Automation for leaders · Runs every weekday at 17:00
Team progress summary
An evening summary of shipped work, active tasks, and blocked projects. Your assistant runs it every weekday at 17:00 and tells you when something needs your attention.
Team progress summary — Sep 14
Automation run • Sep 14
Team progress summary
Output
Here is the Harbor & Pine team progress summary for Monday, September 14, 2026, gathered from GitHub and Linear.
Blocked and waiting on decisions
- Discount code stacking: Ezra Holt is waiting on your decision for Linear issue WEB-88. The checkout code needs confirmation on whether promotional codes like WELCOME10 can combine with free shipping on harborpine/storefront. Work on branch feature/discounts is paused until you decide.
Shipped today
- Mobile navigation fix: Mira Sand merged pull request 44 in harborpine/storefront, resolving Linear issue WEB-82. Mobile menu links now wrap cleanly on smaller screens.
- Warehouse inventory sync: Ezra Holt completed and closed Linear issue WEB-85, correcting stock count sync intervals between the web store and Portland Warehouse.
In progress
- Cart drawer styling: Mira Sand opened pull request 46 in harborpine/storefront for Linear issue WEB-87. It refines variant pickers for apparel sizes. Ezra Holt has been assigned to review the changes.
- Catalog query latency: Ezra Holt started work on Linear issue WEB-89 to evaluate slow database response times on collection pages. No pull request has been opened yet.
Automation steps. Your assistant follows these 3 steps each time it runs, using your connected code.
- 01
Each weekday evening, summarize what my team shipped, what's in progress, and what's blocked, from merged and open pull requests and from issue and project movement in our task tracker.
- 02
Group it by project or person.
- 03
Put anything stuck or waiting on a decision at the top, since that's where I can help, and link every item to its pull request or issue.
Adjust the automation in chat
Tell your assistant what to do differently and it sets up that version for you.
- Only include pull requests and tasks related to the storefront repository.
- Send the summary at 6:00 PM instead of 5:00 PM.
- Group the progress list by team member instead of project.
Results arrive as a message from your assistant. Each run posts to your conversation with your assistant, and can email you too. The automation keeps a log in your knowledge base and reads it before each run to see what has changed.
Adjustable schedule
Runs every weekday at 17:00 by default. Pick another time when you add it, or ask in chat for a custom schedule.
Only useful reports
When nothing needs attention, the run says so in a line or stays quiet. When there are findings, you get them with a link to the full run.
What it does on its own
Summarizes pull requests and tasks on its own. Changes nothing and sends no messages. An automated run has no tool that sends, posts, shares, or deletes anything.
This automation reads your code. Connect GitHub to Fieldwork. The automation uses whichever you connect. It also uses your tasks when connected.
More automations for leaders.
Questions about this automation.
- How do I set this up?
- Open your assistant on the Agents page in Fieldwork, locate Team progress summary in the job library, and click Add. If GitHub or your task tracker is not connected yet, the setup card prompts you to connect them before starting your weekday 5:00 PM schedule.
- Does this automation make changes in GitHub or our task tracker?
- No. It only reads activity from GitHub and your connected tracker, such as Linear, to prepare your summary. It never closes issues, merges pull requests, posts comments, or sends messages to your team.
- Where do I receive the daily summary?
- Your summary arrives as a message in your conversation with your assistant and can also be emailed to you. When there is no team activity during the day, your assistant notes it briefly or stays quiet.
- Can I run this update before 5:00 PM?
- Yes. You can ask your assistant in chat for a current progress update whenever you need one, and it will gather the latest activity on request.
Security first
No training on your data
Neither we nor our model providers train on your data. Inference runs with zero retention wherever the provider supports it.
Access
Agents only see what the person asking can see. Conversations, files, apps and connections stay private until shared, and admins have no way into conversations.
Encryption and isolation
Data is encrypted at rest and in transit. Each user's code runs in its own microVM, and secrets reach models by name only.
Continuity
Continuous backups, replicated to a second region. Data is exported on request and deleted within 30 days of a contract's end.