Browse Tasks

Select category

Select category

Select category

Select category

Select Task

Select Task

Select Task

Select Task

Select Tasks

Select Industry

Agent Playbook

Browse agentic AI tasks that instruct LLMs to carry out specific jobs.
These can be integrated into existing workflows in your apps and tools.

Claims Policy Verification

Claims Triage

Claims Fraud Analysis

Customer Query Categorisation

Policy Comparison

Damage Assessment from Images

Insurance Needs Analysis

Policy Renewal Recommendation

Claims Status Update

Compliance Documentation Check

Claims Documentation Validation

Query Triage and Escalation

Marketing Analyst

Personalised Product Recommendation

This agentic AI task generates personalised product recommendations - vital for e-commerce personalisation agents. The task configuration outlines how to:

  • Analyse user behaviour patterns and preferences

  • Identify relevant product associations and trends

  • Generate contextually appropriate suggestions

  • Rank recommendations by user relevance

  • Adapt suggestions based on interaction data


As a modular task, it integrates with catalogue and analytics systems, enabling AI agents to execute intelligent recommendation generation within existing e-commerce workflows. The task specification includes outputs for preference analysis, product matching, and recommendation optimization, adaptable across various retail contexts and user segments.

Example outputs:

{
  "recommended_products": [
    "PROD123",
    "PROD456",
    "PROD789",
    "PROD101",
    "PROD202"
  ],
  "recommendation_reasons": [
    "Similar to recently viewed running shoes",
    "Complementary to user's recent purchase of fitness tracker",
    "Trending product in user's frequently browsed 'Outdoor Gear' category",
    "Based on positive reviews from users with similar purchase history",
    "Seasonal recommendation aligned with user's interest in winter sports"
  ],
  "user_affinities": [
    "Athletic footwear",
    "Fitness technology",
    "Outdoor activities",
    "Winter sports equipment"
  ],
  "recommendation_strategy": "Mixed strategy: Past behaviour, complementary products, and seasonal trends",
  "confidence_scores": [
    "95",
    "88",
    "82",
    "79",
    "75"
  ],
  "diverse_recommendations": true,
  "personalisation_level": "High",
  "additional_insights": "User shows a strong preference for premium athletic brands and tends to make purchases in preparation for seasonal activities. They are also likely to be interested in new fitness technology products."