ProcureIQ — Autonomous Procurement Analyst Agent

ProcureIQ is an autonomous AI agent that prepares software contract renewals end-to-end in under 20 seconds — detecting upcoming renewals, pulling negotiation history from memory, gathering live market intelligence, computing BATNA (Best Alternative to a Negotiated Agreement), generating a cited negotiation brief, drafting a vendor outreach email, and routing for internal approval — all without human intervention. Pitched as: "The autonomous procurement analyst for mid-market companies that can't afford Tropic ($36K/yr). Self-hosted for ~$600/yr." 10-step ReAct loop powered by IBM Watsonx Orchestrate ADK (tool registration), IBM Watsonx.ai Granite-3-8b-instruct (brief + email generation), IBM Watsonx slate-30m embeddings (semantic cache), Tavily (4 parallel vendor intelligence queries), and Redis (SemanticCache for 7-day vendor intel + long-term negotiation memory via Agent Memory Server). Key capabilities: - Live market intelligence: pulls competitor pricing, vendor red flags, and financial signals from 20+ sources per vendor via Tavily - Semantic cache: RedisVL SemanticCache stores intel with IBM Watsonx embeddings — cache hits return in <200ms, saving Tavily credits - Long-term memory: Redis Agent Memory Server retains negotiation history across sessions; agent cites past outcomes when computing leverage - BATNA calculator: computes target price, walk-away price, discount %, leverage points, and a 0–100 confidence score from contract + usage + intel data - Fully template-fallback: demo runs without LLM keys; IBM Watsonx unlocks LLM-generated briefs and emails Demo scenarios: A) Datadog (strong leverage) — 48 unused seats + competitor pricing → 20%+ target discount B) Snowflake (weak leverage) — 95% utilization → agent honestly says "weak position" C) Cache hit — re-run any vendor → Redis returns intel in <200ms, no Tavily credits used

View source

// Project brief

// Built with

IBM

Redis

TavilyFastAPI,Streamlit,IBM Watsonx Orchestrate ADK, ibm-watsonx-ai SDK, Python 3.12, uv

// More from this event

Keep exploring what builders shipped.

All projects →

solosquard

mystery-shopper-AI

Automate the detection of signup friction using AI agents that navigate like real users and report issues instantly.

RedisTavilyIBM

ContractIQ

We built ContractIQ, a 6-agent procurement workflow that turns contract documents into a decision-ready renewal package. IBM watsonx Orchestrate manages the full agent flow, including routing, parallel execution, confidence checks, and approval gates. Redis powers workflow state, inter-agent messaging, audit history, and cached memory across the pipeline. Tavily brings in live external research like vendor pricing, market signals, and competitive alternatives to ground the final recommendation.

RedisTavilyIBM

Midas

OpenClaw Finance Agent — Enterprise AI that learns your business without seeing your secrets. Finance teams want AI that understands their vendor patterns, approval workflows, and GL structures — but compliance (GDPR, SOX, CCPA) blocks them from exposing sensitive data to train it. The result is that companies only use AI for suggestions. It's too risky to let it actually execute anything. We built a local-first AI system that solves this with comprehensive tokenization. Before any AI model sees the data, every sensitive field is replaced with a structural token. Microsoft Corp becomes VENDOR_001[TIER_LARGE]. $150,000 becomes AMT_LARGE[CFO]. Employee emails become APPROVER_LEVEL_CFO. PII is never extracted in the first place — it doesn't enter the pipeline at all. The model learns your company's patterns from tokens alone. The system uses two-tier AI routing. A locally fine-tuned model (LoRA on Mistral 7B, 4-bit quantized) handles 80% of routine tasks like invoice processing, spend analysis, and GL posting — under 500ms at $0.01 per task. Complex reasoning like forecasting and risk analysis routes to Claude API at $0.50 per task. Smart routing decides based on task complexity and model confidence. Every AI decision passes through MCP governance servers before execution. Is the approver authorized for this amount? Is the GL account valid? Is there budget available? Are there any policy violations? All gates must pass before the system acts. Every decision is logged to an immutable, hash-chained audit trail stored in tokens — not real data. SOX compliant by design. The architecture runs two isolated AI agents: Hermes handles coding and infrastructure (Docker, GitHub, codebase intelligence, Doppler secrets), while Midas handles financial analysis and compliance (governance, audit, GL validation, Tavily research, Redis). Each agent has its own Claude Code CLI wrapper and dedicated MCP servers. Namespace isolation ensures Hermes never touches financial governance and Midas never touches infrastructure. Training improves continuously through three channels: Tavily batch-researches public financial data, the /dream command generates synthetic training examples on demand, and Honcho from Plastic Labs automatically optimizes prompts based on real usage patterns. The system gets smarter with every interaction. Custom AI trained on your tokenized data. Runs on a laptop. Zero cost per local query. Full compliance audit trail. Policy-governed execution. Built in 48 hours for the IBM Hackathon, Procurement and Finance Track. https://www.loom.com/share/d05ac73cb5f94fb1b2ad99df0e1d32ea

RedisTavily