Ask the Automator to watch this project folder. Whenever a new file is added — an email, a meeting note, a report, anything — read it and update project_status.md to reflect what it tells us. Keep these sections current: What's done, What's in progress, Blockers, Decisions made, What's next. Don't just append — rewrite each section so it always reflects the current state, not a log of events.
Finding the right automation tool and wiring this up.
Done — the automation is live. Here's what's now running:
| Setting | Value |
|---|---|
| Watches | project_alpha/ (all subdirectories) |
| Trigger | Any new file created — email, meeting note, report, anything |
| Action | Read new file + read project_status.md → rewrite all five sections |
| Rule | Don't append — rewrite each section to reflect current state, not a log |
The next time a file lands in the folder, this fires automatically. You don't need to do anything.
A new file has been added to the project folder. Your job is to read it and update project_status.md so it reflects the current state of the project.
STEP 1: Read the new file
Read the file at the path provided in the event data. It could be an email, meeting note, report, status update, or any other document. Extract everything relevant: decisions made, work completed, work in progress, blockers, and next steps.
STEP 2: Read the current project_status.md
Read project_status.md if it exists. Understand what is already recorded there.
STEP 3: Rewrite project_status.md
Rewrite (not append to) project_status.md so it always reflects the CURRENT state...
STEP 4: Confirm
Report back: what file was processed, what key information was extracted, and what changed.
Automation Details:
File Path: project_alpha/emails/thread_apr_22.txt
File Name: thread_apr_22.txt
File Extension: .txt
Event Type: create
Triggered at: 2026-04-22T14:47:00.000Z
Reading the new file and the current status doc, then rewriting the affected sections.
project_status.md updated. Here's what changed:
| Section | What changed |
|---|---|
| Blockers | Added: API dependency from Platform team not ready — blocks the data sync feature. ETA unknown. |
| Decisions made | Added: Team agreed to build a mock data layer to unblock frontend work while waiting on API. |
| In progress | Updated: "Data sync feature" now marked as blocked pending API. "Frontend build" updated to note mock data layer approach. |
| What's next | Added: Assign someone to own the mock data layer this week. |
Everything else in the status doc is unchanged — only the sections affected by this email were rewritten.
Ask the Automator to make it so that every Friday at 5pm, Majk Rabbit reads everything that arrived in the project folder this week and produces a polished HTML status report — something I could send to stakeholders. Call it status_report_[date].html. Same sections as the status doc, but designed to be read by people outside the team who need the big picture, not the detail.
Setting up the weekly report automation now.
Done — the weekly report automation is live:
| Setting | Value |
|---|---|
| Schedule | Every Friday at 5:00 PM |
| Reads | Everything in project_alpha/ that arrived during the week |
| Output | status_report_[date].html — stakeholder-ready, big picture not detail |
| Sections | Same as the status doc, written for people outside the team |
First run: this Friday at 5pm. You don't need to do anything.
It's Friday 5:00 PM. Read everything that arrived in project_alpha/ this week and produce a polished HTML status report for stakeholders.
Output file: status_report_[date].html — write it to the project folder. Same sections as the internal status doc, but written for people outside the team who need the big picture, not the detail.
Automation Details:
Automation: Weekly Status Report
Schedule: Friday 5:00 PM
Triggered at: 2026-04-19T17:00:00.000Z
Reading everything that arrived in the project folder this week, then building the stakeholder report.
Done — status_report_apr_19.html is in the project folder. It covers what shipped this week, what's in progress, the active blocker and its workaround, and next week's priorities.
You can find it in project_alpha/status_report_apr_19.html, or ask me to open it.
Open the report.
- API dependency from Platform team not ready — blocking data sync feature. Workaround: mock data layer in progress, frontend work continues unblocked.
Ask the Automator to watch this project folder. Whenever a new file arrives, read it and keep me accurately informed about where this project actually stands. You decide what structure and sections would be most useful — I just want to be able to read one file and know what's happening.
Setting up the automation — open goal, structure decided at run time.
Done — the automation is live:
| Setting | Value |
|---|---|
| Watches | project_alpha/ (all subdirectories) |
| Trigger | Any new file created |
| Goal | Keep you accurately informed — structure decided by the agent each run based on what the project needs |
No sections specified. Each time it runs, it'll read the project first and decide what structure would be most useful.
A new file has been added to the project folder. Keep the project owner accurately informed about where this project stands.
Goal: Read the new file and update project_status.md so it reflects the current state. You decide what structure and sections are most useful for this specific project — don't just fill in a template.
Automation Details:
File Path: project_alpha/emails/thread_apr_22.txt
File Name: thread_apr_22.txt
Event Type: create
Triggered at: 2026-04-22T14:51:00.000Z
Reading the full project folder first to understand the context before deciding what structure would be most useful.
Here's how the two approaches compare on the same folder:
| Method prompting | Outcome prompting | |
|---|---|---|
| Structure | Your 5 sections, exactly as specified | 6 sections — added one you didn't ask for |
| Added section | — | "Risk register" — the email threads show a pattern of late-breaking dependencies; this project needs a dedicated risk section |
| Blockers | Listed as a section | Promoted to the top — given the API dependency, it's the most important thing to see first |
| What you get | Predictable, easy to skim, you know where everything is | Structured around what this project actually needs to surface |
The risk register wouldn't have appeared in the method version because you didn't ask for it. But after reading the email patterns, it's clearly what this project needs most.
Ask the Automator for a list of automations — which are enabled, when they last ran, and how to pause or change one.
Here are your active automations:
| Name | Trigger | Status | Last ran |
|---|---|---|---|
| Project Status Updater | New file in project_alpha/ | ✅ Active | 2:47 PM today |
| Weekly Status Report | Friday 5:00 PM | ✅ Active | Last Friday |
To pause, change the trigger, or delete a rule — just say which one and what you'd like to do. You can also see all automations and their full run history in Apps → Automator.
If a new file mentions a blocker or missed deadline, flag it separately so I notice it immediately.
Added to the rule. Now whenever a new file triggers an update, I'll also check for blockers or missed deadlines. If I find one, I'll write a separate ALERT.md in the project root — one file, always the current alert, overwritten each time. If there's nothing to flag, the file stays empty.
The status doc update still runs regardless — the alert is an addition, not a replacement.
Each time the status updates, append a one-line entry to a changelog so I can see what changed and when.
Added to the rule. After each status update, I'll append one line to changelog.md:
The changelog grows over time. The status doc stays current. You get both: a snapshot of now and a record of how it got there.