slug: pypestream provider: Pypestream generated_by: planning/capability-mapping/scripts/classify_capabilities.py model: claude-opus-5 frame: - Telecommunications min_confidence: 0.7 capability_model: source: https://github.com/vincentmakes/turbo-ea-capabilities license: CC-BY-4.0 attribution: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities, CC BY 4.0 notice: NOTICE edge_count: 3 edges: - tag: Conversations API spec_file: pypestream-conversations-api-api-openapi.yml capability_id: BC-430.10 capability_id_l1: BC-430 capability_name: Customer Inquiry Management confidence: 0.75 evidence: POST /contactCenter/v1/conversations/{conversationId}/end End Chat; GET /contactCenter/v2/conversations/{conversationId}/history Retrieve Conversation History reason: Contact-centre conversation handling — sending messages, typing indicators, ending chats and retrieving history — realises inbound customer contact handling/resolution. - tag: Insights spec_file: pypestream-insights-api-openapi.yml capability_id: BC-4280.30 capability_id_l1: BC-4280 capability_name: Product Usage Analytics confidence: 0.75 evidence: insights_funnel_retrieve, insights_path_retrieve, insights_retention_retrieve, insights_trend_retrieve reason: Funnel, path, retention and trend analyses over event datasets are exactly the analytical views of product usage described by Product Usage Analytics. Some chance the intended framing is generic analytics/BI, hence 0.75. - tag: Endpoints spec_file: pypestream-endpoints-api-openapi.yml capability_id: BC-430.10 capability_id_l1: BC-430 capability_name: Customer Inquiry Management confidence: 0.7 evidence: POST /messaging/v1/chats/{chat_id}/start Start Engagement; POST /messaging/v1/chats/{chat_id}/message Send Message reason: Messaging engagement lifecycle (start, message, typing, end) for consumer chat sessions with the AI agent — inbound customer contact handling; generic tag name lowers confidence slightly.