- Productized workflow library
- Core Console self-serve operator surface
- Per-firm budget cap + audit log
- Standard integrations (CRM, email, docs, storage)
- Email support, business hours
- Cancel anytime
Plans that scale with what you actually run.
Core is published and self-serve. Forge and Private Edge are scoped to your engagement so you see the design, the timeline, and the run-rate before you commit.
- Workflow design pass
- Custom integrations to your existing tools
- Evaluation suite scored before production
- Configurable human-review gates
- Same platform safety net as Core
- Direct engineering line
- Secure on-prem appliance, NWA-managed
- Local RAG (pgvector) — no documents leave the firm
- Outbound-only mTLS to control plane
- Self-healing 5-stage recovery
- Custom workflow design, like Forge
- Direct engineering line
What you get at each tier.
| Feature | Core | Forge | Private Edge |
|---|---|---|---|
| Productized workflow library | ✓ | — | — |
| Custom workflow design | — | ✓ | ✓ |
| Custom integrations | Standard set | ✓ | ✓ |
| Evaluation suite | — | ✓ | ✓ |
| Per-firm budget cap | ✓ | ✓ | ✓ |
| Audit log per step | ✓ | ✓ | ✓ |
| Human-review gates | ✓ | ✓ | ✓ |
| Versioned releases | ✓ | ✓ | ✓ |
| Data residency — NWA cloud | ✓ | Optional | — |
| Data residency — customer premises | — | Optional | ✓ |
| Local RAG (documents stay on-node) | — | — | ✓ |
| Outbound-only mTLS network | — | — | ✓ |
| Self-healing supervisor | Cloud-native | Cloud-native | 5-stage on-appliance |
| Customer support | Email (business hours) | Direct engineering | Direct engineering |
| Free trial | 15 days | Discovery call | Discovery call |
| Pricing | $2/day per agent + AI usage | Custom | Custom |
Common questions about pricing.
What counts as a deployed agent?
A deployed agent is one workflow assigned and enabled on your account. Disable a workflow and the daily charge stops the next billing day.
Is there a free trial?
Yes — Core includes a 15-day free trial with no card required. Forge and Private Edge engagements start with a discovery call and a design pass before any commitment, so you see the timeline and run-rate first.
How is AI model usage billed?
AI model usage is passed through at cost. The platform tracks tokens per workflow and per firm, enforces a per-job budget cap, and shows your current month's usage in the Core Console.
Workflows raise a budget error before the API call when the cap would be exceeded. Silent overspend isn't a configurable state.
Can I cancel anytime?
Yes. Daily-charged Core agents stop charging the next billing day after you disable them. Forge and Private Edge have engagement terms scoped before signing.
Where is my data stored?
Core runs in NWA-managed Google Cloud Platform infrastructure (US region). Forge can run there and/or on Edge nodes, depending on the workflow's data boundary.
On Edge, data is stored on the on-prem appliance at your premises. Only retrieved chunks ever cross the network boundary; full documents stay on-node.
Is my data portable?
Yes. Audit logs and account data are exportable. Workflow definitions are portable across tiers — a Forge workflow can move to Private Edge without rewriting the workflow.
What happens at end-of-trial on Core?
You'll be prompted to add a payment method to continue. Disabled agents stop charging immediately. No agents are billed without an explicit enable from your operator.
Are there volume discounts?
Talk to us. For multi-agent or multi-site deployments, we structure pricing per engagement.
Need a custom quote?
Forge and Private Edge engagements are scoped per project. We'll outline timeline, design, and run-rate after the discovery call.