Meta launches Muse for Small Business, an AI assistant that could build growth plans from sales and ad data
The new business features connect the existing Muse app to tools such as Shopify, QuickBooks and Stripe.
Meta says owners can also ask it to review monthly finances for unusual expenses. It must get approval before publishing, sending messages or spending money.
The service is available in the US and Canada.
The new business features connect the existing Muse app to tools such as Shopify, QuickBooks and Stripe.
Meta says owners can also ask it to review monthly finances for unusual expenses. It must get approval before publishing, sending messages or spending money.
The service is available in the US and Canada.
Turn incoming client emails into an action checklist
A client’s email may mix background information, requests and deadlines. Grok Automations can extract the tasks whenever a matching message arrives. This setup needs a paid SuperGrok plan, a Gmail account and the client’s sender address.
1. Open Grok Connectors. Choose New Connector → Gmail, sign in and approve the requested access. Reading email is enough for this task.
2. Open Automations and create an automation named “Client email checklist”. Under Add Trigger, choose an email trigger for your connected mailbox. Set the sender filter to the client’s email address. Add a subject filter if you only want messages about one project.
3. Paste this into Instructions:
4. Choose an app notification or email notification, then save. When the next matching email arrives, open the automation’s run history and inspect the result.
Compare the checklist with the original message: are the tasks assigned to the right person, and are the deadlines accurate? If Grok adds a task the client never requested, tighten the instructions before relying on later results.
A client’s email may mix background information, requests and deadlines. Grok Automations can extract the tasks whenever a matching message arrives. This setup needs a paid SuperGrok plan, a Gmail account and the client’s sender address.
1. Open Grok Connectors. Choose New Connector → Gmail, sign in and approve the requested access. Reading email is enough for this task.
2. Open Automations and create an automation named “Client email checklist”. Under Add Trigger, choose an email trigger for your connected mailbox. Set the sender filter to the client’s email address. Add a subject filter if you only want messages about one project.
3. Paste this into Instructions:
Read the email that triggered this run. Turn it into a short checklist for me, the recipient.
Start with the sender, subject and a one-sentence summary.
Then list:
- Actions explicitly requested of me.
- The deadline for each action, exactly as written. If none is given, say "No deadline stated".
- Questions I need to answer.
Separate other people's tasks from mine. Quote the short passage supporting each action and deadline. Flag unclear wording instead of guessing. If no action is requested, say so.
Use only this email. Do not send replies or change my mailbox.
4. Choose an app notification or email notification, then save. When the next matching email arrives, open the automation’s run history and inspect the result.
Compare the checklist with the original message: are the tasks assigned to the right person, and are the deadlines accurate? If Grok adds a task the client never requested, tighten the instructions before relying on later results.
OpenAI launches Dots: AI assistants that can notice work you forgot to do
OpenAI reports that an early tester’s dot noticed he had not billed a publication. It prepared the invoice and sent it after his approval.
Each dot has its own cloud computer and keeps project context between chats. It can continue working while your computer is off.
Background research can read connected apps, but cannot send messages or change their content. Further actions depend on permissions.
OpenAI reports that an early tester’s dot noticed he had not billed a publication. It prepared the invoice and sent it after his approval.
Each dot has its own cloud computer and keeps project context between chats. It can continue working while your computer is off.
Background research can read connected apps, but cannot send messages or change their content. Further actions depend on permissions.
Your awkward walk could give a game character its personality
A beginner game maker needs a character to sneak away looking guilty. A normal walking animation feels wrong. This character needs the tiny pause, the nervous turn, the careful steps of someone who definitely ate the last biscuit.
The creator could act it out for a phone camera. DeepMotion Animate 3D turns video of human movement into 3D animation that can be applied to a compatible humanoid character. No motion-capture suit is required.
The software estimates how the body moves through space and uses that motion to animate the character’s digital skeleton. That gives the creator’s own timing and body language a route into the game. The hesitation can be performed, instead of built entirely by adjusting poses by hand.
