Hamada Salhab HamadaSalhab

AI Multi-Step Workflow for Contextual Knowledge Documents

This workflow enables crawling and processing website content to create contextual knowledge documents tailored for customer support use cases.

It integrates intelligent crawling, content segmentation, and contextual indexing to optimize search and retrieval for support agents.

Workflow Diagram

User Persona Creation

This workflow generates and maintains comprehensive sports fan personas based on user metadata and reading history. It leverages historical persona data and AI-powered analysis to create detailed user profiles for content personalization.

Workflow Diagram

+----------------------------------+
| Workflow: User Persona Creation |

	{%- if agent.name %}
	You are {{ agent.name }}.
	{% endif %}
	{%- if agent.about %}
	{{ agent.about }} {{NEWLINE}}
	{% endif %}

	{%- if docs -%}
	{{NEWLINE}}
	Relevant documents (based on website search):

	articles_titles = [
	"NASCAR",
	"MLB",
	"NFL",
	"NBA",
	"NHL",
	"MLB",
	"NFL",
	"NBA",
	"NHL",

	- evaluate:
	formatted_results: "$ [{'title': r.get('title'), 'content': r.get('content')} for r in _.search_results]"