Calendar, emails, Clio
Every evening a Power Automate flow collects the lawyer's Outlook calendar meetings, sent emails, Teams calls and Word editing time in SharePoint. Personal entries and emails with no matter indicators are skipped.
At the end of the month lawyers reconstruct from the Outlook calendar and from memory how many hours went to each matter, and some of the work goes unbilled. The assistant drafts timesheets from the calendar, emails and Clio entries and prepares an invoice narrative for SAP Business One or Sage. The partner approves.
Built for ISO 27001NIS2 DORA
At a firm that bills by the hour, the money is made in Clio time entries, but the entries appear last. A lawyer writes emails in Outlook all day, talks to a client in Teams, drafts a document in Word and only in the evening or on Friday tries to remember which matter they spent how much time on. Some hours vanish, some are assigned to the wrong matter, and at the end of the month a partner, before approving invoices, reads the entries and asks colleagues what hides behind "consultation, 2 hrs". Accounting then retypes the approved amounts into SAP Business One or Sage by hand.
The assistant drafts the timesheet for the lawyer. Every evening it reviews the Outlook calendar meetings, sent emails, Teams calls and Word editing time in SharePoint, matches them to matters in Clio by client, parties and matter number, and proposes time entries with a duration and a description: "Preparing response to claim, matter no...., 1.5 hrs". The lawyer confirms them in Teams or Clio, corrects the duration or moves them to another matter, and an unconfirmed entry is not billed. At the end of the month the assistant takes the confirmed entries and prepares an invoice narrative for each client at the level of detail set in the firm's engagement agreement, plus an import file for SAP Business One or Sage. The partner reviews the narrative, writes off hours that will not be shown to the client and approves, and only then is the invoice issued in the accounting system. We implement it as a Power Automate flow in your Microsoft 365 tenant, and email and meeting content that contains matter details is summarised by a model in MDP CLOUD's private GPU cloud in Lithuania (EU) or by Claude through Amazon Bedrock in an EU region, with no training on your data and with a log in line with GDPR.
Four steps from input to a record in your system, with human approval wherever there is risk.
Every evening a Power Automate flow collects the lawyer's Outlook calendar meetings, sent emails, Teams calls and Word editing time in SharePoint. Personal entries and emails with no matter indicators are skipped.
The model matches the activity to Clio matters by client, parties and matter number and builds a draft of time entries with a duration and a description. The lawyer confirms them in a Teams card or in Clio and corrects the duration or the matter. Only confirmed entries become billable time.
At the end of the month the assistant builds an invoice narrative for each client from the confirmed Clio entries, at the level of detail the engagement agreement requires, and prepares an import file for SAP Business One or Sage. The partner reviews, writes off hours and approves, and accounting issues the invoice in the accounting system.
If an activity cannot be assigned to a matter or the duration is unusual, for example 9 hours on one matter, the assistant does not create an entry and asks the lawyer. Every month we review how many draft entries were corrected and refine the matching rules together with a partner.
A flow in your Microsoft 365 tenant with access only to the calendar, sent emails and Teams call metadata, and no access to other people's mailboxes.
Time entries are created in Clio through an API or an import with the status "pending approval" and are confirmed in the lawyer's Teams card or in Clio itself.
Monthly invoice narratives at the level of detail set in the firm's engagement agreements, and an import file or an API record into SAP Business One or Sage after the partner's approval.
Every proposed, corrected and approved entry is logged with the time and the user. Training for lawyers and accounting and support during the first month are part of the implementation.
Power Automate + Outlook + Clio + SAP Business One import. We choose the platform by the task and by where your data may be located. For more on this service and its limits, see the service page.
No. It prepares only the invoice narrative and an import file for SAP Business One or Sage. The partner approves the hours and the narrative, accounting issues the invoice in the accounting system, and it goes to the client through the firm's usual procedure. An unconfirmed time entry never reaches an invoice.
The narrative contains only the activity name, the matter and the duration, at the level of detail set in the client agreement, not quotations from emails. The model sees the email text only to assign an activity to a matter, processes it in MDP CLOUD's private cloud or in Bedrock in an EU region, and does not store it outside the log.
Yes: we connect to SAP Business One through an import file or an API, to Sage through an import, and to Clio through an API or an export, depending on the version. If your firm uses a different practice management system, we take the time entries from it on the same principle. We have no official partnerships with these systems. We work with their public interfaces and, before proposing a solution, check what your version allows.
A similar matter is searched for in Clio, SharePoint folders and Westlaw, and the ruling a colleague cited last year takes half a day to find.
Enquiries from the website and Outlook wait until someone reads them, checks for a conflict of interest and replies.
The contract the client sent is read from the top, and the checklist is kept in the lawyer's head.
A response to a claim starts from a blank Word page or a copy of an old matter, with the facts retyped from Clio.
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
AI risks are identified and managed like any other IT risk.
We reply within 1 business day