Automation for leaders · Runs every day at 08:00
Side project brief
Daily monitoring of costs, user trends, and performance for your project. Your assistant runs it every day at 08:00 and tells you when something needs your attention.
Side project brief — Sep 17
Automation run • Sep 17
Side project brief
Output
Harbor & Pine storefront activity over the past 24 hours shows steady checkout conversion but an emerging mobile checkout latency issue after yesterday's merge.
Key metrics from Google Analytics
- Unique visitors: 1,420 across all channels, up 4 percent day over day.
- Checkout starts: 118 sessions reached step one.
- Completed orders: 38 purchases, with an overall conversion rate of 2.68 percent.
- Drop-off signal: Mobile cart-to-checkout abandonment climbed from 18 percent to 29 percent between 4:00 PM and midnight.
GitHub activity in harborpine/storefront
- Mira Sand merged pull request 214 at 3:15 PM, updating the cart drawer asset bundle.
- Two subsequent commits by Ezra Holt updated dependency lockfiles for automated security alerts.
- Automated test runs passed, but synthetic mobile page load times rose by 1.4 seconds on checkout routes right after pull request 214 merged.
Hosting and compute trends
- Build minutes remain within standard monthly quotas, with 42 minutes used yesterday.
- Serverless edge invocation count rose 12 percent, tracking the traffic bump without error spikes.
Suggested actions
- Ask Mira to inspect bundle sizing on the cart drawer scripts to recover mobile load speed.
- Keep monitoring mobile checkout drop-off through this afternoon before deciding on a revert.
No code changes or settings adjustments were made by this run.
Automation steps. Your assistant follows these 5 steps each time it runs, using your connected code.
- 01
Each day, check on my side project using its analytics and its code repository.
- 02
Brief me on costs, user behavior and performance trends, and catch early what I'd want to know: a cost spike, a drop-off, a regression.
- 03
Decide for yourself which signals are worth tracking and tell me about any I hadn't thought to ask for.
- 04
Suggest improvements the data points to.
- 05
Keep it short and decision-oriented, not a data dump.
Adjust the automation in chat
Tell your assistant what to do differently and it sets up that version for you.
- Alert me immediately if checkout conversion drops below two percent.
- Include daily hosting cost estimates alongside usage metrics.
- Focus only on commits and pull requests authored by Ezra or Mira.
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 day at 08:00 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
Monitors analytics and repository activity on its own. Changes nothing in your code or settings. 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 web analytics 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, find Side project brief in the job library, and choose Add. The card prompts you to connect GitHub and Google Analytics if they are not linked yet, and schedules runs for 8:00 AM daily.
- What does it do on its own versus wait for me?
- It reads metrics from Google Analytics and commit history from GitHub on its own. It never edits code, closes pull requests, updates repository settings, or changes your tracking properties.
- Where do the daily briefs arrive?
- Your brief lands as a message in your chat with your assistant and can also be delivered to your email inbox. If there is no new activity or anomaly to highlight, it keeps its note very brief.
- Can I run this for multiple GitHub repositories?
- Yes. Tell your assistant in chat which repositories to watch, and it will track code merges and deployment trends across all of them in the same daily report.
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.