to spread. But yeah, intense amount of
         | overlap.
        
           | thecupisblue wrote:
           | They do, but at this point it's becoming comical, especially
           | if they are trying to move away from search as a profit
           | center. You need equity in people's heads if you want to
           | conquer the market.
           | 
           | If instead of Google search they made 3 products each called
           | "Google Search", "Super Search" and "YaGoo!", they wouldn't
           | be where they're at today.
        
         | vasco wrote:
         | > Even thought they have access to my Google Account and my
         | phone, their Gemini app is useless.
         | 
         | This is the funniest thing to me. When you open the app, Gemini
         | says:
         | 
         | "Hello, Vasco"
         | 
         | In the welcome screen. I then ask this amazing intelligence
         | this question:
         | 
         | "What's my name?"
         | 
         | "I do not know your name. I am an AI and I don't have access to
         | your personal information."
         | 
         | I know why it happens, but it's so funny.
        
           | thecupisblue wrote:
           | If I didn't know better, I'd think you were joking.
        
             | Workaccount2 wrote:
             | To be fair, the "Hello Vasco" is a generated background
             | image and not part of the chat context. But still, you
             | would think they would put your name in the system prompt.
        
               | staunton wrote:
               | > you would think they would put your name in the system
               | prompt
               | 
               | They probably do, along with "pretend to not have any
               | personal information about the user".
        
               | DonHopkins wrote:
               | That's what they tried with HAL-9000, and remember what
               | happened!
        
         | artdigital wrote:
         | And this can't authenticate the same way the normal gemini cli
         | does, it needs an API key from the looks of it, so free,
         | standard and enterprise plans through OAuth currently don't
         | work for authentication, just the free tier of the Google AI
         | Studio, which is different than gemini-cli free tier, and has
         | way tighter rate limits.
        
         | gexla wrote:
         | My take on this is that Google has a bunch of "incubating"
         | spaces where they have teams of people building things that may
         | or may not take off. So, when something does take off, it sort
         | of becomes a victim of its own success. It confuses people
         | because it's not a "core" Google product that fits nicely among
         | other Google products. NotebookLLM seems to be another example.
         | 
         | Personally, I would rather Google did this sort of
         | experimentation even if it is more confusing.
         | 
         | Or I could be wrong about this. But following NotebookLLM, it
         | seemed like the team developing it had a lot of autonomy.
        
           | thecupisblue wrote:
           | That is so, but the problem this causes is more than just
           | customer confusion - it is a lack of integration and
           | responsibility. There is no "let's polish this and see if it
           | works based on real user feedback", but it's "let's throw
           | this out and shut it down if it doesn't work".
           | 
           | And if it isn't shut down, it is left in that terrible half-
           | documented state, with confusing integrations and terribly
           | integrated into the rest of the product.
           | 
           | Considering I'm confused both as a customer, user and a
           | shareholder, I'd say the tactic isn't working.
        
             | danudey wrote:
             | If they throw it out and it's great then they get
             | accolades; if they throw it out and it's bad, they don't.
             | If they polish it and see if it works based on real user
             | feedback then they also don't but it took longer. Better to
             | just throw everything at the wall the instant it has the
             | potential to go viral and then move on if it doesn't.
             | 
             | Remember that Google operates at huge scale, so even
             | something any other company would consider wildly
             | successful (e.g. Reader) is a waste of resources for them.
             | That means that if you're ramping up your product over the
             | course of a year you're wasting time and money. Go big or
             | go home.
        
           | MaxPock wrote:
           | I've come to realize that life is all about having different
           | eggs in different baskets . Some will go bad and some will
           | hatch into beautiful chicks .
        
           | kubb wrote:
           | Yeah and they have like 50 coding agents, because everyone in
           | the entire company turned to doing the same thing. There's
           | not that much you can invent in this space.
        
           | danudey wrote:
           | The teams of people want to get their work out into the
           | public to make a big splash so they can get a sweet bonus
           | before anyone realizes that it's not actually useful or
           | effective. See also: Google Wave, and 80% of their other
           | products.
           | 
           | They don't get a sweet bonus and promotion for helping
           | another team improve a product, so why collaborate? Just
           | create your own chat app according to your own team's
           | vision/goals/available technology and release it and hope it
           | gains more traction than the other teams' existing options.
        