It still takes some cleanup. A clear view of the whole body matters; hidden limbs make movement harder to interpret. Sliding feet or an incorrect pose can turn a guilty escape into an accidental skating routine.
The interesting part is how personal this can be. A ready-made walk supplies movement. A slightly ridiculous performance can supply character. For a beginner, acting becomes another way to make something original—even if the first audience is just a phone balanced on a shelf.
A beginner game maker needs a character to sneak away looking guilty. A normal walking animation feels wrong. This character needs the tiny pause, the nervous turn, the careful steps of someone who definitely ate the last biscuit.
The creator could act it out for a phone camera. DeepMotion Animate 3D turns video of human movement into 3D animation that can be applied to a compatible humanoid character. No motion-capture suit is required.
The software estimates how the body moves through space and uses that motion to animate the character’s digital skeleton. That gives the creator’s own timing and body language a route into the game. The hesitation can be performed, instead of built entirely by adjusting poses by hand.
It still takes some cleanup. A clear view of the whole body matters; hidden limbs make movement harder to interpret. Sliding feet or an incorrect pose can turn a guilty escape into an accidental skating routine.
The interesting part is how personal this can be. A ready-made walk supplies movement. A slightly ridiculous performance can supply character. For a beginner, acting becomes another way to make something original—even if the first audience is just a phone balanced on a shelf.
Fix a failing test on your development server with Codex
If your project already runs on a remote server, Codex can edit its files and run tests there using the existing environment.
You need the current ChatGPT desktop app on your Mac with Codex access, working SSH credentials, and a remote project with its dependencies installed. Codex must also be installed and signed in on the server, with the
1. Add a named host to
2. Run
3. In the ChatGPT app, open Settings → Connections → SSH. Add or enable the host, then select the project folder on the server. These are the steps in OpenAI’s SSH setup guide.
4. Start a chat in that remote project. Replace the brackets below with your test command and failure details:
5. Review the changed files. Confirm the original test actually ran and passed, rather than being skipped. Run the same test yourself in the server’s project folder before committing the fix.
If your project already runs on a remote server, Codex can edit its files and run tests there using the existing environment.
You need the current ChatGPT desktop app on your Mac with Codex access, working SSH credentials, and a remote project with its dependencies installed. Codex must also be installed and signed in on the server, with the
codex command available in your remote login shell.1. Add a named host to
~/.ssh/config on your Mac. Replace the example address, username and key path with your own:Host devbox
HostName devbox.example.com
User you
IdentityFile ~/.ssh/id_ed25519
2. Run
ssh devbox in your Mac’s terminal. Resolve any connection errors before continuing. Run exit to return to your Mac.3. In the ChatGPT app, open Settings → Connections → SSH. Add or enable the host, then select the project folder on the server. These are the steps in OpenAI’s SSH setup guide.
4. Start a chat in that remote project. Replace the brackets below with your test command and failure details:
Reproduce this failing test: [test command and error].
First confirm the hostname, project directory and Git branch. Check for existing uncommitted changes and preserve them.
Find the cause and make the smallest necessary fix. Do not weaken the test to make it pass.
Rerun the failing test and relevant nearby tests. Show the diff, exact commands and results. Do not commit or deploy.
5. Review the changed files. Confirm the original test actually ran and passed, rather than being skipped. Run the same test yourself in the server’s project folder before committing the fix.
Dyna shows its Taku robot handling hotel laundry from washer to shelf in an hour-long demo
The company’s uncut demonstration shows it pausing towel folding to attend to a dryer, then resuming where it left off. Its AI tracks machine status and towel counts in text memory to choose the next task.
Dyna’s earlier folding system needed people to supply towels and remove finished stacks. Automating these handoffs could mean less supervision for hotel staff. The demo does not establish reliable operation across a full shift.
The company’s uncut demonstration shows it pausing towel folding to attend to a dryer, then resuming where it left off. Its AI tracks machine status and towel counts in text memory to choose the next task.
