Content Intelligence

Documentation Index

Fetch the complete documentation index at: https://docs.kaireonai.com/llms.txt

Use this file to discover all available pages before exploring further.

​

Overview

Content Intelligence analyzes the performance of your Creatives across channels and uses AI to generate actionable insights and improvement suggestions. It identifies which subject lines, copy patterns, and Creative variants drive the best engagement — and recommends specific changes to underperforming content. Navigate to AI > Content Intelligence in the sidebar to view the dashboard, or trigger analysis programmatically via POST /api/v1/ai/analyze/content. The Content Intelligence dashboard page (/ai/content-intelligence) runs two intelligence tools automatically on load and every 5 minutes:

• analyzeOfferPerformance — Identifies top and bottom performing offers, surfaces anomalies and performance summaries
• runHealthCheck — Extracts content-related health findings (issues mentioning “content”, “creative”, or “offer”)

​

Performance Metrics Tracked

Content Intelligence tracks Creative performance using data from the Respond API. Every time you record an outcome (impression, click, conversion), the system aggregates metrics per Creative. The analyzer loads up to 200 Creatives per analysis run to prevent overly large LLM prompts.

​

Insight Types

The analysis produces two types of ContentInsight objects: Each insight includes:

​

Insights Generation

Click Generate Insights to run an AI analysis of your Creative performance data. The AI examines patterns across all your Creatives and channels.

​

Channel-Level Analysis

The AI compares performance across channels and identifies:

• Which channels produce the highest CTR relative to the overall average
• Channels outperforming the average by 30% or more are highlighted as strong performers
• Channel-specific insights include the number of Creatives analyzed for confidence assessment

​

Individual Creative Analysis

For each Creative, the AI evaluates:

• Underperformers — Creatives with CTR below 50% of the average and at least 100 impressions get flagged with rewrite suggestions
• Top performers — Creatives with CVR above 150% of the average and at least 50 clicks are highlighted as templates for new content
• Confidence is "high" for Creatives with 500+ impressions (underperformers) or 200+ clicks (top performers)

​

Subject Line Analysis

For email and push notification Creatives with subject lines, the AI analyzes:

• Short vs. long — Subject lines are split at 50 characters. If short subjects outperform long ones by 20% or more, an insight is generated
• Requires at least 4 Creatives with subject lines to run this analysis
• Reports both the short and long average CTR with sample counts

​

Rewrite Suggestions

When the AI identifies underperforming Creatives, it generates specific rewrite suggestions:

• Original Creative — Referenced by creativeId
• Suggested content — An improved version based on patterns from your top-performing Creatives
• Rationale — Why the change is expected to improve performance, based on comparison to peers
• Metrics — Current CTR, average CTR, and impression count for context

​

Applying Rewrites

When you click Apply on a rewrite suggestion:

1. A new Creative variant is created as a draft, linked to the original Creative’s Offer
2. The variant contains the suggested copy changes
3. You can review, edit, and activate the variant
4. Optionally, set up an A/B experiment to test the variant against the original

​

Heuristic Fallback

If the LLM call fails, the analyzer falls back to deterministic heuristic analysis that:

1. Computes CTR and CVR for every Creative
2. Groups by channel and identifies channels outperforming the average by 30%+
3. Flags individual Creatives with CTR below 50% of average (with 100+ impressions) for rewrite
4. Highlights individual Creatives with CVR above 150% of average (with 50+ clicks) as templates
5. Compares short vs. long subject lines when enough data is available

​

Best Practices

• Accumulate data first — Wait until Creatives have at least 100 impressions before generating insights. Small sample sizes produce unreliable analysis.
• Run insights regularly — Creative performance shifts over time. Generate fresh insights weekly or after major campaign changes.
• Test before replacing — Use A/B experiments to validate rewrite suggestions before fully replacing existing Creatives.
• Segment by channel — Channel-level insights are often more actionable than aggregate insights. Focus on one channel at a time.

​

Advanced Parameters

Each content analysis run can be fine-tuned using the Advanced Parameters panel. Expand it to adjust: Per-run overrides apply only to that analysis and do not change your saved tenant configuration. To change organization-wide defaults, go to AI Configuration.

​

Large Dataset Warning

When the Creative dataset contains 5,000 or more rows, a confirmation dialog appears before analysis begins. The dialog shows:

• Accuracy comparison — ML Worker uses TF-IDF and statistical analysis on the full dataset vs. LLM analysis of Creative metadata
• Estimated cost — Token count and approximate cost if proceeding with LLM
• Speed comparison — ML Worker processes locally in seconds vs. LLM round-trip

You can choose Use ML Worker (recommended for large datasets) or Proceed with LLM (limited to 200 Creatives).

​

Next Steps