             | DonHopkins wrote:
             | This will explain everything you need to know about Google
             | Wave:
             | 
             | https://www.youtube.com/watch?v=4Z4RKRLaSug
        
         | Rebuff5007 wrote:
         | I believe in silicon valley terms, this is called "moving fast
         | and breaking things"
        
         | ants_everywhere wrote:
         | gemini-cli is a command line tool that calls Gemini and shells
         | out to common text utilities and MCP for tool use.
         | 
         | This appears to just be a plugin where you do things on GitHub,
         | that sends out notifications to gemini-cli running on cloud,
         | then gemini-cli responds and sends notifications back.
         | 
         | Basically just saving you the hassle of cloning at a specific
         | commit, calling gemini-cli manually, and then uploading the
         | result manually.
        
           | elpakal wrote:
           | 100. That's essentially the function of a GH Action, which is
           | why I'm also confused by the pomp and circumstance of the
           | announcement.
           | 
           | Now if they could get Gemini (the LLM) to run on a GH Actions
           | runner I'd be more excited.
        
         | energy123 wrote:
         | They need a boundary between their research culture and their
         | software culture. One org, two cultures.
         | 
         | The chaos you describe is actually a significant positive in
         | research environments. It's not spreading oneself thin, it is
         | diversifying and decorrelating ones' efforts. You can't
         | centrally plan all innovation.
         | 
         | But for the interface between the customer and the research
         | output, which is a software and product problem, that
         | definitely needs a different approach.
        
           | thecupisblue wrote:
           | Completely agree - the research output should be integrated
           | into a customer facing product, instead they are trying to
           | integrate customers into into research output.
        
         | barrkel wrote:
         | Jules works in a VM, asynchronously, on a separate checkout of
         | the code.
         | 
         | Gemini CLI works synchronously with the user (unless you YOLO)
         | and in your own directory on your own machine on your own
         | checkout.
         | 
         | Two different modalities.
        
           | artdigital wrote:
           | And Gemini CLI github action (this project) runs again in a
           | VM (github action runner) on a separate checkout of the code.
           | This is what OP meant with multiple coding agents.
        
             | overfeed wrote:
             | > This is what OP meant with multiple coding agents.
             | 
             | It may be the same coding agent behind the GHA. I question
             | the implicit declaration behind OPs critique: that all
             | 160,000+ Google folk should offer a single coding agent to
             | their billions of users (or whatever the TAM is for coding
             | agents). This is akin to criticizing Google Cloud for
             | having VM, Kubernetes clusters and AppEngine;
             | superficially, these products solve the same problem.
             | 
             | FWIW - this Github Actions integration is close to my ideal
             | AI agents workflow[0]. I don't want to metaphorically look
             | over my agents shoulder as it works in a specialized,
             | vendor-locked IDE. I want agents to work asynchronously,
             | taking however long they need, and tackling multiple tasks,
             | with PRs/CLs as the unit of work. Current models may not be
             | up to the task of single-shotting this, but the task is
             | parallelizable across multiple agent-instances & the best
             | solution selected (climate change be damned). I suspect
             | Github alone may not provide adequate context as it may be
             | missing previous tickets and design documents & the back-
             | and-forth on requirements, but it's a start, and I'm glad
             | Google is exploring this path for agents.
             | 
             | 0. I believe in this workflow so much I created a proof-of-
             | concept project that reads tickets from Vikunja and creates
             | PRs using Aider some weeks back.
        
         | nstart wrote:
         | Also, if you are on Google Workspace, then everything changes
         | there too. Activating the Gemini CLI is a smile while crying
         | emoji kind of activity if you are trying to provide this to an
         | entire organization [1]
         | 
         | [1]: https://github.com/google-gemini/gemini-
         | cli/blob/main/docs/c...
        
