Agent Tracks

Chat interface for historical Adaptive event JSON data. Ask questions in plain language, get charts, tables, and answers. Makes procurement analytics accessible to buyers and CS without SQL or a BI tool.

Redesign the Adaptive UI to the level of the best consumer-grade products — so easy someone with no procurement experience can use it with no training. Clean, polished, and futuristic with UX focused on current user state, next action, and JTBD.

Reduce UI complexity through contextual AI assistance. Intelligently pops up at the right moments when help could be needed — providing relevant guidance with the ability to chat. Can guide to different parts of the system, explain system behavior, and actively help create or update specific pages — turning Copilot from a reactive helper into a proactive builder. You can add information to the brain/memory on the go. It can tell you what is next for you. Smart Clippy 2026!

Takes request data or uploaded files and creates the best possible FM Adaptive sourcing event — with proper module selection, field mapping, and content population. Handles different file types including XLS, Word, PDF, and as a bonus, PPT slides. The goal is a fully configured, ready-to-launch event with minimal human input. The extra bonus being able to consume and process extra large complex engineering files like product design docs, engineering concepts, and abstract technical diagrams.

Transforms unstructured input — files, emails, Slack/Teams messages, images, voice recordings — into a native compelling fully backed request.

Enables same-day onboarding — ideally hours. Automate customer data upload and mapping during onboarding. Drop data — any format — and the agent auto-maps fields, validates cross-references, and surfaces gaps before a human has to touch it. Scope includes intake schema, rules, data fields, pricebooks, Adaptive default templates, categories, suppliers, POs, golden dataset generation, system pre-flight check, and customer-shareable reports or interfaces for feedback.

Upgrade the current rec system to intelligent, explainable supplier recommendations that outperform both standalone LLMs and existing AI recs by combining the two approaches. Grounded in FM spend history and supplier performance data, it helps with discovery and ranking by intertwining traditional and AI-driven methods. It can gather live data from the internet, build supplier advanced profiles, utilise LLM for data generation and validation, utilise advanced ranking criteria and algorithms. Can support complex input formats like any JSON structure.

Interface within the Supplier Portal that helps suppliers fill in responses to RFXs — both Fairmarkit-generated events and external RFXs imported from other systems. The agent helps suppliers respond to more events with higher-quality answers by learning from previously submitted responses as a knowledge base. By extending to non-Fairmarkit events, this capability can be productized as a premium supplier experience. Having more supplier activity — qualitative and quantitative, beyond just what is generated in Fairmarkit events — also provides more relevant data to further improve supplier recommendations.