AI agents: use cases and implementation choices
Adrian Sjøholt and Frode Stenstrøm of ProsessPilotene covered trends, models and use cases for AI agents in business.
Adrian Sjøholt and Frode Stenstrøm of ProsessPilotene covered trends, models and use cases for AI agents in business.
In this 2025 webinar, Adrian Sjøholt, solution architect at ProsessPilotene, and Frode Stenstrøm opened a series on artificial intelligence with a review of AI agents. They compared the leading language models from OpenAI, Google, Anthropic, Meta, Microsoft and Amazon, noting differences in token size, cost and suitability for different tasks.
They then explained foundational concepts such as vector databases, which give language models a form of memory, and the Model Context Protocol (MCP), an open protocol from Anthropic that lets AI agents connect to a company's own systems through APIs without building each integration from scratch.
Practical examples included automated quote generation from incoming emails, project plans generated from contract documents, better knowledge-article search for customer service, and AI-assisted coding. The two also demonstrated how AI agents can be specialised for narrower tasks and chained together in a workflow, rather than building one large general-purpose agent meant to cover everything.
The session closed with a recommended approach to adoption: identify business areas with real value, ensure clean underlying data, match the right model to the right task, and start small with clear ownership and management backing, relevant for organisations in any industry considering AI agents.
CRM-Konsulent
Gründer og teknologistrateg
Som gründer og teknologistrateg i ProsessPilotene jobber jeg med å hjelpe virksomheter forstå og bruke teknologi som en strategisk kraft for bedre arbeidsprosesser, kundeopplevelser og beslutninger. Rollen kombinerer forretningsutvikling, teknologirådgivning, virksomhetsarkitektur og formidling. Jeg arbeider særlig i skjæringspunktet mellom AI, CRM, digitale plattformer, data, analyse og fremtidens arbeidsliv. En sentral del av rollen er å være brobygger mellom ledelse, fagmiljøer og teknologi. Det handler om å gjøre komplekse teknologiske muligheter forståelige, vurdere hva som faktisk skaper verdi, og bidra til at digitale løsninger blir en naturlig del av hvordan virksomheter jobber. Jeg bruker også rollen til å formidle faktabaserte perspektiver på hvordan AI og teknologi påvirker ledelse, organisasjoner, ansatte og kunder.
Ask a question or share what helped you.
Make Copilot a useful part of customer work
CourseDesign and test a role-based AI workflow with clear sources, checks and accountability.
Use Copilot in Excel for analysis you can verify
CourseAsk precise data questions, check calculations and turn findings into decisions with visible qualifications.
Delegate a work task to Microsoft Copilot Cowork
CourseGive Cowork a bounded multi-step assignment and verify the plan, actions and final output.
Use Copilot for meetings and follow-up that lead to action
CoursePrepare meetings, verify summaries and turn decisions into clear follow-up.
Jets Group's experience with AI in sales and order work
October 21, 2025 • Webinar — Trond Jarnes of Jets Vacuum told Stine Sletvold and Frode Stenstrøm how AI in Dynamics 365 Sales now automates quote lines.
June 19, 2025 • Webinar — Frode Stenstrøm and Adrian Sjøholt tested Google, OpenAI and Anthropic AI models on real project-planning tasks, from requirements to a presentation.
May 25, 2025 • Webinar — Frode Stenstrøm and Adrian Sjøholt had Google Gemini, Microsoft Copilot and Claude compete at drafting a contract.
April 2, 2025 • Webinar — Ane Tronsaune showed Frode Stenstrøm how to automate a Dynamics 365 discount approval with Power Automate, Teams and AI Builder.
Automation | Article
The data agent gained a larger role in analytics
OpenAI’s Data agent could investigate company data and build shareable interactive dashboards. Access controls and source trails needed to follow analysis and action through the workflow.
Customer Service | Article
Service Agent gained tools for staffing decisions
WEM MCP tools enabled time-off requests, shift swaps and shift bids in Service Agent. Administrators could enable each tool for a role, team or pilot group.
Information security | Article
Norway to reconsult on its AI law after EU rule changes
On 4 August 2026, the Norwegian government announced that its proposed AI Act would return to consultation after changes in the EU simplification package.
Automation | Article
New tools for managing agent costs
Copilot administrators gained central controls for consumption-based cost. Purview controls extended to Cowork, and agent metrics could connect with organisational context.
The EDPB published new guidelines on web scraping for generative AI and adopted final blockchain guidelines.
Service Agent became generally available across Dynamics 365 and Microsoft 365. Workforce Engagement Management connected demand, staffing and quality work.
Share a question or reflection.
Be the first to contribute.