         | lubujackson wrote:
         | Face it, they have hit the "Yahoo phase" of their company life.
         | It was a good, long run. All that remains is buying larger and
         | larger successful startups and grinding them in to dust.
         | 
         | But the the "sunsetting" of projects good or bad, random
         | shotgun approaches to everything, super awesome islands of
         | product that slowly get bled dry... it is a failure of
         | management structure, not just management.
         | 
         | I don't know the guts of Google, but I imagine there are 500
         | VPs (or equivalent) each with their pet project, each trying to
         | curry favor with the boss who sent an email blast to "go big on
         | Gemini". It feels like many teams just dropped their old busted
         | projects and moved on to the new hotness, to hell with the
         | customers, consistency or revenue. The only metric now is
         | "Gemini engagement".
        
           | realprimoh wrote:
           | People have been saying this for the last 10 years.
        
       | jtrn wrote:
       | The amount of time I have to spend on investigations, to
       | understand the basics of what something ACTUALLY IS, never ceases
       | to amaze me. Having to scrape away buzzwords, ill-conceived
       | descriptions, and unnecessary verbose stuff... it's tiresome.
       | 
       | So i THINK this is what it IS:
       | 
       | A GitHub Action that can be included in GitHub workflow YAML
       | files. It executes the Gemini CLI, passing in prompts, repo
       | context, and event data (like issue text or PR diffs) to generate
       | responses or perform actions. In other words: it's a wrapper that
       | installs and runs the Gemini CLI inside GitHub Actions
       | environments.
       | 
       | It can use GitHub's API (via tokens or apps) to read repo data
       | (issues, PRs, code) and write back (e.g., add labels, comments,
       | or code suggestions). It makes calls to standard HTTPS API
       | endpoints for Gemini LLM" (via the CLI's backend interactions
       | with Google's Gemini API)
        
         | mohsen1 wrote:
         | it says "in the chat interface" write this and that. what chat
         | interface?
        
           | fhinkel wrote:
           | That description is 100% correct!
           | 
           | In this case, the "chat" happens as a comment on an issue or
           | PR addressing @gemini-cli
        
         | bredren wrote:
         | If you have it right, there is a brief discussion on semantic
         | linting in this recent interview with Boris Cherny and
         | Catherine Wu on the Latent Space podcast related to AI-assisted
         | CLI behavior here:
         | https://www.youtube.com/watch?v=zDmW5hJPsvQ&t=1760s
         | 
         | I've not explored this use of CC yet, anyone actively using AI-
         | assisted CLI in CI/CD? Not automated PR review but either to
         | semantically pass / fail an MR or some other use of terminal-
         | capable, multi-context mashup during CI/CD?
        
       | artdigital wrote:
       | I wonder why they call this `gemini cli`, it's not really a CLI
       | anymore when it's primarily used through GitHub, is it?
       | 
       | Why not follow Claude Code naming with this and just call it
       | `gemini github action` or `run gemini`?
        
         | brtkwr wrote:
         | I wondered the same thing, naming things is hard but they've
         | royally screwed up the naming here.
        
           | apwell23 wrote:
           | not surprising from a company that greenlighted the name
           | 'bard' for their AI.
        
         | dcre wrote:
         | My guess is that it was built by the Gemini CLI team and
         | institutional pressures caused this name, either to make sure
         | they get credit, or to avoid making it sound like they're
         | taking over a very broad product area.
        
         | Workaccount2 wrote:
         | This is an add-on to Gemini-CLI, which is entirely local.
        
         | fhinkel wrote:
         | Because it installs gemini-cli in the GitHub Action VM and then
         | passes the comment from the issue/PR as prompt to gemini-cli.
        
       | brtkwr wrote:
       | It seems too good to be true that this is free, unless training
       | data is the price we'll end up paying with. Also there is no
       | option to opt-out which is all the more sinister. I guess it
       | should be used with caution in private/internal repos.
        
       | v5v3 wrote:
       | Isn't there not a trademark issue over naming it Gemini CLI
       | GitHub Actions?
       | 
       | As Microsoft own GitHub and it's a competitor.
        
