Overview
Built a solution design builder that lets sellers compose modular Microsoft-based offers and export proposals, statements of work and battlecards in minutes, with an Azure OpenAI job keeping product names and licensing accurate.
Who This Is For
Technology consultancies and Microsoft partners selling modular cloud, security, data and AI services to mid-market and enterprise organisations. This case is most useful if:
- every proposal is assembled from scratch by a different seller
- presales engineers spend their time rebuilding the same statements of work
- Microsoft product names and licensing change faster than your sales material
- you want sellers to package cross-business-unit offers without losing commercial control
The Challenge
The consultancy sold managed services and consulting across several business units, built on a large and changing set of Microsoft products. Each proposal, statement of work and battlecard was assembled by hand.
Offers were inconsistent, slow to produce and easy to get wrong, especially licensing and product names that Microsoft updates regularly.
Our Approach
We built a solution design builder that lets sales managers and presales engineers compose a modular offer in five steps and export the full sales pack, with AI keeping the product catalogue accurate.
- A five-step flow: deal basics, situation and challenges mapped to Well-Architected pillars, the answer, the customer environment with a recommended tier, and the offer.
- A modular catalogue: 4 business units, 26 solution archetypes, 58 Microsoft products, 57 managed workstreams, 35 consulting work packages and 53 reference cases, combinable across units.
- Instant documents: customer proposal, discovery, onboarding and run statements of work, a sales battlecard and matched reference cases, exported as Word, PowerPoint, PDF or Markdown directly in the browser.
- AI-checked accuracy: a scheduled Azure OpenAI job uses the Microsoft Learn MCP server to verify product names, licensing and partner specialisations every 25 days, and logs what needs correcting.
- AI in delivery economics: a model of AI-assisted delivery effort and savings feeds an internal margin view, and a one-click prompt hands the configured offer to an AI assistant for further drafting.
Impact
Minutes, not days. A seller can configure an offer and export the proposal, statements of work and battlecard in one session.
One catalogue, many combinations. 26 archetypes and 58 products packaged consistently across 4 business units, with pricing tiers by organisation size.
Accuracy that maintains itself. AI checks the catalogue against Microsoft's own documentation, so licensing errors are caught before a customer sees them.
Modular services only scale if sellers can assemble them without an architect in the room. Here the architecture is built into the tool.
Built and delivered by ECM.DEV. Client details are withheld at the client's request.
Topics
Delivered Norwegian-to-English translation and QA review of SpareBank 1 Markets' website content, covering their research, corporate finance and capital markets service lines.
Built a data-driven content and channel strategy for Econa, Norway's professional association for economists and business graduates, building on an already-delivered website redesign to reduce member churn.
Built a CRM-connected advertising sales platform for a leading Nordic digital marketplace. Connected audience data, targeting options, advertising formats, pricing and sales contacts into a single self-service portal for advertisers and media agencies, replacing a fragmented sales experience with a repeatable path from research to qualified inquiry.
The Content Infrastructure Imperative
Why AI Amplifies Every Flaw in Your Content Operating System
What agents need to operate your content
The article discusses the infrastructure and capabilities required for AI agents to effectively manage content operations in enterprise environments, focusing on the practical requirements developers must understand when building systems that automate content workflows.
Content-to-Pipeline Check
See how far your content connects to sales, and how much of what sales learns comes back.