Agentic Workflow Orchestrator banner
nammnjoshii nammnjoshii

Agentic Workflow Orchestrator

Data community

Description

A production-style agentic workflow platform for procurement intelligence. Discovers opportunities across 12 fragmented public portals, filters and scores them through a 7-agent pipeline, enriches them with stakeholder contacts, and delivers a fully automated ranked intelligence digest, twice weekly.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Agentic Workflow Orchestrator

A production-style agentic workflow platform for procurement intelligence. Discovers opportunities across 12 fragmented public portals, filters and scores them through a 7-agent pipeline, enriches them with stakeholder contacts, and delivers a ranked intelligence digest — fully automated, twice weekly.

![Python](https://img.shields.io/badge/Python-3.11+-blue?logo=python&logoColor=white) ![Tests](https://img.shields.io/badge/Tests-197%20passing-brightgreen) ![License](https://img.shields.io/badge/License-MIT-lightgrey) ![GitHub Actions](https://img.shields.io/badge/CI-GitHub%20Actions-2088FF?logo=github-actions&logoColor=white)


What It Does

Government procurement portals publish hundreds of RFPs per week across fragmented sources with no unified API. Manual review is inconsistent, time-consuming, and misses opportunities that don't match obvious keywords. This platform automates the full intelligence cycle:

  1. Discovers — scrapes 12 Canadian and US government procurement portals twice weekly
  2. Scores — runs a two-phase LLM scoring pipeline against a configurable capability profile
  3. Enriches — discovers and validates decision-maker contacts at each issuing organization
  4. Delivers — produces a ranked Intelligence Digest with scored opportunities and personalised outreach openers every Monday morning

Architecture

flowchart TD
    A[12 Procurement Portals] --> B[ProcurementIntelligenceSpecialist\nPlaywright + BeautifulSoup4]
    B --> C[OpportunityQualificationSpecialist\nPre-filter LLM · 0–100 score]
    C --> D[StrategicScoringAgent\nScoring LLM · 9 structured fields]
    D --> E[ScoringAssuranceAnalyst\nValidation + retry · max 2]
    E --> F[StakeholderIntelligenceSpecialist\nSerpAPI + Hunter.io]
    F --> G[StakeholderRelevanceAgent\nWeighted relevance scoring]
    G --> H[ExecutiveOutreachStrategist\nPersonalised opener]
    H --> I[(SQLite DB)]
    I --> J[IntelligenceDeliveryA