Procurement tech

A recent Airbase report found 96% of procurement teams already use AI for tasks like market intelligence, automated data entry, contract analysis, and predictive analytics.

Procurement tech

experience

Plank teams have built AI systems for procurement including supplier matching, sourcing automation, contract analysis, and spend insights, all integrated with ERP systems and designed for continuous learning.

Procurement tech
AI-Driven Supplier Discovery and Risk Scoring
  • Use LLMs and embeddings to extract, normalize, and match vendor data across public directories, certifications, and inbound proposals.
  • Score vendors on delivery performance, ESG criteria, pricing volatility, and contractual risk using predictive models.
  • Recommend supplier alternatives and diversification strategies based on category benchmarks and performance patterns.
Automated Sourcing and Negotiation Agents
  • Generate RFPs/RFQs using AI from prior templates, spend history, and spec documents.
  • Use AI agents to analyze incoming bids, detect anomalies, and recommend award strategies based on multi-factor optimization.
  • Enable real-time negotiation support with chat-based interfaces and suggested counter-offers.
Smart Purchase Order Routing and Approvals
  • Apply AI to detect outliers and route POs based on past exceptions, urgency, and policy context.
  • Predict delays, budget breaches, or contract non-compliance from PO patterns and supplier behavior.
  • Support adaptive approval flows that learn from user decisions and organizational patterns.
Spend Intelligence and Anomaly Detection
  • Automatically categorize spend data using NLP over invoice line items and procurement descriptions.
  • Surface trends, outliers, and savings opportunities using unsupervised clustering and anomaly detection.
  • Power dashboards that adapt in real-time to user queries and highlight risk or inefficiency hotspots.
Contract Intelligence and Compliance Monitoring
  • Extract clauses, obligations, and renewal terms from scanned or structured contracts using OCR and LLMs.
  • Monitor usage, spend, and SLAs against contract terms with alerting for breaches or renewals.
  • Summarize and compare contractual risks across similar agreements for audit and compliance teams.
Integrated Infrastructure with AI Feedback Loops
  • Use event-driven architecture to integrate with ERPs and finance systems while collecting training signals from workflows.
  • Continuously improve models for categorization, scoring, and recommendations using user interaction data.
  • Maintain SOC 2 and ISO-compliant data pipelines while enabling safe, adaptive AI learning within procurement environments.

Customer Showcase

Diagon AI

Procurement tech
Procurement tech
Energy tech
Energy tech
Saas
Saas

Diagon is a VC-backed AI-powered equipment sourcing platform that unifies hardware, services, and financing into one streamlined experience—built by a team that has managed over $5B in manufacturing equipment for leading brands like Tesla, Astra, and Bright Machines.

AI-powered procurement research copilot:

‍
Built a domain-specific AI agent system fine-tuned on battery chemistries, vendor catalogs, and robotics specs—enabling procurement teams to explore, compare, and source equipment with precision.

Autonomous vendor workflow automation:

‍
Replaced manual procurement steps (email, fax, RFPs) with a multi-agent system that autonomously handles vendor inquiries, negotiations, and evaluations—learning from prior transactions to improve over time.

Scalable, intelligent data ingestion engine:

‍
Engineered a smart crawling and indexing pipeline to fetch and deduplicate tens of terabytes of equipment data, ensuring a continuously updated knowledge base with minimal manual upkeep.

Dynamic taxonomy generation via topic modeling:

‍
Developed an AI system that classifies equipment and SKUs using semantic embeddings and unsupervised topic modeling—creating a unified schema across diverse product types without hand-labeled categories.

‍

see details

Fitmate

Procurement tech
Procurement tech
Consumer
Consumer

Fitmate is an AI-powered fitness coaching platform, trusted by institutions like Stanford and Duke Medicine, that combines an AI coach with human coaches to support users with personallized health goals.

LLM-powered multi-agent AI health coach:

Built a personalized coaching system using LangGraph, orchestrating agents for fitness planning, nutrition, obstacle handling, and recipe recommendations. The system maintains evolving user profiles with both short- and long-term memory via vector embeddings.

Real-time insight extraction from voice calls:

Developed a Gemini LLM-based pipeline to transcribe human coach calls and extract actionable insights, enabling real-time updates to user plans.

AI-driven recipe engine with Instagram integration:

Developed a Gemini LLM-based pipeline to transcribe human coach calls and extract actionable insights, enabling real-time updates to user plans.

Enterprise-grade security and scalability:

Architected for millions of users with HIPAA and SOC-2 compliant infrastructure, integrated with leading EHR systems, and supported by dynamic prompt evaluation pipelines using LangSmith and Braintrust. Built with custom eval pipelines (LangSmith + Braintrust) to reduce hallucinations and ensure model quality through live and synthetic testing.

see details

Engineers we’ve worked with

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut morbi bibendum interdum sit. Tincidunt magna nisi, a amet sit enim dui accumsan. Phasellus in nunc gravida.

Engage With Our Lab

For Companies

Build a team

Work with us
For Engineers

Join a team

View open roles
For Graduates

Accelerate your career

Learn about fellowships
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.