Fast Track AI unlocks agent-to-agent collaboration beyond APIs for igaming operators

Other AI agents can now request player context and intelligence directly from Fast Track AI without learning its platform.

Key takeaways:

• Fast Track has launched agent-to-agent support, letting Fast Track AI communicate and collaborate directly with other AI agents used by igaming operators.
• Unlike standard API or MCP tool exposure, Fast Track AI retains understanding of its ecosystem, player context, capability interactions and operator-specific governance.
• Other agents can request player context or intelligence and receive reasoned responses without needing to know Fast Track’s data structures, APIs or internal tools.
• CEO Simon Lidzén said organisations are moving to people-and-agents working together, and a single agent cannot be expected to understand every system it touches.
• The feature forms part of Fast Track’s continued build-out of an AI-native platform that already combines real-time player data, engagement, gamification, risk and value modelling.

Press release.- Fast Track has introduced agent-to-agent support for Fast Track AI, allowing its intelligence layer to work directly with other AI agents running across an igaming operator’s systems and teams. The move goes beyond simply exposing APIs or MCP tools: Fast Track AI itself understands the platform, player context and operator controls, so specialist agents elsewhere can draw on that expertise without mastering the underlying product. The company positions the capability as a necessary step towards scalable ecosystems of specialised agents.

Fast Track expects the next phase of enterprise AI to be built around ecosystems of specialised agents working together across systems and teams. 

Fast Track already operates as a mission-critical platform, supporting hundreds of users across CRM, player engagement, gamification, real-time player intelligence and decision-making. Its AI and data science capabilities play a key role in how operators interpret player behaviour and model value. 

With agent-to-agent support, that intelligence now extends beyond the Fast Track interface. 

Other agents elsewhere in the organisation can interact directly with Fast Track AI to request context, reason about player activity and support better-informed decisions within their own workflows. 

The approach goes further than exposing a set of APIs or MCP tools. 

An MCP implementation can make tools available to another agent, but the responsibility for understanding when to use those tools, how they should be combined and how the underlying platform operates still sits with the consuming agent. 

Fast Track’s approach keeps that expertise inside Fast Track AI. 

Fast Track AI understands the Fast Track ecosystem, how its capabilities interact and the operational context in which they are used. It can also operate within the governance, workflows and controls established by each operator. Other agents can work with a specialised Fast Track agent without learning how to operate the underlying platform. 

Simon Lidzén, co-founder and CEO of Fast Track, said:  “We believe organisations are moving towards a world where people and agents work together. For that to scale, a single agent cannot be expected to understand the inner workings of every system it interacts with.

“Fast Track AI already understands Fast Track, the player context within it, how its capabilities work together and the workflows and governance established by the operator. Agent-to-agent support means that intelligence can now participate directly in a much wider agentic organisation. 

“We want Fast Track AI to work alongside the other agents an operator adopts, helping them make better-informed decisions wherever those decisions are being made.” 

Fast Track has also continued to expand beyond CRM execution. 

Fast Track’s platform brings together real-time player data, engagement history, gamification, gameplay risk, value modelling and AI-driven decision-making. Products including Fast Track Rewards, Greco and True Value all form part of a broader intelligence layer that helps operators see what is happening and decide where to act. 

An agent working within another area of the business could, for example, request relevant player context or intelligence from Fast Track AI without needing direct knowledge of Fast Track’s data structures, APIs or internal tools. Fast Track AI can interpret the request, apply its domain understanding and return the appropriate context or action within the operator’s established controls. 

Specialist agents stay focused on their own domains while drawing on Fast Track’s data science and real-time context. 

Lidzén continued: “The opportunity becomes much bigger when agents stop being confined to individual products. An agent should be exceptionally good at understanding its own domain, but it should also be able to collaborate with the rest of the organisation. 

“As Fast Track continues to expand its capabilities in AI, data science and modelling, we want that intelligence to become increasingly useful across the operator, not only inside one interface or one team. Agent-to-agent support is an important step in making that possible.” 

The release forms part of Fast Track’s continued development of an AI-native platform. 

Frequently asked questions (FAQs)

• What is agent-to-agent support in Fast Track AI? It lets Fast Track AI communicate and collaborate directly with other AI agents used by an operator. Those agents can request player context or intelligence and receive responses that already incorporate Fast Track’s domain knowledge and governance rules.
• How is this different from APIs or MCP tools? An MCP or API approach makes tools available, but the consuming agent still has to decide when and how to use them and understand the platform. Fast Track keeps that expertise inside Fast Track AI so other agents do not need to learn the system.
• What can other agents request from Fast Track AI? They can ask for relevant player context, behavioural intelligence or decision support. Fast Track AI interprets the request, applies its understanding of the operator’s data and workflows, and returns appropriate information or actions within established controls.