Deadline alerts
Watches every tracked date across contracts, filings, and matters, and warns the named owner while there is still time left to act on it.
No ready-made setup for this job yet.
Describe the job in a sentence, the way you would brief a colleague: when it should happen, what to check, and what to hand you. That sentence is the automation.
The job, and what good looks like.
What breaks: a deadline list is right on the day it is built and wrong a month later, and the only version anyone trusts is the one a lawyer keeps privately. The legal ops coordinator spends the first week of every month reconstructing what is due from calendars and memory, and a date that was missed never resurfaces on its own. A notice window closes quietly, and the consequence arrives weeks later as an unintended renewal. What the workflow does: it collects tracked dates from the contract records, the filing calendar, and the matter log, and holds them as one list with the owner, the notice period, and the date. Notice windows are kept separate from the date they lead to, because the earlier of the two decides it. Each warning names the date, the owner, and what happens if nothing is done, and it repeats until the task closes. Overdue items are listed weekly and stay listed until someone resolves them. What a person still approves: the business owner decides whether to act, and a lawyer confirms a date that reads as unusual before the warning goes out.
When it is handled
- Every tracked date on one list
- Notice windows held separately
- Warning names the date and the owner
- Overdue items never drop off the list
Works with tools like
- Conga
- Icertis
- DocuSign
- Diligent
- FairNow
You stay in charge.
At every step.
It compares and flags. Every legal call stays yours.
- It never signs or advises
It quotes deviations against your playbook. Accepting, signing and advising stay with a lawyer.
- Every flag shows its source
Each deviation quotes the clause it is about, every step is recorded, and a file change can be put back.
- Confidential stays contained
Each automation reaches only the folders you connect for it, and a local model keeps processing on your machine.
Before you download.
- Where does it run?
- On your Mac or Windows computer, in the background. It keeps working after you close its window, and only reaches the folders and apps you connect for each automation.
- How does it connect to our CRM and other tools?
- Through each app's own connection where it offers one, signed in once by you, or by using the app in a browser the way you would. Each automation gets only the connections you give it, and the tools a page names are examples you can swap for your own.
- Does it run when my computer is asleep?
- It keeps your computer awake while a job runs and just before a scheduled one. While the computer is closed or off, nothing runs; when it wakes, it checks the inbox, calendar and other sources it watches for anything that arrived meanwhile.
- How does my team use it?
- Each person who runs automations installs the app. Keep a project in a shared folder, such as Google Drive or a network drive, and teammates can open it and follow every run, while one person owns it and runs it.
- Do I need anyone technical to set it up?
- No. Download the app, add an automation in plain words, and connect only what that job needs. Nothing runs until you switch it on.
Already have tools for this? Here is the difference.
Contract management systems
Storing signed contracts and running approval routes.
Their rules can't read new paper against your playbook or explain a deviation in plain words.
Flowchart automation tools
Moving records between apps.
Clause-level judgment does not fit into branches, and every exception becomes another one to maintain.
AI chat assistants
Summarizing a contract when you paste it in.
Nothing happens until someone asks, and the playbook lives in a chat instead of a document you control.
AUTOMATE.md
Your routine, written in plain words. It runs on its own, follows your rules, handles the exceptions a flowchart can't, and asks you when it matters. The file stays yours, whichever AI model runs it.
Start with one job.
Make it your own.
macOS — coming soon- 1
Get the app
It runs on your computer, next to your files.
- 2
Add the automation
Paste the instructions into the app, or save them as a file next to your work.
- 3
Try it, then turn it on
Run it once and check the result. It only runs on its own once you switch it on.