Submit offer AI Agent Strategy and System Design

 
1. GENERAL INFORMATION: 
Regulars ApS

Mindebrogade 3, 3.th

Aarhus C 8000

CVR: 43492462

Contact: Magnus Damiri, CTO, magnus@getregulars.com, +45 50 15 10 20

2. PRESENTATION OF COMPANY: 

Regulars is a software company building digital loyalty and customer engagement solutions for cafés, restaurants, and other hospitality businesses. Our platform helps merchants create and manage loyalty programs, memberships, gift cards, and customer-facing experiences across digital channels.

We are currently exploring how AI and agent-based systems can support both our internal workflows and product development. This includes understanding where agent systems create real value, how they should be designed in a production software environment, and how they can be introduced responsibly in a SaaS platform handling customer, merchant, and operational data.

Our goal is not only to identify relevant use cases, but also to build the internal technical understanding needed to assess, design, and later implement agent-based capabilities in a robust and scalable way.

3. DESCRIPTION OF THE TASK UNDER MARKET EVALUATION: 

We are seeking an experienced AI advisor with strong expertise in agent systems, LLM-based application design, and software architecture to support our team through knowledge sharing, strategic guidance, and technical sparring.

The purpose of the collaboration is to help our team understand how AI agents work in practice and how agent-based systems can be designed and implemented as part of a modern software product.

The collaboration is expected to focus on the following areas:

AI Agent Strategy and System Design

Strategic guidance on when and how to use AI agents in software systems, including explanation of core agent concepts such as planning, memory, tool use, orchestration, autonomy levels, and human-in-the-loop patterns; guidance on the difference between deterministic automation, assistant-style workflows, and true agent systems; and support in identifying where agent-based approaches are relevant and where they are not.

Architecture and Implementation Considerations

Technical sparring on how agent systems can be integrated into a production SaaS environment, including architecture for agent orchestration, tool calling, state handling, and workflow control; infrastructure considerations related to scalability, latency, cost control, monitoring, and reliability; design patterns for integrating agents with existing backend services, APIs, databases, and business logic; and approaches to evaluation, testing, observability, and safe rollout of agent-based features.

Relevant Use Cases for Regulars

Exploration and prioritisation of realistic use cases relevant to our platform, such as internal productivity and knowledge workflows, merchant onboarding and setup assistance, campaign or loyalty program recommendations, customer support assistance, content or asset generation workflows, and analytics or insight-supporting assistants.

The purpose is not to fully implement these use cases during the advisory project, but to assess their feasibility, value, and architectural implications.

Security, Governance, and Responsible Use

Guidance on how to work responsibly with AI agents in a commercial software setting, including data privacy and secure handling of merchant and customer-related information, access control and permission design for agents interacting with internal systems, model selection and vendor considerations, risk management, fallback strategies, and limitations of agent-based systems, as well as governance principles for introducing AI-assisted functionality into a production environment.

The advisor’s role will be to equip our team with the understanding, frameworks, and technical direction required to move forward internally after the project ends.

4. TASK OBJECTIVES AND SUCCESS CRITERIA: 

Objectives

The goals of the project are to strengthen our team’s understanding of AI agents and agent-based software design, clarify which agent patterns are relevant for our business and product context, receive guidance on suitable architecture, infrastructure, and integration principles, identify and prioritise a realistic set of use cases for further development, and establish a practical foundation for future in-house implementation.

Success Criteria

We will assess the success of the project based on the following criteria: our team gains a clearer strategic and technical understanding of AI agents and their implementation in software systems; we receive a documented overview of recommended architecture principles and design considerations; we receive a prioritised assessment of relevant use cases for Regulars; we receive a practical implementation roadmap outlining next steps, dependencies, and key risks; and the deliverables are concrete enough for our internal team to use as a basis for future development decisions.

 
5. BUDGET OG SPECIFICATION OF AN OFFER: 
We expect a written offer to include at least: 
• Date of submission of offer 
• A brief presentation of the bidder, stating the CVR number and contact details. If relevant, with references and history 
• Bidder's proposal for solving the task 
• Specification of the price for solving the task 
• Discount, if relevant 
• Timeframe and end date 
• Conditions for the offer, if any 
 
6. BACKGROUND FOR THE TENDER: 
Beyond Beta is subject to a number of requirements for good, healthy financial management, including documentation that the agreed price for external purchases is an expression of the market price. This tender is part of these requirements. 
We emphasize that the bidder must only make an offer on the requested task.  
Services of executing or implementing nature cannot be approved  
The winning bid is chosen based on an assessment of the best correlation between price and quality