Back to blog
Case Study

How Anthropic Claude Powers IMPACT and CostKatana

·12 min read

At Hypothesize, we build products that solve real problems with AI. Two of our flagship offerings, IMPACT, built with P3M.AI, and CostKatana, rely on Anthropic's Claude models as a core intelligence layer. This case study details exactly how we use Claude in each product, from model selection and orchestration to reporting and cost tracking.

CostKatana: How Claude Is Used

1. Governed Agent (AI Task Orchestration)

The Governed Agent selects Claude models by task complexity:

This tiered approach ensures the right model for the job, using Sonnet 4.5 for production code and deep reasoning, and Haiku 4.5 for lightweight tasks to optimize cost and latency.

2. Auto Recommendation Agent

Uses Claude Haiku 4.5 (via AWS Bedrock) for cost optimization advice based on usage patterns.

3. Visual Compliance

Claude 3.5 Sonnet is used for visual and design compliance checks.

4. Chat and AI Routing (Cortex)

Claude models are exposed through the AI gateway as one of the supported providers. Requests are routed to the correct model via Bedrock and the AI router.

5. Pricing and Cost Tracking

Anthropic is configured as a provider in the pricing registry. Cost calculation and token counting use Anthropic's tokenizer (@anthropic-ai/tokenizer). Model pricing for Haiku, Sonnet, and Opus (3, 3.5, 4, 4.5, 4.6) is stored and used for cost estimates.

6. AWS Bedrock Integration

Claude is invoked through AWS Bedrock, which provides multiple Claude variants (Haiku, Sonnet, Opus), regional deployment control, and fallbacks when inference profiles are missing.

7. Marketing and Landing Pages

The marketing site highlights Claude as a supported provider in pricing tables and provider logos.

CostKatana Summary

Use CaseModel(s) UsedPurpose
Governed AgentSonnet 4.5, 4, Haiku 4.5Task planning and execution by complexity
Auto RecommendationsHaiku 4.5Cost optimization suggestions
Visual ComplianceSonnet 3.5Visual/design compliance checks
Chat / AI GatewayAll supported modelsUser-facing chat and AI routing
Cost TrackingAll modelsUsage and cost analytics
ExperimentationVariousA/B testing and model comparison

P3M (IMPACT): How Claude Is Used

Infrastructure

Claude is accessed via AWS Bedrock (not the Anthropic API directly). The default model is Claude 3.7 Sonnet (anthropic.claude-3-7-sonnet-20250219-v1:0). A fallback model, Claude 3.5 Haiku, is used when the main model fails. Configuration is via env vars: AI_MODEL=claude, CLAUDE_INFERENCE_PROFILE_ARN, FALLBACK_CLAUDE_INFERENCE_PROFILE_ARN. The system can be switched to Nova Pro by setting AI_MODEL=nova.

Cost & Usage

CostKatana is used for usage tracking. Per-organization AI credits are enforced, calls are blocked without sufficient credits. Token usage and costs are recorded in the AIUsage model.

Where Claude Is Used (Use Cases)

FeatureServicePurpose
KPI generationaiKpiServiceGenerate KPIs from category name, description, industry context, and requirements
Criteria enhancementaiKpiServiceImprove/refine KPI criteria and task templates
Audit summariesaiAuditServiceAnalyze audit data and create summaries
Audit analysisaiAudit.controllerDeep analysis of audit results
Auditee reportsaiAuditeeReportServiceAI reports for individual auditees using audit and assessment data
Anecdotal recordsaiAnecdotalRecordServiceVertical, horizontal, and trend analysis of performance records
Overall reportsoverAllReportServiceDashboard reports combining audits, tasks, and trends
Video auditsvideoAuditServiceAI analysis of video audit content
One-time auditsoneTimeAuditAIServiceAI analysis for ad-hoc audits
Assessment reportsassessmentAIServiceAI-generated assessment reports
Group analyticsgroupAnalyticsServiceAI insights and comparisons across groups
Dashboard insightsaiDashboardInsightServiceAI insights for dashboards
AI chatbotaiChatbotServiceIntent detection, extraction, and conversational responses

Claude powers content creation and analysis in P3M across reports (audit, auditee, assessment, video, one-time, and dashboard), KPI setup (generation, criteria refinement, task templates), anecdotal records (trend and horizontal analysis), group analytics, the AI chatbot, and dashboard insights. Note: AI relevance filtering for search results (e.g., image-based filtering) uses Amazon Nova Pro in AIRelevanceFilterService, not Claude.

Summary

Both CostKatana and P3M rely on Claude as a core AI layer: CostKatana for governed orchestration, cost optimization, and tracking; P3M for audit analysis, report generation, KPI refinement, and conversational AI. AWS Bedrock provides scalable, regional access to multiple Claude variants, while CostKatana tracks usage and costs across the stack.

Interested in how we can help you leverage Claude for your products? Get in touch.