Category
Chat Engine
Omnichannel AI Chatbot platform, integrations, and user journeys
API Specification
--- The Chat Engine API is organized into 5 domains. Knowledge and contact management are delegated to AI Brain and Contact Intelligence respectively. | Domain | Base Path | Descri
Chat Engine — Backlog
Audited 2026-06-28. Overall: 7.8 / 10 | Parameter | Score | Notes | |-----------|------:|-------| | API Design | 8.0 | 25+ routes, SSE streaming, cursor pagination; analytics/event
Domain Model
This document defines the core business entities and their relationships for the Chat Engine. --- With AI Brain and Contact Intelligence now built, the Chat Engine's domain is narr
Frontend & UI Specification
This document outlines the detailed user interface structure, page layouts, and component interactions required in the apps/seller-dashboard Next.js to manage the Chat Engine. ---
Chat Engine — Durable Object Hot Path (Neon scale-to-zero)
Last updated: 2026-07-01 Status: Built, flag-gated CE_HOTPATH_DO, NOT enabled in prod. Validate one tenant before rollout. --- chat-engine ce_, contact-intelligence ci_, and brain
Memory Management Specification
--- In v1, the Chat Engine owned its own tri-layer memory pgvector, Redis, PostgreSQL. In v2, memory is fully delegated: | Memory Type | Service | How Chat Engine Uses It | |:---|:
Proactive Sessions — Architecture Reference
Last updated: 2026-06-30 Status: Architecture decided. Implementation Phase 8. Verified against live source. --- CE is currently 100% reactive — contacts initiate, CE responds. CI
Prompt Engineering & AI Security Spec
This document outlines the core LLM orchestration strategies, prompt wrappers, context injection rules, and systemic guardrails for the Chat Engine. Since the LLM is nondeterminist
Security & Privacy Spec (Trust & Safety)
This document outlines the strict data privacy, multi-tenant boundaries, and cryptographic security measures implemented within the Chat Engine. Since the system ingests proprietar
System Architecture: HLD & LLD
This document defines the High-Level Design HLD and Low-Level Design LLD for the LogicSpike Chat Engine, an omnichannel AI chatbot platform. --- The Chat Engine is the thin orchest
Tool Registry — Architecture Reference
Last updated: 2026-06-29 Status: Architecture decided. Implementation Phase 7. --- CE currently gives the LLM one tool: recall_memory. This makes it a talking bot only. Tool Regist
Phase 1: Discovery & User Journeys
The Chat Engine Omnichannel AI Chatbot Platform is a powerful, integrated service offered to LogicSpike Tenants Business Owners, E-commerce, Agencies. It allows them to instantly p
Chat Engine — Product Vision
Last updated: 2026-06-29 Status: Architecture finalized. Phase 6A intelligence layer, no storage change ready; Phase 6B DO/D1 storage deferred. Verified against live source 2026-06
Voice Agent — Architecture Reference
Last updated: 2026-06-29 Status: Architecture decided. Implementation deferred to Phase 16. --- A voice channel for CE where contacts speak and the bot responds in audio. Same CE i