Nova Core is built on a multi-layer agentic architecture. At its core is the Nova Orchestrator — a stateful coordination engine that manages agent lifecycles, task graphs, message passing, and HITL approval gates. Every agent is a microservice-like entity: stateless, LLM-backed, and scoped to a single domain.
02The Nova Core Orchestrator
The Orchestrator is the central nervous system of Nova Core. It maintains a directed acyclic task graph (DAG) for each project, where each node represents an agent task and each edge a dependency. The orchestrator schedules tasks based on graph topology, monitors completion, handles retries, and triggers HITL gates at defined phase boundaries.
The Orchestrator is stateful and survives restarts. All task state, agent outputs, and approval decisions are persisted in the Nova Core state store and are fully auditable.
Core Responsibilities
• Task Graph Management — Build, validate, and traverse project-specific DAGs derived from the LLD document • Agent Lifecycle — Spawn, monitor, pause, and terminate agents based on graph state • Message Bus — Route inter-agent messages and shared context payloads via an async pub/sub system • HITL Gate Enforcement — Block downstream tasks until human approval is received at defined checkpoints • Retry & Fallback — Detect agent failures and re-route to secondary LLM or escalate to human review
// Orchestrator task dispatch — simplifiedasyncfunction dispatchTask(task: AgentTask) {
// Resolve dependencies from task graphconst deps = await graph.getDependencies(task.id);
if (!deps.every(d => d.status === 'completed')) return;
// Check for HITL gateif (task.requiresApproval) {
await hitlGateway.requestApproval(task);
return; // Paused until human approves
}
// Route to correct agent with LLM assignmentconst agent = agentRegistry.get(task.agentRole);
const model = llmRouter.select(task.agentRole, task.complexity);
await agent.execute({ ...task, model });
}
03Agent Registry & Role Definitions
Each agent is registered in the Agent Registry with a role schema that defines its input/output contracts, allowed LLM models, token budgets, HITL requirements, and integration hooks.
Agent
Primary Model
Token Budget
Output Type
HITL
brd-agent
claude-opus-4
32k
Structured JSON + Markdown
Required
spec-agent
claude-opus-4
48k
FSD Document
Required
arch-agent
claude-opus-4
64k
HLD + LLD + Diagrams
Required
scrum-agent
gpt-4o
16k
Jira Payload (REST)
Required
ux-agent
claude-sonnet-4
24k
Wireframe Specs + Tokens
Optional
frontend-agent
claude-sonnet-4
80k
Git Commits (PR)
Optional
backend-agent
claude-sonnet-4
96k
Git Commits (PR)
Optional
cloud-agent
claude-sonnet-4
48k
Terraform / CDK Files
Optional
security-agent
gpt-4o
32k
Audit Report JSON
Required
qa-agent
claude-sonnet-4
64k
Test Suites + Report
Required
release-agent
gpt-4o-mini
16k
CI/CD Config + Notes
Required
04LLM Routing Engine
The LLM Routing Engine dynamically selects the optimal language model for each agent task based on four signals: task complexity, output type, latency requirements, and cost budget. This ensures high-stakes tasks (architecture, security) use the most capable model while routine tasks are handled cost-efficiently.
Every major phase boundary in the pipeline has a mandatory HITL gate. The gateway sends a structured notification to the project stakeholder via the Nova Core Dashboard (and optionally Slack/email). Stakeholders can Approve, Request Changes, or Reject with inline comments. Agents remain paused until a decision is received or the SLA timeout triggers an escalation.
HITL gates cannot be disabled at the BRD, Architecture, and Release phases. This is a hard constraint built into the orchestrator to ensure human oversight on all critical deliverables.
06Context & Memory Management
Nova Core maintains a two-tier memory system per project. The Short-Term Context Window carries the last N agent interactions and is passed as system context to active agents. The Long-Term Vector Store persists all documents, decisions, and code artifacts, allowing any agent to semantic-search project history at any point in the lifecycle.
07Parallel Execution Engine
Once the Architecture phase is complete and approved, the Build phase spawns up to 5 concurrent agents (Frontend, Backend, Cloud, Database, AI Stack). Each agent works on isolated branches and communicates shared contracts via the API specification locked in the LLD. The Orchestrator monitors for conflicts and mediates via a shared contract registry.
08Security & Audit Trail
Every agent action — including prompts sent, model responses received, decisions made, and tools called — is written to an append-only audit log. This log is immutable, tamper-evident, and exportable. The Security Agent performs a continuous OWASP scan on all generated code and blocks release if critical vulnerabilities are found.
Nova Core is designed for SOC 2 Type II compliance. All data is encrypted at rest (AES-256) and in transit (TLS 1.3). Customer LLM API keys are stored in an isolated secrets vault and never logged.
Constel Global
Nova Core Technical Docs v1.0 — April 2026 — Confidential
Now in Beta — 500+ teams building smarter
A Constel Global Product
Your EntireEngineering Team,
Powered by AI.
Nova Core deploys a full virtual engineering organisation — from requirements to release — using specialised AI agents that work in parallel, 24 hours a day.