Staff fill in Clockify or Harvest on Friday from memory, so some client hours are never invoiced. AI drafts a daily log from the Outlook calendar, mail and Jira tasks, the employee approves it in a minute and the entries go to Clockify, while supplier invoices are matched to projects and prepared for SAP Business One or QuickBooks Online.
Built for ISO 27001NIS2 DORA
In a professional services firm, the client invoice rests on time tracking in Clockify or Harvest, and time tracking rests on the employee's memory. A consultant works with several clients a day, answers emails in Outlook, attends Teams meetings and closes tasks in Jira or Asana, but fills in the log at the end of the week, when half of the small tasks are already forgotten. Some hours drift into "general work", and the invoice to the client ends up smaller than the time actually spent. Meanwhile accounting receives supplier invoices that have to be assigned to projects and entered into SAP Business One or QuickBooks Online so you can see project profitability, and that is also done by hand, by asking around who the invoice is for.
At the end of each day, the solution uses Microsoft Graph to review the employee's Outlook calendar, sent emails and Teams meetings, takes the tasks closed or commented on that day from Jira or Asana, and prepares a draft daily log: which client and project, how much time, a short description. The employee receives the draft in Teams, corrects durations or assignments and approves it in a minute. Approved entries are written through the API to Clockify or Harvest under the correct project, accumulate in a project table and at month end become the basis for client invoices, which the project manager reviews and the accountant issues. In parallel, supplier invoices received in Outlook are recognised, assigned to a project and cost category by supplier, project number or purchase order, and prepared for import into SAP Business One, QuickBooks Online or Sage, where the accountant approves the batch. We build it with Power Automate flows in your Microsoft 365 tenant, pull data through Microsoft Graph with minimal permissions, recognise invoices with AI Builder or Azure AI Document Intelligence in an EU region, and integrate with Clockify, Harvest, Jira and the accounting system through an API, file export or an email flow, depending on your plan. The employee's calendar and emails are used only for the draft, are not stored and are not copied anywhere.
Four steps from input to a record in your system, with human approval wherever there is risk.
At the end of the day a Power Automate flow uses Microsoft Graph to pick up the employee's Outlook calendar entries, the subjects and recipients of sent emails and Teams meetings, and from Jira or Asana the tasks closed or commented on that day. The content is used only to assign a client and project, not for storage.
AI groups activity by client and project from your Clockify or Harvest project list, estimates durations from the calendar and the timing of emails, and writes a short description. Activity it cannot assign it flags as a question to the employee instead of dropping it into general work.
The employee corrects and approves the draft in Teams, and the entries appear in Clockify or Harvest through the API. At month end the project manager reviews the client's hours and the accountant issues the invoice. Supplier invoices reach SAP Business One, QuickBooks Online or Sage only after the accountant approves the batch.
Activity with no clear client and invoices from new suppliers go to a separate list where a person assigns them by hand, and the solution remembers that assignment. We track how much employees change the draft in Clockify and tune the assignment rules so that approval stays a matter of a minute.
Access to the Outlook calendar, mail metadata, Teams and Jira or Asana tasks only as far as the draft requires, with an agreed list of permissions and a log.
A daily message to the employee in Teams with the day's entries by Clockify or Harvest project, with approval and correction in one place.
A summary by project of approved hours from Clockify and received invoices, in SharePoint or Power BI, from which the project manager sees profitability and the accountant issues invoices.
Recognition of supplier invoices received in Outlook, assignment to projects and cost categories, batch approval and import into SAP Business One, QuickBooks Online or Sage.
Power Automate + Microsoft Graph + Jira or Asana tasks + Clockify or Harvest integration + SAP Business One, QuickBooks Online or Sage import. We choose the integration method for each system after checking your plans. For more on this service and its limits, see the service page.
No. It uses Outlook calendar entries, email subjects and recipients, Teams meetings and Jira tasks only to suggest which client to assign time to. Email content is not stored, screens are not monitored, and only the employee sees the draft until they approve it. We agree and document the list of permissions before launch.
Yes. Clockify and Harvest have public APIs, through which approved entries land under the correct project. We read Jira and Asana tasks through their APIs or an export. We import into SAP Business One through an import file or API, and into QuickBooks Online or Sage through their import formats. We choose the integration method after a check at the start of the project, and if your ERP runs in our ERP hosting, the integration is simpler.
No. Invoices are recognised and assigned to projects, but only a batch approved by the accountant is imported into SAP Business One, QuickBooks Online or Sage. The accountant sees every document with its assignment and can correct it, and corrections are logged.
After a client meeting, the account manager has to record what was agreed in HubSpot or Pipedrive, but usually does it in the evening from memory,…
Everything lands in the shared info mailbox in Outlook and the website form: pricing questions, document requests, complaints and serious enquiries.
Procedures sit in SharePoint, rules in Bitrix24 or in emails, and material from earlier projects in Jira and in colleagues' heads, so staff ask…
A proposal or contract is prepared by copying the last Word document and changing the details, and a mistake in a name or an amount is noticed…
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
