Automation for marketing · Runs every Friday at 10:00
Ship-to-story drafts
Changelog entries and social posts drafted from merged pull requests and tickets. Your assistant runs it every Friday at 10:00 and tells you when something needs your attention.
Ship-to-story drafts — Sep 18
Automation run • Sep 18
Ship-to-story drafts
Output
Hi Nell,
Two customer-facing changes merged this week across GitHub and Linear for Harbor & Pine. Four other pull requests covered internal build maintenance and were excluded.
Proposed drafts are below for your review. Nothing has been published or posted.
1. Product sizing charts
- Source: Linear issue WEB-142, GitHub pull request 88 by Mira Sand in harborpine/storefront
- What changed: Size guide charts now appear directly on product pages for tops and outerwear, including the Cascade Merino Crew and Ridgeline Rain Shell.
- Who it helps: Shoppers choosing between sizes before ordering.
- Proposed changelog note: We added detailed sizing charts to all tops and outerwear pages so you can find your exact fit before checking out.
- Proposed social post: Wondering whether to size up in the Cascade Merino Crew? Clear measurements and fit notes are now live on every apparel page at Harbor & Pine.
2. Delivery estimates in cart
- Source: Linear issue WEB-156, GitHub pull request 91 by Ezra Holt in harborpine/storefront
- What changed: The cart drawer now displays estimated delivery arrival windows from the Portland Warehouse before checkout.
- Who it helps: Customers planning orders for upcoming trips or gifts.
- Proposed changelog note: See delivery estimates directly in your cart before starting checkout.
- Proposed social post: Know when your gear arrives before you buy. Cart delivery dates are now live for all orders shipping from our Portland Warehouse.
Feedback and edits can be made directly, or let me know if you would like alternative phrasing.
Automation steps. Your assistant follows these 3 steps each time it runs, using your connected code.
- 01
Each Friday, scan what shipped (merged pull requests, closed feature tickets, changelog entries) and pick the handful customers would care about.
- 02
For each, draft a short take in plain English: what changed, who it helps, and why it matters, as a changelog note and a social post.
- 03
Skip internal refactors, lead with customer value, and link back to the pull request or ticket so I can verify.
Adjust the automation in chat
Tell your assistant what to do differently and it sets up that version for you.
- Only include updates from the Web team in Linear.
- Draft two alternative social post options for each update.
- Skip pull requests that only update dependencies or documentation.
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 Friday at 10:00 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
Drafts changelog updates and social posts for your review. Publishes nothing on its own. 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 marketing.
Questions about this automation.
- How do I set this up?
- Open your assistant on the Agents page in Fieldwork, locate Ship-to-story drafts in the job library, and choose Add. You will be prompted to connect GitHub and your task tracking tool such as Linear if they are not linked yet. It starts on the suggested schedule of every Friday at 10:00 AM, which you can adjust when you add it.
- What does it do on its own?
- The assistant reads merged pull requests and closed tickets, then drafts changelog entries and social posts for you to review. It never posts updates, publishes changelogs, or alters code on its own.
- Where do the results arrive?
- Drafts arrive as a message in your conversation with your assistant and can also be emailed to you. When no customer-facing features shipped during the week, it lets you know briefly or stays quiet.
- Can I run this before Friday if we release early?
- Yes, you can ask your assistant in chat to scan recent pull requests and draft updates whenever you want them. It will check your latest merged work on demand without waiting for Friday morning.
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.