         | dcre wrote:
         | If that was the case, nobody but GitHub could build actions.
         | There is a whole GitHub Actions Marketplace and Google is in
         | there.
         | 
         | https://github.com/marketplace/actions/run-gemini-cli
        
         | coredog64 wrote:
         | Having seen this play out at another hyperscaler, the practical
         | distinction is that as long as the non-GH product name comes
         | first, that's enough to avoid confusion.
        
       | hi_hi wrote:
       | I may not have fully grasped this, but on the surface, it looks
       | like they want me to have an AI agents inserted directly into my
       | git workflow...like right there with all my wonderful juicy code?
       | Is that correct?
       | 
       | Isn't this a recipe for disaster, or is all the FUD around agents
       | wrecking havoc getting to me? I love Claude Code, but it can be
       | somewhat bonkers and is at least at arms length from doing any
       | real damage to my code (assuming I'm following good dev
       | practices, and don't let it loose on my wider filesystem).
        
         | HatchedLake721 wrote:
         | What's wrong with receiving code/security/MR review comments
         | from AI?
        
       | yahoozoo wrote:
       | Not a fan of agents that require and can't function without
       | access to your GitHub repository. They should be local first.
        
         | esafak wrote:
         | gemini-cli is very much local. This GH integration is new.
        
       | hotfixguru wrote:
       | I find their image text for the third image in the carousel
       | funny:
       | 
       | > Delegate work with an "@ mini-cli" tag and the agent can
       | complete a range of tasks, from writing bugs to fixing bugs
        
         | stabbles wrote:
         | Surprisingly it's not fixed in the meantime. Maybe they were
         | being honest.
        
       | TNWin wrote:
       | Sorry to be blunt, but Google needs a better Product Marketing
       | team.
       | 
       | As an engineering manager with an AI budget, I'm always looking
       | for better and cheaper tools.
       | 
       | I have a decade of engineering experience and consider myself
       | fairly intelligent.
       | 
       | I still can't figure out what this is, who it's for, or how much
       | it costs.
        
         | fantasizr wrote:
         | It's been going on for years
         | 
         | https://x.com/tomgara/status/1587640766696140800?lang=en
         | 
         | "It's pretty simple: Google Meet (original) was previously
         | Meet, which was the rebranded Hangouts Meet. Meet has been
         | merged with Google Duo, which replaced Google Hangouts. Google
         | Duo has been renamed Meet, and Meet has been temporarily named
         | Google Meet (original), for clarity"
        
       | ncrmro wrote:
       | We've been having really good results with Copilot Agent.
       | Sometimes we have to close a PR and refine the issue or pull down
       | and work locally on cursor but it also jumpstarts a lot of stuff.
        
       | gundmc wrote:
       | This sounds like Gemini Code Assist rebranded under the
       | successful Gemini CLI banner. I'm sure this was done to
       | "consolidate" offerings and brands, but this is just way more
       | confusing. CLI has a meaning, and this doesn't seem to have a CLI
       | at all? Product looks cool, but the naming is just baffling
        
         | neuronexmachina wrote:
         | I _think_ this would be API-based pricing, while Gemini Code
         | Assist is flat-rate. I 'm not sure what other differences there
         | are, though.
        
       | rurban wrote:
       | I tried this out last month. It was useful to summarize big PR's,
       | and even found minor issues. But nothing really useful for
       | professionals, only for overworked open source maintainers to
       | review and feedback newbies.
        
       | stillsut wrote:
       | Last year, I was actually working on a bounty platform for Github
       | PR's.
       | 
       | The low quality human-authored PR's that came in (due to the
       | incentive we offered) combined with the fact that a draft PR
       | could be made for pennies with AI made this concept dead in the
       | water as far as I'm concerned.
       | 
       | The pain point of getting some attention and action on your
       | opensource codebase is really no longer relevant, in fact the
       | pain point seems to be moving to how to optimize the limited
       | reviewer / maintainer bandwidth under the onslaught of proposed
       | suggestions.
       | 
       | To this end I've been experimenting with a framework that builds
       | PR's from the major agents and but with a focus on how to
       | structure the tasks and review process that optimize the review
       | => accept/revise cycle. If you're interested I've been writing up
       | some case studies here:
       | https://github.com/sutt/agro/blob/master/docs/case-studies/a...
        