Dyna’s earlier folding system needed people to supply towels and remove finished stacks. Automating these handoffs could mean less supervision for hotel staff. The demo does not establish reliable operation across a full shift.
The same photo, different files. AI can spot it.
A birthday photo can appear in your camera backup, chat downloads and old exports. Compressed or resized copies may escape an exact duplicate check, which compares file contents. Renaming alone does not fool it.
Immich, a photo library you run on your own server, uses machine learning to group visually similar pictures for review. Your library can stay on your own hardware.
The key distinction is identical files versus similar pictures. A compressed copy may be redundant; a deliberate edit or a frame where everyone has their eyes open may be worth keeping.
AI finds likely copies. You decide what to remove, recover space and keep the versions that matter.
A birthday photo can appear in your camera backup, chat downloads and old exports. Compressed or resized copies may escape an exact duplicate check, which compares file contents. Renaming alone does not fool it.
Immich, a photo library you run on your own server, uses machine learning to group visually similar pictures for review. Your library can stay on your own hardware.
The key distinction is identical files versus similar pictures. A compressed copy may be redundant; a deliberate edit or a frame where everyone has their eyes open may be worth keeping.
AI finds likely copies. You decide what to remove, recover space and keep the versions that matter.
Bad bass? The chair may matter more than new speakers
Bass booms at the desk and almost disappears a few steps away. Reflections from room surfaces can reinforce or partly cancel bass frequencies. Speaker placement and where you sit both matter.
Room EQ Wizard (REW) measurements taken with a calibrated microphone show peaks and dips at your listening position. An AI assistant can use those graphs and a room sketch to explain possible causes and suggest a small speaker or chair move to test.
REW’s room simulator can help explore positions, though its rectangular room model is an approximation. Fresh measurements and listening tell you whether a move helped.
AI turns a confusing graph into a practical experiment with equipment you already own. The next audio upgrade might simply be moving your chair.
Bass booms at the desk and almost disappears a few steps away. Reflections from room surfaces can reinforce or partly cancel bass frequencies. Speaker placement and where you sit both matter.
Room EQ Wizard (REW) measurements taken with a calibrated microphone show peaks and dips at your listening position. An AI assistant can use those graphs and a room sketch to explain possible causes and suggest a small speaker or chair move to test.
REW’s room simulator can help explore positions, though its rectangular room model is an approximation. Fresh measurements and listening tell you whether a move helped.
AI turns a confusing graph into a practical experiment with equipment you already own. The next audio upgrade might simply be moving your chair.
DeepMind adds hidden AI labels to protein designs
A watermark can show that an image was made with AI. DeepMind’s SynthID Bio brings that idea to proteins by embedding a detectable pattern in the order of their building blocks, called amino acids.
In a Nature study, researchers added these marks to existing protein designs. Lab tests showed that the marked proteins still attached to their intended targets about as well as unmarked versions.
The approach could help labs that make DNA check incoming orders for AI designs. It could also help researchers identify AI entries in biological databases.
This is an early demonstration. Changing a protein’s sequence can largely erase the mark, so it cannot reliably identify every AI-designed protein.
A watermark can show that an image was made with AI. DeepMind’s SynthID Bio brings that idea to proteins by embedding a detectable pattern in the order of their building blocks, called amino acids.
In a Nature study, researchers added these marks to existing protein designs. Lab tests showed that the marked proteins still attached to their intended targets about as well as unmarked versions.
The approach could help labs that make DNA check incoming orders for AI designs. It could also help researchers identify AI entries in biological databases.
This is an early demonstration. Changing a protein’s sequence can largely erase the mark, so it cannot reliably identify every AI-designed protein.
❤1
Google unveils Gemini 4 Argon, reporting a 2.7× speedup in video decoding
Google says its agents replaced 32,000 lines of code in an existing Rust version of the libgav1 decoder, preserving identical video output.
They repeatedly tested speed and inspected the compiler’s output. Their safe Rust code let the compiler generate parallel instructions automatically.
The gain is measured against the earlier Rust version. Google says it brings performance closer to optimized C++.
