Agentic Index
Numa vs Toma (2026)
The dealership voice shortlist, and the gap between them is installed base.
Numa has the largest footprint in the category at more than a thousand dealerships with Stellantis, GM and BMW approval, running a Voice AI Operator for complex multi turn and Spanish calls, a Smart Inbox unifying voice and text, LiveCSI quality monitoring and full context human handoffs, documenting 5 of 14. Toma covers inbound answering, live service calendar booking, parts and sales, recall outreach and SMS with a personalized voice per store, a16z and Y Combinator backed at more than a hundred dealerships, documenting 3. OEM approval is the practical difference for most groups.
Choose Numa if
- OEM approval from Stellantis, GM or BMW is required by your group or your manufacturer.
- Complex multi turn and Spanish calls are where your current system fails.
- Quality monitoring and full context human handoff are part of how you manage the floor.
Choose Toma if
- A distinct voice per store matters for how your brand sounds to customers.
- Recall outreach and parts handling are the specific workflows you want automated.
- You are a smaller group and want a younger vendor working closely with you.
| At a glance | Numa | Toma |
|---|---|---|
| Category | Voice agent | Voice agent |
| Entry price | Contact sales | Contact sales |
| Free / trial | Not published | Not published |
| Pricing confidence | contact only | contact only |
| Feature | N Numa |
T Toma |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
Full / Explicit | Full / Explicit |
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
Partial | Partial |
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
Full / Explicit | Full / Explicit |
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
No / Not documented | No / Not documented |
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
Partial | No / Not documented |
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
Full / Explicit | Partial |
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
No / Not documented | No / Not documented |
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
Full / Explicit | No / Not documented |
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
No / Not documented | No / Not documented |
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
No / Not documented | No / Not documented |
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
No / Not documented | No / Not documented |
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
No / Not documented | No / Not documented |
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
No / Not documented | No / Not documented |
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
No / Not documented | No / Not documented |
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | N Numa |
T Toma |
|---|---|---|
|
Entry price Lowest public entry point |
Contact sales | Contact sales |
|
Pricing confidence How public the numbers are |
Contact only | Contact only |
|
Billing Primary billing axis |
not captured | not captured |
|
Variable cost Workload / overage exposure |
Medium variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
No free tier
|
No free tier
|
|
Buying motion Self-serve vs sales call |
Sales call | Sales call |