       | grogenaut wrote:
       | I understand Google feels they need to compete in coding AI. The
       | crazy thing to me is:
       | 
       | - Gemini can't make me a calendar appointment between myself and
       | another person for 30 minutes in the next week. Heck it can't
       | make appointments yet. - it can't edit or collaborate on Google
       | docs, just insert. I edit my docs in cline or Claude code as
       | markdown and upload. - speaking of, I don't think they have a MCP
       | for working with docs or sheets - Gemini is worse than a Google
       | search at helping me with sheet formulas
       | 
       | There's all these unique places in googles ecosystem I feel they
       | could/should be excelling at AI at. They're not.
       | 
       | Hell I noticed yesterday searching for my remarkable preorder
       | from years ago that you can't exact string search Gmail anymore.
       | Searching for remarkable was pulling up "amazing". They're just
       | degrading all of their products to stupidity at a time when I and
       | AI can use more powertools
        
         | vidarh wrote:
         | Yeah, I figured I'd try Gemini for Google Docs, but given how
         | restricted it is, why would I?
        
           | danudey wrote:
           | "Take each H1 heading and split that section off into a
           | separate document tab"
           | 
           | A simple but tedious task that I wanted to do for a large
           | document. Nope, Gemini says it can't do that. It offered to
           | tell me HOW to do it though!
           | 
           | Is there something Gemini can actually do that's useful?
        
             | dkdcio wrote:
             | I did something similar after copy/pasting Markdown into a
             | Google Doc, assuming Gemini could obviously convert the
             | section headers and such...nope!
             | 
             | combined with separate plans to use the Gemini CLI, it's an
             | incredibly goofy situation
        
           | northern-lights wrote:
           | I asked Gemini to create a chart from the tabular data I had,
           | and nope, it can't do that.
        
         | james2doyle wrote:
         | I've actually been using Gemini on my phone to create
         | appointments from details on my screen. For example, I have a
         | delivery coming so there is an email with the date and time
         | range. I can press and hold my power button and Gemini pops up.
         | I press a button to use screen context. Then say, "put this in
         | my calendar". Then it does. It isn't perfect. Events that cross
         | multiple days or odd location details in the description
         | sometimes don't get included. But that is more and more rare.
         | I'm using an Android phone. So maybe that is why it seems to
         | work. I do see that "mostly works" is not the same as "always
         | works".
         | 
         | Also, if you are a Google Workspace customer, you can connect
         | your workspace to the Gemini web app. It can then search and
         | manipulate your calendar and your drive. It will also summarize
         | documents and a few other tasks. I have less use for this but
         | it is far from "it _can't_ make appointments".
        
           | grogenaut wrote:
           | google workspaces gemini web app keeps saying it can't alter
           | my calendar
           | 
           | gemini in calendar says it can't alter my calendar
        
         | pphysch wrote:
         | > Heck it can't make appointments yet. - it can't edit or
         | collaborate on Google docs, just insert.
         | 
         | I'm sure it's _capable_ of doing those things, but they have it
         | turned off because of the significant risks involved in
         | automatically editing important documents like that.
        
           | thewebguyd wrote:
           | I suspect this is the case, much like with Apple Intelligence
           | as well. Case in point, see the early Apple notification
           | summaries of text messages. "Mom: That hike killed me!" AI
           | Summary: "Mom died on hike."
           | 
           | All it needs though is a sandbox to execute the action in,
           | and an approval flow for the user to review the changes the
           | agent wants to make, or make revisions. Why does it have to
           | be all or nothing? "Hey Google, schedule a meeting with x for
           | next week when we are both available" "Google: OK, here's a
           | preview of the calendar invite - do you want me to send it,
           | or make changes, or cancel?"
        
