Supply chain · Production
Generative AI Bootcamp: AI Agents Web Series by Dataiku
The problem
(not stated)
Workflow diagram · grounded in source
1
Build conversational AI agents
ai_action
“design, build, and scale AI agents that turn complex data into conversational experiences — all powered by the Dataiku LLM Mesh”
2
Agent toolbox execution
ai_action
“using tools like dataset lookup, web search, and email notifications to deliver real results”
3
Clinical trial research automation
ai_action
“turns weeks of manual research into minutes, automating PI analysis, surfacing insights”
4
Supply chain risk assessment
ai_action
“AI agents uncover risks, suggest alternate suppliers, and calculate cost impact”
5
Financial crime investigation
ai_action
“AI agents that unify KYC, monitoring, and watchlists, uncover patterns”
Reported outcome
(not stated)
Reported metrics
Clinical research timeturns weeks of manual research into minutes
Reported stack
DataikuDataiku LLM MeshMCP
Frequently asked questions
What did this team achieve with this AI workflow?
(not stated)
What tools did this team use?
Dataiku, Dataiku LLM Mesh, MCP.
What results were reported?
Clinical research time: turns weeks of manual research into minutes (source-reported, not independently verified).
How is this supply chain AI workflow structured?
Build conversational AI agents → Agent toolbox execution → Clinical trial research automation → Supply chain risk assessment → Financial crime investigation.