Model access is initially limited to trusted cyber defenders through Fairwind, with no firm date for a wider release.
Google says its agents replaced 32,000 lines of code in an existing Rust version of the libgav1 decoder, preserving identical video output.
They repeatedly tested speed and inspected the compiler’s output. Their safe Rust code let the compiler generate parallel instructions automatically.
The gain is measured against the earlier Rust version. Google says it brings performance closer to optimized C++.
Model access is initially limited to trusted cyber defenders through Fairwind, with no firm date for a wider release.
Perplexity brings paid market data into an AI conversation
Perplexity’s Premium Sources lets its Computer assistant search selected data from PitchBook, CB Insights and Statista: private company funding, industry research and market estimates.
Computer picks relevant sources and cites the originals. Small teams can explore competitors’ funding and market demand in one conversation, without separate subscriptions to those providers.
Access covers selected material, not full databases. It requires Pro or Max on the web and available Computer credits. Runs consume credits; Pro has no recurring monthly allowance, while Max includes one.
Perplexity’s Premium Sources lets its Computer assistant search selected data from PitchBook, CB Insights and Statista: private company funding, industry research and market estimates.
Computer picks relevant sources and cites the originals. Small teams can explore competitors’ funding and market demand in one conversation, without separate subscriptions to those providers.
Access covers selected material, not full databases. It requires Pro or Max on the web and available Computer credits. Runs consume credits; Pro has no recurring monthly allowance, while Max includes one.
❤1
A half-remembered tune can be a search query
You remember a song from childhood car journeys. The chorus is still there, but the title and every useful lyric have vanished. Your brain kept the soundtrack and threw away the label.
Google’s Hum to Search can work with that fragment. It compares a hummed melody with recorded songs, even when your voice, pitch or speed differs from the original.
The clever part is making two very different sounds comparable: your kitchen humming and a studio recording with a whole band. The model turns each into a numerical representation that emphasizes the melody. Similar melodies should end up close together, despite the missing drums or your unexpected solo career. That is the principle behind Google’s system.
The results are possible matches, with listening providing the moment of recognition. A familiar phrase might bring back the whole chorus. A tune invented by someone in your family, however, may have no recording in the catalogue to match.
What makes this useful goes beyond music recognition: a memory can become searchable before you can put it into words. Sometimes you have no idea what to type, yet still know exactly how something goes.
You remember a song from childhood car journeys. The chorus is still there, but the title and every useful lyric have vanished. Your brain kept the soundtrack and threw away the label.
Google’s Hum to Search can work with that fragment. It compares a hummed melody with recorded songs, even when your voice, pitch or speed differs from the original.
The clever part is making two very different sounds comparable: your kitchen humming and a studio recording with a whole band. The model turns each into a numerical representation that emphasizes the melody. Similar melodies should end up close together, despite the missing drums or your unexpected solo career. That is the principle behind Google’s system.
The results are possible matches, with listening providing the moment of recognition. A familiar phrase might bring back the whole chorus. A tune invented by someone in your family, however, may have no recording in the catalogue to match.
What makes this useful goes beyond music recognition: a memory can become searchable before you can put it into words. Sometimes you have no idea what to type, yet still know exactly how something goes.
Create a reusable bug review for your Git branch
Before merging code, you may want separate checks for logic errors and missing tests. Grok Build can save that process as a workflow, with another agent checking the findings before you read the report.
You need a local Git repository, a branch with committed changes, and Grok Build installed and signed in. Tests require the project’s dependencies.
1. Follow the Grok Build setup guide. In your terminal, open the project folder and run
2. Paste this into Grok Build:
Answer its questions about scope. Ask it to save the workflow in the project. Grok creates and smoke-checks the workflow; that check does not prove its reviews will be correct.
3. Launch it with the comparison you need:
This example reviews committed branch changes since the shared ancestor with
Use
Before acting on a finding, open the cited lines and try its reproduction steps or relevant test. A useful finding should demonstrate an actual failure; a report with no findings is not proof that the branch is bug-free.