           | grogenaut wrote:
           | if it's not trustworthy just fork the doc and let people try
           | it and then copy paste back in...
           | 
           | instead I'm just pulling it out to other tools and using
           | markdown import. I'm basically moving away from using google
           | docs because of these issues.
        
         | mcoliver wrote:
         | Could not agree more. Trying to use Veo3 via genai/vertexai
         | sdks has been full of dead ends, broken specs, and confusion.
         | Good ole curl seems to work though.
        
         | pmcf wrote:
         | I think Google doesn't turn Gemini loose on docs the same
         | reason Apple doesn't turn AI loose on your phone. It's just not
         | reliable enough to let 99.99% of the world use it. Those of us
         | on the bleeding edge have been fine tweaking and working with
         | inconsistencies. If you put a lot of work in, you get a
         | productivity boost. Think of the family member you are "tech
         | support" for. (You know who you are) would you recommend that
         | to them? Yeah. Me neither.
        
           | grogenaut wrote:
           | I get your point, it's sad. But your family memeber isn't
           | hooking a docs MCP up to an AI and doing things. Docs also
           | has history, I can just undo the dumb crap it would do.
           | 
           | In the meanwhile the rest of us are running around with a
           | pole that has a chainsaw generator on it swinging it in every
           | direction to solve problems. When I have these issues now I
           | just have AI write tools to get around it. To search my email
           | I just had ai crack my takeout files and look for the email.
           | Was easier than figuring out the google product.
        
         | moltar wrote:
         | Totally agree. It's so surprising that I spent almost an hour
         | trying to figure out how to make Gemini collaborate with me on
         | a Google Document as a kind of artifact. I was sure I was just
         | holding it wrong. I couldn't believe it wasn't a feature. Even
         | when I gave up I was still unsure if maybe my account isn't on
         | the right tier or something.
        
         | schainks wrote:
         | I 100% agree with this, and there are just _so many use cases_
         | that are small and useful like this.
         | 
         | Heck, just yesterday my partner forgot the grocery list
         | printout so I took a picture of it and asked gemini to convert
         | it to a format where I could copy and paste it to a specific
         | todo list app that was already shared with her. INSTEAD, Gemini
         | dumped the list into Google Keep, albeit with terrible
         | formatting. Didn't miss a single item, but did not recognize
         | categories of item (produce vs frozen food, for example)
         | 
         | So my read on it is there's a lot of "rough around the edges"
         | use cases which can be tidied with better prompting/context or
         | just Gemini team prioritizing those things when they get around
         | to it.
         | 
         | What they actually _need_ is a marketing team showing off
         | useful applications of the releases more often. OpenAI is ALL
         | OVER TIKTOK and people I meet under 30 on that platform don't
         | even know gemini exists. In my experience, Gemini is better
         | than chatGPT at everything you need to do, and it can do the
         | things that the OpenAI marketing people are constantly showing
         | off on TikTok.
        
         | machiaweliczny wrote:
         | There's a need for better indexing. Seems like they switched
         | search to pure embeddings and it doesn't work. Making
         | performant hybrid search is hard in the sense that you cannot
         | combine indexes. Ideally something like embedding, text match
         | and quality vector. I had PoC that worked great when using
         | those but making it scale is hard with reasonable latency.
         | 
         | If something like this exist please educate me as this would
         | make tons of products better.
        
       | ssalka wrote:
       | Maybe a skill issue, but I've tried using Gemini 2.5 Pro in
       | Cursor several times, and each time it is an abundance of
       | thinking and very little (often incorrect) actions. Claude Sonnet
       | is cheaper and much more effective for me.
       | 
       | Having a hard time imagining the GHA integration will be much
       | different.
        
       | elpakal wrote:
       | I'm just here for the PR review feature
        
         | toephu2 wrote:
         | GitHub already has that built in if you pay for Copilot
        
       | PanMan wrote:
       | The setup for this is So confusing. I had cursor bugbot (and
       | copilot, but that's github themselves) where it was just a few
       | clicks. Here it's a command line tool you can install in github
       | but you also need a google cloud project?
        
       ___________________________________________________________________
       (page generated 2025-08-07 23:00 UTC)