Email triage for law firms
A firm’s inbox receives court notifications, opposing counsel’s submissions, client documents and assorted enquiries every day — and one missed notification can cost a deadline. The agent sorts the flow, attaches each message to the right matter and surfaces what binds the firm.
In your day-to-day
- 01
Priority flagging of court notifications and messages linked to the RPVA e-filing platform, attached to the matter concerned.
- 02
Attachment of submissions and exhibits received to the right matter, with references already extracted.
- 03
Routing of new-prospect enquiries into the firm’s intake process, out of the flow of live matters.
A typical scenario
A firm’s main inbox takes a hundred messages a day: court notifications, opposing submissions, client documents, enquiries — and the morning sort keeps the secretariat busy for a full hour.
- 01
At 9:02 AM a court-of-appeal notification arrives: it is flagged to the associate on the matter and the responsible partner before the day’s signing folder is even opened.
- 02
Forty pages of opposing submissions received through the e-filing platform are filed to the right matter, their numbered exhibits already attached.
- 03
A client message slipping a substantive question between three attachments is routed to the lawyer — not to filing.
What changes
The morning sort disappears — and above all, no court notification can sit waiting in a full inbox anymore.
Order of magnitude
Working assumptions
- →around a hundred messages a day in the firm’s inbox
- →roughly 1 hour of daily sorting at the secretariat
On the order of 5 sorting hours a week returned to the secretariat — and the risk of a missed notification brought toward zero, which is worth more than the hours.
Indicative estimate built on average sector assumptions — it gets recalibrated on your actual volumes during scoping.
What eats your days
- →
Fee reminders and requests for payment on account come after the casework — and the firm’s cash flow pays for it every quarter.
- →
Procedural-deadline tracking rests on diaries kept by hand — and one missed deadline engages the firm’s liability.
- →
The firm’s inbox mixes court notifications, opposing counsel’s submissions, client documents and prospect enquiries — everything arrives at the same level.
How it works
- 1
Measure before sorting
We start by measuring the real flow: who writes, about what, what actually needs action. Sorting rules are built on that data — not on impressions.
- 2
Sort, extract, route
The agent classifies each message, extracts the useful data (references, amounts, deadlines) into your tools, and routes to the right person. Urgent items are flagged within minutes.
- 3
Answer the recurring
Acknowledgements, document requests, standard questions: the agent replies on its own within the approved fence. The rest lands pre-qualified in your team’s queue.
Typical results
95%
of messages classified and routed with no human involved
4 min
between an urgent message arriving and being flagged
0
client requests lost in the pile
Orders of magnitude observed in production; your diagnostic sets your own baseline and targets.
Frequently asked questions
These emails are covered by professional secrecy — how is that handled?+
The agent runs inside the firm’s mailbox, with no copy leaving your environment: minimal access, every action logged, no data used to train third-party models. The setup is documented so the firm can answer for it.
What if it misfiles a procedural notification?+
It starts in assisted mode: it proposes, your secretariat validates, and nothing is ever deleted or moved out of your sight. Autonomous sorting is only enabled on categories where reliability is demonstrated — and court notifications are always surfaced, never silently filed.
Is this the problem eating your team’s time?
Tell us how you work today — 30-minute call, then a free written diagnostic of what this agent would change for you, with numbers.
Get my free diagnosticFree resource
Get the self-assessment grid for your sector
Sales, admin, support, operations: the 20 tasks AI agents already handle in SMEs — with, for each one, the tell-tale sign that your team is concerned.