Multi-agent orchestration
Specialist agents for query parsing, product configuration, pricing, and quote generation, coordinated through structured handoffs.
Case Study · B2B PROCUREMENT
Natural-language B2B procurement.
The story
B2B procurement is full of multi-step friction, parse the quote request, configure the right product, calculate dynamic pricing, generate a quote. Founder Melyssa Plunkett-Gomez saw the opportunity to collapse this into a natural-language AI workflow. KUMO is building Racepoint as a multi-agent LLM SaaS.
What we delivered
Specialist agents for query parsing, product configuration, pricing, and quote generation, coordinated through structured handoffs.
Procurement teams interact in plain language; agents handle the multi-step backend without exposing the orchestration.
Inventory- and contract-aware pricing that adapts in real time to availability, terms, and customer-specific deals.
Quote document creation with the configuration, terms, and pricing context resolved, ready for review and send.
Evaluation harnesses per agent so regressions are caught in CI before they reach a customer.
Observability, fallback paths, and human-in-the-loop on edge cases, designed for production, not a demo loop.
Highlights
FINTECH · YC S20 How KUMO built the first production version of Volopay, a YC S20 corporate-card fintech that's raised $30M and operates across 6 countries.
Read the story ->
B2B SAAS · OUR OWN PRODUCT How KUMO built and operates CampaignHQ, our own cloud-native email and WhatsApp marketing automation platform.
Read the story ->How KUMO built Equipp, the digital rental marketplace for Ralco Synergy, a 25-year IT hardware leader serving India's top tech companies.
Read the story ->We'll listen first, ask the right questions, and follow up with a clear proposal.