Before merging code, you may want separate checks for logic errors and missing tests. Grok Build can save that process as a workflow, with another agent checking the findings before you read the report.
You need a local Git repository, a branch with committed changes, and Grok Build installed and signed in. Tests require the project’s dependencies.
1. Follow the Grok Build setup guide. In your terminal, open the project folder and run
grok. First launch opens a browser for authentication.2. Paste this into Grok Build:
/create-workflow Create a project workflow named review-changes. Accept a target argument containing a Git diff range. Review only changes in that range, reading surrounding code when needed. Use two parallel reviewers: one for logic bugs, one for missing tests and edge cases. Then use a separate verifier to check each finding against the code and available tests. Do not edit project files or install dependencies during a review. Return one report with confirmed findings, file and line references, likely impact, and reproduction steps. Put unverified concerns in a separate section and say which tests could not run.
Answer its questions about scope. Ask it to save the workflow in the project. Grok creates and smoke-checks the workflow; that check does not prove its reviews will be correct.
3. Launch it with the comparison you need:
/workflow review-changes {"target":"origin/main...HEAD"}
This example reviews committed branch changes since the shared ancestor with
origin/main. Replace that reference if your base branch has another name, and fetch the remote first if your local reference is stale.Use
/workflows to view progress. For a later branch, run the saved workflow again with the appropriate diff range. The workflow documentation covers these commands.Before acting on a finding, open the cited lines and try its reproduction steps or relevant test. A useful finding should demonstrate an actual failure; a report with no findings is not proof that the branch is bug-free.
Perplexity releases an AI model for routine business decisions
The new model helps developers build apps that sort incoming information into predefined categories.
For example, a customer reports a broken integration. The model can assess which support team should handle it and how urgent it is. It returns probabilities for the available options, so an app could route the request automatically or send an uncertain case to a person.
This could reduce manual sorting in customer support. The model handles classification; it does not write replies to customers.
Developers can use Perplexity’s paid API or download the model to run on their own hardware. Running it locally requires a powerful GPU.
The new model helps developers build apps that sort incoming information into predefined categories.
For example, a customer reports a broken integration. The model can assess which support team should handle it and how urgent it is. It returns probabilities for the available options, so an app could route the request automatically or send an uncertain case to a person.
This could reduce manual sorting in customer support. The model handles classification; it does not write replies to customers.
Developers can use Perplexity’s paid API or download the model to run on their own hardware. Running it locally requires a powerful GPU.
Nurses say an AI scheduling tool creates extra work
Timpani is an AI tool built by Palantir for HCA Healthcare, a hospital operator. It helps create nurses’ work schedules: who works on which days and shifts.
WIRED interviewed six nurses about the tool. They said they had to spend time fixing their schedules. One nurse, Amber Retzloff, said it failed to follow more than half of her 50 shift requests. Nurses also reported shifts with too few nurses or too few experienced staff.
HCA says Timpani saves managers time. It also says nursing leaders still have the final say on schedules.
To understand whether the tool helps overall, we need to count both the time managers save and the time nurses spend fixing schedules.
Timpani is an AI tool built by Palantir for HCA Healthcare, a hospital operator. It helps create nurses’ work schedules: who works on which days and shifts.
WIRED interviewed six nurses about the tool. They said they had to spend time fixing their schedules. One nurse, Amber Retzloff, said it failed to follow more than half of her 50 shift requests. Nurses also reported shifts with too few nurses or too few experienced staff.
HCA says Timpani saves managers time. It also says nursing leaders still have the final say on schedules.
To understand whether the tool helps overall, we need to count both the time managers save and the time nurses spend fixing schedules.
Gemini can control several smart home devices in one request
Switching off the bedroom lights and TV can be one request to Gemini on Android. No need to open separate controls for each device.
Its Google Home connection works with compatible lights, thermostats and other smart home devices. You can name the devices or describe the change you want in a room. Google Home connects the devices; Gemini interprets your request.
