- App typeai workflow
- Features3
- AuthYes
- Paymentsnone
- Integrationsai_provider, storage
AI features · Scoped · FixedExample scopeTicket AI-7701SCOPE SAMPLE
Fixed-price AI app features—not open-ended model experiments
Founders want AI that does a job: classify support tickets, extract fields from uploads, draft scope from a brief—not a science project billed hourly. Lab Twelve scopes AI features as bounded slices: prompt + UI + guardrails + eval hooks, priced from MVP Sprint or AI add-on ranges depending on depth. Models never invent your quote; the pricing engine maps complexity tiers to published numbers. Humans own security, cost controls, and the pass before production.
$3,950 – $6,9507–15 business days
Scope your AI featureIncluded
In scope
| Scoped AI workflow | Included |
|---|---|
| Structured outputs | Included |
| Production deploy | Included |
| Human review gate | Included |
| Handoff on model env vars | Included |
Scoped AI workflow: Not unbounded chat
Structured outputs: Validated against schema
Production deploy: Same as non-AI builds
Human review gate: Before merge to main
Handoff on model env vars: You hold API keys
Excluded
Not in base scope
| Training custom models | Not in base scope |
|---|---|
| Unmetered token spend | Not in base scope |
| R&D without definition of done | Not in base scope |
Training custom models: Inference + orchestration only
Unmetered token spend: Runtime is your AWS/Anthropic bill
R&D without definition of done: Manual review path instead
A representative ScopeSpec ticket—your quote is built from your answers in the scope chat.
Timeline
Day 0
AI job definition
Input, output schema, failure modes.
Days 2–6
Workflow + UI
User path around the model call.
Days 7–11
Guardrails + logging
Rate limits, PII rules, fallbacks.
Days 12–15
Deploy + cost sheet
Runtime estimate for you to own.
FAQ
Questions for this build type
How do you price AI complexity?
Number of workflows, structured outputs, and integrations map to Business App, MVP Sprint, or AI add-on bands—all from offers.ts.
Which models do you use?
Provider is scoped per project—typically Anthropic for extraction and chat. You own runtime cost.
Is this AI-native delivery?
Yes for our pipeline. Your product AI is a scoped feature slice, not unlimited generation.
Ready for a fixed quote?
One conversation at /start turns your brief into a locked scope and published price.