Choosing the process
Together we pick the process that repeats most often, has a clear definition of "done" and has its data in your systems. We define what the AI does on its own and what it does only after a person approves.
AI for professional services companies
In a professional services firm, time is the product, and a large share of it goes on Outlook enquiries, proposals, updating HubSpot or Pipedrive after meetings and a Clockify log filled in from memory on Friday. AI prepares replies, drafts and CRM records from your templates and documents, and the consultant approves. We implement it with access rules and data in the EU.
Built for ISO 27001NIS2 DORA
- Drafts of proposals and contracts
Unbilled hours: Outlook enquiries, proposals, CRM, Clockify
- Minutes first reply in Outlook instead of hours
- From a template Word proposals built from the HubSpot record
- After the meeting Teams summary and next steps in the CRM record
- With a link Clockify log from the calendar in a minute
In consulting, accounting, legal, IT and marketing firms, the day is made of small tasks nobody pays for. A client writes to the shared info mailbox in Outlook and waits for someone to forward it to the right person. A proposal is written from the last proposal in Word, changing the names and forgetting one appendix. After a Teams call the account manager promises to update the HubSpot or Pipedrive record and does it a week later, if at all. A new hire asks where the procedure is, and it sits in an email from 2023. The Clockify or Harvest log is filled in on Friday from memory, and the invoice to the client ends up smaller than the time actually spent.
AI takes over exactly this layer: an assistant answers standard enquiries in Outlook and hands complex ones to a person with the client history from the CRM, proposal drafts are prepared in Word from your templates and the HubSpot or Pipedrive record, Teams meeting summaries land in the client record in the CRM on their own, the knowledge base answers with a link to the procedure in SharePoint, and a draft Clockify log is prepared from the calendar and mail. We implement it with Microsoft 365 Copilot, Claude or ChatGPT, and integrate with HubSpot, Pipedrive, Clockify and SAP Business One or QuickBooks Online through an API, file export or an email flow, depending on your version. Before connecting AI we put access in order by client and role, keep data in an EU cloud, and for legal and financial firms we offer private AI in the MDP CLOUD GPU cloud in Lithuania (EU).
What we implement for professional services firms
The 5 solutions we implement most often in this industry. Each one starts with a single process, has a human approval step and is measured.
Customer enquiry assistant with handoff
The assistant reads enquiries from the shared Outlook mailbox and the website form, recognises the topic, answers standard questions from your service descriptions and FAQ, and passes complex enquiries to the responsible person with a summary, the client history from HubSpot or Pipedrive and a suggested reply. A person always sees what the assistant answered and can step in.
We build it with: Claude agent via API + Outlook + HubSpot or Pipedrive integration
Drafts of proposals and contracts
The account manager picks the client record in HubSpot or Pipedrive and a service bundle, and Copilot in Word prepares a proposal or contract draft from your templates with the correct company details, scope and terms. A lawyer or manager reviews and approves, and the approved contract is sent to the client from Outlook.
We build it with: Copilot in Word and Outlook + HubSpot or Pipedrive data
CRM updates after calls and meetings
Recordings of Teams meetings and calls are transcribed, a summary, agreements, next steps and deadlines are extracted, and the result is written to the client record in HubSpot or Pipedrive with tasks created. The account manager approves the record instead of writing it from memory.
We build it with: Copilot Studio + Power Automate + HubSpot or Pipedrive integration
Internal knowledge base for employees
Procedures in SharePoint, internal rules, service descriptions and material from earlier projects in project folders are combined into one assistant that answers staff in Teams with a link to the document. A new hire gets up to speed in days, not weeks, and veterans stop hunting for which email version of a rule is current.
We build it with: ChatGPT Custom GPT or Claude + SharePoint documents
Time tracking and incoming invoices
From the Outlook calendar, mail, Teams and the task system, AI prepares a draft daily log by client and project. The employee approves it in a minute and the entries go to Clockify or Harvest. Approved hours become the basis for invoices, and incoming supplier invoices are recognised, assigned to projects and prepared for import into SAP Business One or QuickBooks Online.
We build it with: Power Automate + Microsoft Graph + Clockify or Harvest integration + SAP Business One or QuickBooks Online import
How we implement it
From the first conversation to a working solution, with measurement and ongoing support.
Access and data
We put access to files and systems in order, give the AI its own identity with the least privileges it needs, turn on an action log and choose where the model runs: your Microsoft 365, Amazon Bedrock in an EU region or our GPU cloud in Lithuania (EU).
Build and test
We build the solution with Copilot, Claude or ChatGPT, whichever fits the task, connect it to your systems and test it on historical documents and enquiries until accuracy reaches the agreed threshold.
Launch and support
We launch with a person in the loop, review the logs and exceptions and adjust the rules. Once the first process runs reliably, we move on to the next one on the list.
Are your processes different?
These solutions are a starting point for a conversation, not a complete list. Tell us which processes repeat in your company, and in one conversation we will tell you what is worth handing to AI and what is not.
Frequently asked questions
Will clients realise an AI is replying, and will it hurt the relationship?
We recommend saying so plainly: the assistant introduces itself as an assistant in the Outlook signature and answers only standard questions, while anything tied to a specific client matter goes to a person with the history from HubSpot or Pipedrive. In our experience, clients value an answer within minutes more than waiting until tomorrow.
Does it work with HubSpot, Pipedrive and Clockify?
Yes. HubSpot, Pipedrive and Clockify or Harvest have public APIs, which is how we connect most often. Where the API is limited, we use file export or an email flow, depending on your plan. With Microsoft CRM we connect directly inside your Microsoft 365 tenant. We choose the integration method after a check at the start of the project. We have no official partnerships with these vendors.
We have no CRM, only Excel and email. Does it make sense?
It does, but we start with the foundation: most often we set up HubSpot or Pipedrive, or put the Microsoft 365 tenant in order, so there is somewhere to write the results. The first AI step in that case is the enquiry assistant in Outlook or the knowledge base in SharePoint, both of which need only mail and documents.
Related services
AI for restaurants and cafes
Bookings arrive through Messenger, reviews land on Google Business Profile and Wolt, sales live in Lightspeed, and supplier invoices reach SAP…
AI for retail
A supplier sends a thousand products with no descriptions for PrestaShop or WooCommerce, customers ask about stock in Lightspeed and parcels with…
AI for transport and logistics companies
Orders from Trans.eu, Outlook and customer portals are retyped into CargoWise by hand, CMR photos travel through Viber, and DKV invoices are keyed…
AI for wholesale
Orders arrive as emails, Excel sheets, PDFs and through EDI from retail chains, customers call about stock and contract prices, and every month…
Expertise confirmed by certifications
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
-
Artificial Intelligence Security Professional
AI systems are deployed with protection against data leakage and model abuse.
-
ISACA Advanced in AI Security Management
The AI security programme and its controls are managed following the ISACA methodology.
-
ISACA Advanced in AI Risk
AI risks are identified and managed like any other IT risk.
Let's discuss AI for your professional services firm
Tell us which processes repeat most in your company. Within 1 business day we will tell you where it makes sense to start and how long it would take.
We reply within 1 business day