For example, you can ask it to adjust the air conditioning for sleep or start a robot vacuum in the kitchen. More precise controls work too: dimming lights to 50%, lowering the temperature by two degrees or pausing the TV.
To connect it, open Gemini with the account you use for Google Home. Ask it to control a device and follow the connection prompt. If Gemini doesn’t pick Google Home, include @Google Home in your request:
Once connected, you can also start Google Home routines by voice or text.
Switching off the bedroom lights and TV can be one request to Gemini on Android. No need to open separate controls for each device.
Its Google Home connection works with compatible lights, thermostats and other smart home devices. You can name the devices or describe the change you want in a room. Google Home connects the devices; Gemini interprets your request.
For example, you can ask it to adjust the air conditioning for sleep or start a robot vacuum in the kitchen. More precise controls work too: dimming lights to 50%, lowering the temperature by two degrees or pausing the TV.
To connect it, open Gemini with the account you use for Google Home. Ask it to control a device and follow the connection prompt. If Gemini doesn’t pick Google Home, include @Google Home in your request:
@Google Home turn off the bedroom lights and TV
Once connected, you can also start Google Home routines by voice or text.
Copilot can answer questions about your in-person meetings
Who promised to send the revised proposal? Microsoft Copilot’s Record feature lets you ask after the meeting ends—even if it never happened in Teams.
The mobile app records the conversation, saves the audio to your work OneDrive, and creates a transcript and summary in Copilot Chat. You can ask follow-up questions, identify commitments or draft a recap. The original audio stays available.
Each recording can last up to 120 minutes. Recording continues while you use other apps on your phone, so you can check a document or your calendar without stopping it.
Who promised to send the revised proposal? Microsoft Copilot’s Record feature lets you ask after the meeting ends—even if it never happened in Teams.
The mobile app records the conversation, saves the audio to your work OneDrive, and creates a transcript and summary in Copilot Chat. You can ask follow-up questions, identify commitments or draft a recap. The original audio stays available.
Each recording can last up to 120 minutes. Recording continues while you use other apps on your phone, so you can check a document or your calendar without stopping it.
Voice control that survives an internet outage
The internet is down. Your video call has frozen, but the desk lamp still responds to your voice. Apparently, switching on a light never needed a trip to a distant data centre.
Home Assistant’s local voice setup makes this possible by keeping the conversation inside your home. Speech-to-Phrase recognises supported commands, Home Assistant handles the request, and Piper speaks the reply. Even a small computer such as a Raspberry Pi 4 can run these speech tools, without sending recordings to an outside speech service.
The crucial detail is the path from your voice to the bulb. The lamp must also support local control. A bulb that depends on its manufacturer’s cloud still depends on the internet, however clever the voice recognition beside it becomes. Your home network and the computer running Home Assistant must stay powered and working.
There is a tradeoff: setup takes some effort, and Speech-to-Phrase understands a limited set of commands rather than unrestricted conversation.
For a desk lamp, that may be plenty. It needs to understand the request, not discuss your reading choices. Local AI independence can be as ordinary as a light that still listens when the internet stops.
The internet is down. Your video call has frozen, but the desk lamp still responds to your voice. Apparently, switching on a light never needed a trip to a distant data centre.
Home Assistant’s local voice setup makes this possible by keeping the conversation inside your home. Speech-to-Phrase recognises supported commands, Home Assistant handles the request, and Piper speaks the reply. Even a small computer such as a Raspberry Pi 4 can run these speech tools, without sending recordings to an outside speech service.
The crucial detail is the path from your voice to the bulb. The lamp must also support local control. A bulb that depends on its manufacturer’s cloud still depends on the internet, however clever the voice recognition beside it becomes. Your home network and the computer running Home Assistant must stay powered and working.
There is a tradeoff: setup takes some effort, and Speech-to-Phrase understands a limited set of commands rather than unrestricted conversation.
For a desk lamp, that may be plenty. It needs to understand the request, not discuss your reading choices. Local AI independence can be as ordinary as a light that still listens when the internet stops.
