Scaling service businesses is hard not because of missing technology, but because expert knowledge is trapped in people’s heads, while their time is drained by repetitive work. The breakthrough comes from letting AI handle the routine, so humans can focus on creativity, judgment, and doing their best work – together, not in competition.
For event production companies like Meeting Tomorrow, growth once followed a familiar pattern: hire more senior experts to manage increasingly complex, manual workflows. But over time, it became clear that the real bottleneck wasn’t creativity or client demand – it was the volume of mechanical work surrounding them.
This case study explores how intelligent AI agents unlocked operational capacity by automating the repeatable 70% of pre-sales work, while intentionally preserving the human judgment that makes exceptional events possible.
Meet Our Client
Meeting Tomorrow is a leading event production company serving major corporate clients across the United States. With decades of experience in the industry, it provides comprehensive end-to-end event organization services - from venue sourcing and logistics coordination to sophisticated audio-visual setups and on-site technical support.
Their success is built on deep domain expertise, with team members who possess up to 20 years of specialized knowledge in translating client visions into flawlessly executed events.
Case Study Shortcut
Challenge
Manual quoting bottleneck
The process of converting vague client requests into detailed technical orders with hundreds of inventory line items was entirely manual, creating significant delays and limiting capacity.
Tribal knowledge dependency
Critical operational knowledge existed only in the minds of senior employees, making the quoting process difficult to scale and vulnerable to knowledge loss.
Resource capacity constraints
With limited staff resources, the company needed to handle growing demand without proportionally increasing headcount, but couldn’t afford to lose the human expertise that makes events exceptional.
Goal
The objective was to strategically automate repetitive aspects of the pre-sales workflow while preserving and amplifying human expertise, enabling the team to scale operations without sacrificing the customization and creativity that differentiate their service.
- Automate the selection of standard "core" equipment that constitutes the bulk of typical orders
- Reduce time spent on manual data entry and repetitive order creation tasks
- Free experienced staff to focus on high-value activities: creative event design, complex staging, and client relationship management
- Maintain 100% human oversight on final orders to ensure quality and handle edge cases
- Create a scalable foundation that allows the business to grow without linear increases in staffing costs
Outcome
The implementation of the AI agent system transformed the Client’s pre-sales workflow by shifting effort away from manual, repetitive tasks toward expert-led validation and creative work. The impact is best illustrated by comparing the state of operations before and after the pilot deployment.
Before
- Quoting process required 100% manual effort from highly experienced staff
- Senior employees spent a significant amount of time on repetitive data entry and inventory selection
- Limited capacity to handle new opportunities due to bottlenecked quoting process
- Standard equipment selection consumed time that could be spent on creative, high-value work
- Knowledge trapped in individual team members, creating scalability challenges
After
- AI pilot handles 50-70% of standard equipment selection automatically
- Experienced staff transitioned from manual data entry to strategic verification and creative design
- Draft orders generated in minutes instead of hours, dramatically increasing throughput capacity
- Team focuses on subjective, creative aspects of event production that require human intuition
- Scalable architecture enables handling increased demand without proportional headcount growth
- Knowledge codified in the system while human expertise remains central to decision-making
Integrate those solutions in your company
Case Study Details
Approach
Agentic Workflow Architecture (LangGraph)
- Implemented non-linear AI workflows that can process multiple steps, backtrack, and choose optimal paths, mimicking human project manager decision-making patterns.
Prompt Engineering & Validation Layer
- Fine-tuned each workflow node with specific prompt engineering techniques and statistical validation rules to prevent hallucinations and maintain quality standards.
Inventory-Grounded Generation
- Strictly grounded AI outputs in the company's actual database, ensuring all recommendations map to real NetSuite ERP inventory IDs with post-processing validation.
Human-in-the-Loop Design
- Created a system that generates 50-70% accurate draft orders for human expert review, addressing the "blank page" problem while maintaining quality control.
Context-Aware Processing
- Enabled the system to ingest multiple data sources (CSV files, PDFs, email correspondence) to build comprehensive context for order generation.
Legacy System Integration
- Built seamless compatibility with existing NetSuite ERP infrastructure to ensure smooth adoption without disrupting established workflows.
Timeline
Project Duration | 2 month
Planning & Discovery | 2 weeks
Development & Testing | 6 weeks
Technology
LangGraph
Google Cloud Platform (GCP)
Large Language Model (LLM)
NetSuite (Database/ERP)
Our team
Adam Komorowski
Senior Data Scientist
Piotr Kowalski
Data Scientist
Marcin Marczyk
Delivery Director
Our Team Expert Opinion
Our approach was simple: automate the 70–80% of work that’s mechanical, and protect the 20–30% that requires judgment. That’s not a compromise, it’s good system design. Every attempt to push AI beyond its reliable boundaries is just another way of manufacturing technical debt.
Adam Komorowski Senior Data Scientist at Addepto
Take the next step
About Addepto
Addepto, a fast-paced, growing company focused on innovations in AI-related and data-oriented areas, supports digital transformation at companies working on electronics manufacturing services.
Here you can learn more about the technologies used in this project:
We help them find ways to use their data effectively with data lakes, data platforms, data engineering and so on.
About us
We are recognized as one of the best AI, BI, and Big Data consultants
We helped multiple companies achieve their goals, but - instead of making hollow marketing claims here - we encourage you to check our Clutch scoring.
Other case studies
check all case studies
Real-Time Baggage Tracking and Prediction Platform for Airlines
AI-powered baggage tracking for airlines. Predict and prevent luggage loss in real time with Addepto’s scalable data and analytics platform.
AI-Powered Candidate Matching Engine
Industry: HR Tech / Recruitment
Service Areas: Data Engineering, Natural Language Processing, ML Engineering
Solution: Modular, AI-powered matching engine that could connect with Client’s existing core platform via API
Transform Engineering Chaos into Strategic Clarity
Discover how AI turns CAD files, ERP data, and planning exports into structured knowledge graphs-ready for queries in engineering and digital twin operations.
read more