Satnam Singh← all work
2025Startup Intelligence · Co-sellDemo available

Startup Advisor & Co-sell Intelligence Platform

A multi-agent intelligence platform that unifies startup, engagement, funding, milestone, and co-sell data into account-, portfolio-, and co-sell-level analyses for advisor recommendations.

Azure AI FoundryMicrosoft FabricAzure AI SearchDQM
headline impact
Demo
advisor and co-sell intelligence · account + portfolio + co-sell analysis in one agentic flow
my role
Role
Developer · architecture, agent logic, data integration, workflow integration, and Microsoft Fabric grounding
status
Status
Demo available · advisor intelligence workflow
demo
Demo available
Demo walkthrough available
the problem

What was broken

Startup Advisors lacked consolidated visibility into portfolio health, milestones, funding readiness, engagement, and co-sell opportunities. Workflows depended on manual analysis across fragmented systems, limiting proactive startup activation and consistent co-sell execution.

my approach

How I built it

I built a multi-agent platform on Azure AI Foundry, Microsoft Fabric, Azure AI Search, and workflow integration services. External data from Founder Hub CRM and Excel is ingested through Shortcuts, Dataflows, and Pipelines into a Fabric Lakehouse on a Medallion architecture, with DQM checks and a metadata + document index layer. On top, Foundry agents run three layers of analysis — Account-level startup info, Portfolio-level concentration and risk, and Co-sell readiness — feeding a Recommendation Agent that aggregates outputs into prioritised advisor actions.

why this way

The reasoning

Advisor workflows are not one question — they are three different lenses on the same startup. Splitting that into dedicated agents under a Recommendation Agent keeps each lens focused and composable. Fabric + DQM gives a single governed data spine, and vectorised domain knowledge in AI Search keeps recommendations grounded.

architecture

How the pieces fit

Data Sources
Founder Hub CRMExcel files
Ingestion & Data Layer (Fabric)
Shortcut · Dataflow · PipelineLakehouse · MedallionDQM CheckMetadata & Document Index
Agent Layer (Azure AI Foundry)
Account-level AnalysisPortfolio-level AnalysisCo-sell AnalysisRecommendation Agent
Retrieval
Azure AI Search · Vector IndexEmbeddingsSemantic / Vector SearchStructured Startup Data
Workflow Integration
Advisor action outputPrompt historyTelemetrySSO · Entra ID
what I built

Key components

  • 01Microsoft Fabric Lakehouse on a Medallion architecture with DQM checks
  • 02Metadata and document index layer feeding the agents
  • 03Account-level agent: startup info, milestone progress, workload usage, growth lever
  • 04Portfolio-level agent: milestone concentration, churn risk, funding events, touch status
  • 05Co-sell agent: co-sell readiness, account status, advisor input, business summary
  • 06Recommendation Agent aggregating outputs across all three lenses
  • 07Azure AI Search vector index over startup domain knowledge
  • 08Advisor action output with telemetry and prompt history
  • 09Single Sign-On through Microsoft Entra ID
what I used

Tech stack

Agentic AI
Azure AI FoundryAzure OpenAIMulti-Agent OrchestrationRAG
Data
Microsoft FabricLakehouseMedallion ArchitectureDataflowsPipelinesDQM
Integration
Azure Logic AppsFunction AppsREST APIs
Retrieval & Security
Azure AI SearchVector SearchEmbeddingsMicrosoft Entra ID
video demo

Supabase-hosted walkthrough

Startup Advisor & Co-sell demo

see it run

In-browser demo

A scripted walkthrough of the demo flow, traced step by step.

startup_advisor · weekly portfolio sweep
press play to watch the trace
next up
Automated DQM Frameworkopen →