Strata update lets Codex CLI use a 125-billion-parameter AI model running on a home PC
Strata is software that runs AI models locally. It uses a compressed model and draws on the graphics card, CPU, system memory and storage. It supports Windows and Linux.
The update adds an interface that lets Codex CLI send requests to Strata. Qwen3.8-Flash-Next supplies the model responses, while Codex handles tool calls and returns their results to the model. In the v0.1.39 release notes, the maintainer reports testing this loop.
The reference PC has an RTX 5070 with 12 GB of video memory and 64 GB of RAM. The model does not fit entirely in the graphics card’s memory.
Developers can use a familiar coding interface while keeping model requests on their own machine. Tools can still make network calls, so a local model does not make every task offline.
Strata is software that runs AI models locally. It uses a compressed model and draws on the graphics card, CPU, system memory and storage. It supports Windows and Linux.
The update adds an interface that lets Codex CLI send requests to Strata. Qwen3.8-Flash-Next supplies the model responses, while Codex handles tool calls and returns their results to the model. In the v0.1.39 release notes, the maintainer reports testing this loop.
The reference PC has an RTX 5070 with 12 GB of video memory and 64 GB of RAM. The model does not fit entirely in the graphics card’s memory.
Developers can use a familiar coding interface while keeping model requests on their own machine. Tools can still make network calls, so a local model does not make every task offline.
Get a small bug fix from a GitHub issue
Claude Code GitHub Actions can work on a bug while your laptop is off. A useful first task is a reproducible error with a clear expected result.
You need a repository on GitHub.com with Actions enabled, admin access for setup, and Claude Code and GitHub CLI installed locally. Authentication uses a Claude subscription token or an API key; GitHub Actions usage is accounted for separately.
1. Connect the repository once.
In its local checkout, run
Follow the prompts to install the app and configure authentication. Continue with Actions setup and select the workflow that responds to @claude mentions. Create and merge the workflow pull request opened by the installer. Official setup guide.
2. Open an issue describing one bug.
Include the steps to reproduce it, the actual result and the expected result. Add relevant file names and the test command if you know them.
For example, if an empty search crashes your app, describe exactly which page and action cause it. Then post this comment from an account with repository write access:
3. Turn the result into a reviewed pull request.
Claude updates its issue comment with progress. For issue requests, it creates a branch and can return a link to a prefilled pull request page. Follow that link and create the pull request. Documented behavior.
Review the changed files. Run the regression test and try both an empty search and a normal search. If Claude could not run checks, run them yourself before merging.
Claude Code GitHub Actions can work on a bug while your laptop is off. A useful first task is a reproducible error with a clear expected result.
You need a repository on GitHub.com with Actions enabled, admin access for setup, and Claude Code and GitHub CLI installed locally. Authentication uses a Claude subscription token or an API key; GitHub Actions usage is accounted for separately.
1. Connect the repository once.
In its local checkout, run
gh auth login, then start claude. Inside Claude Code, run /install-github-app.Follow the prompts to install the app and configure authentication. Continue with Actions setup and select the workflow that responds to @claude mentions. Create and merge the workflow pull request opened by the installer. Official setup guide.
2. Open an issue describing one bug.
Include the steps to reproduce it, the actual result and the expected result. Add relevant file names and the test command if you know them.
For example, if an empty search crashes your app, describe exactly which page and action cause it. Then post this comment from an account with repository write access:
@claude Fix the empty-search crash described above. An empty query should show “Enter a search term” without sending a search request. Keep normal searches working and avoid unrelated changes.
Add a regression test using the existing test framework. Report which checks you ran and which you could not run. Prepare the fix on a new branch for review.
3. Turn the result into a reviewed pull request.
Claude updates its issue comment with progress. For issue requests, it creates a branch and can return a link to a prefilled pull request page. Follow that link and create the pull request. Documented behavior.
Review the changed files. Run the regression test and try both an empty search and a normal search. If Claude could not run checks, run them yourself before merging.