Zapvol Documentation
Agent engineering concepts on one side, Zapvol platform docs on the other.
Zapvol
Getting Started
Set up Zapvol and run your first agent task in minutes.
Concepts
Design principles and mental models — how to think about Zapvol's primitives before reading the architecture.
Architecture
How the monorepo, packages, and runtime pieces fit together.
Platform
Cross-cutting platform concerns shared by every subsystem — authentication, storage, secrets, networking.
Operations
Observability stack, log pipeline, dashboards — how to run and monitor Zapvol in production.
Business
Economics
The economics of LLM products. Cost model, control mechanisms, and ROI framework — universal thinking for any LLM agent product.
Metrics
Planned — business metrics for LLM agent products: north-star, retention, unit economics, activation path.
Pricing
Planned — pricing strategy for LLM agent products: subscription, usage-based, hybrid, tier design, enterprise contracts.
Growth
Planned — growth mechanisms for agent products: activation, expansion, self-serve vs sales-led, referral, onboarding.
Playbooks
Planned — operational playbooks for customer success, onboarding, expansion, churn-save, and internal support.
Compliance
Planned — data compliance, audit trails, model output liability, and industry certifications (SOC2 / HIPAA / GDPR).
AI SDK
Harness
Harness Engineering
Build agent harnesses — long-running flows, multi-agent coordination, context engineering.
Context Engineering
Design theory for prompts, memory, and context lifecycle — treat the attention budget as a finite resource.
Claude Code Design
Reverse-engineer Claude Code — the reference agent harness — to extract design principles for building your own.