Agentic Index
Nominal vs Rillet (2026)
Both vendors last verified
Nominal and Rillet both attack month end close with AI, from different layers. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Nominal deploys agentic accounting on top of your existing stack, with agents that match, reconcile, and post journal entries, while Rillet is an AI native ERP that replaces the ledger itself for scaling companies, automating revenue recognition, SaaS metrics, and close with human sign off. Both are contact sales. Choose Nominal to add agents to your current ERP. Choose Rillet to replace the ERP outright.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Nominal and Rillet are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,140 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Nominal if
- You want to keep your current ERP and layer autonomous close agents on top.
- Matching, reconciliation, and journal posting are the specific jobs to automate.
- A lower disruption path to an automated close appeals to you.
Choose Rillet if
- You are a scaling company ready to replace the ledger with an AI native ERP.
- Revenue recognition, SaaS metrics, and investor reporting native to the ERP matter.
- Consolidating close automation into the system of record is the end state you want.
| Feature | N Nominal |
R Rillet |
|---|---|---|
| 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. |
||
|
NominalIntegrations & Tool Calling The platform is ERP agnostic by design and plugs into any ERP, ledger or data source. Workday, Microsoft Dynamics 365, Oracle, Sage Intacct and SAP each have a named solution page, and NetSuite, QuickBooks, national and regional banks and procurement systems connect as well. A bi directional data ledger runs across entities, systems and currencies. Agents post corrections as they occur and write adjustments back to the general ledger, and resolution agents solve discrepancies at source. SourceNominal, nominal.so/our-platform and nominal.soread 2026-09-07 |
||
|
RilletIntegrations & Tool Calling The systems the agents act across are named. Native Integrations is a product line, presented as the single source of financial data. Rillet is an agent of Plaid Financial Ltd for regulated bank account information. Salesforce, Stripe, Ramp, Brex, Rippling and Snowflake make up the connected stack, with continuous bank and processor syncing and native Stripe payout matching, workflow agents handle the data pulls, and the MCP surface reaches Salesforce and Snowflake. SourceRillet, rillet.com/product/aura-ai, rillet.com/product/native-integrations named in navigation, and info.rillet.comread 2026-09-07 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
NominalWorkflow Orchestration A network of autonomous agents runs accounting operations across systems, entities and time. The agents carry out reconciliation, transaction matching, variance analysis, consolidation and close continuously, instead of waiting for instructions or for period end. By Nominal's account they orchestrate tasks as well as execute them, understanding dependencies, monitoring progress and adapting as new data or exceptions emerge. Nominal calls the model Agentic Performance Management, a coordinated system of specialized agents with a transaction level data foundation beneath them. SourceNominal, nominal.so/our-platform and nominal.so/blog/agentic-workflowread 2026-09-07 |
||
|
RilletWorkflow Orchestration Customers compose multi step workflows that agents run. Workflow agents complete sophisticated accounting tasks end to end, reliably and repeatably, with the customer writing the rules in plain English and Aura handling the schedule, the data pulls and the handoffs. Approval workflows route journal entries, sync events and agent proposals with materiality tiers, and close management runs task checklists across the period. Because the rules are written in plain English, customers compose the flow themselves instead of running a fixed pipeline. SourceRillet, rillet.com/product/aura-ai and rillet.com/product/security-and-permissionsread 2026-09-07 |
||
|
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. |
||
|
NominalTriggers & Channel Coverage Trigger agents are a named product. They monitor financial data in real time and activate next steps automatically across systems and workflows when thresholds are crossed, data shifts or anomalies appear. Transaction Patrol agents monitor account activity continuously to detect anomalies and risks early. Agents also run between period ends as transactions flow in from connected ERP and bank feeds, and they review close status across entities continuously and flag delays before they compound. SourceNominal, nominal.so/our-platform and nominal.so/blog/agentic-ai-accountingread 2026-09-07 |
||
|
RilletTriggers & Channel Coverage Three kinds of trigger start the agents. Aura runs continuously, always on, watching for anomalies, flagging exceptions and proposing accruals as they happen. Workflow agents run on schedules Aura handles. Events drive the rest, since continuous close is a real time architecture in which every transaction is fully processed the moment it arrives, with continuous bank and processor syncing, so transaction arrival drives the agent chain instead of a batch cycle. SourceRillet, rillet.com/product/aura-ai and info.rillet.comread 2026-09-07 |
||
| 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. |
||
|
NominalKnowledge Grounding & RAG The Shadow Ledger is a unified, bi directional data ledger across entities, systems and currencies. Nominal names a transaction level data foundation as one of the three things autonomy requires. Agents reason against it and return sourced answers to close questions. What persists is the transaction record itself, the operational data layer the product maintains. Nominal names no index, graph or embeddings layer over a knowledge corpus, and describes no way to load the customer's policies or documents into a store the agents can query. SourceNominal, nominal.so and nominal.so/our-platformread 2026-09-07 |
||
|
RilletKnowledge Grounding & RAG Aura answers from the customer's live general ledger and company configuration, which feed an intelligence layer. It answers natural language questions about vendors, accounts, balances or any cut of the data with numbers sourced from the GL, working against real ledger data, not a stale copy. The ledger is a persistent, structured, continuously updated store of the customer's financial record that outlives any run and stays queryable. SourceRillet, rillet.com/product/aura-airead 2026-09-07 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
NominalMemory & State Persistence The Shadow Ledger and the transaction level data foundation hold the accounting record the product maintains. The agents learn from historical data and user interactions across cycles, and that learning is absorbed into the agents instead of being stored as memory. Nominal describes no memory layer the agents keep, and does not say where memory lives, how long it lasts or how it is deleted for a single customer. SourceNominal, nominal.so/our-platformread 2026-09-07 |
||
|
RilletMemory & State Persistence Rillet says Aura remembers how the team works, so it answers, acts and reconciles the way the team would. That describes adaptation, not a memory feature. There is no named memory construct, stated scope or lifetime, recall surface for each user or workflow, or deletion path. The live general ledger and company configuration feeding the intelligence layer are the application's data and the customer's setup, not memory, and learned working patterns absorbed into behavior are not a memory a customer can inspect. SourceRillet, rillet.com/product/aura-airead 2026-09-07 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
NominalHuman Oversight & Guardrails When an agent proposes an entry, it does not post automatically. The entry appears in a queue with full documentation showing the matching logic, source transactions and recommended treatment, and a controller reviews and approves it before it reaches the general ledger. Finance teams configure approval thresholds, define materiality levels and set the rules for when human review is required, and the system handles everything below those thresholds automatically. Nominal's principle is that control stays human, with agents doing the work and people guiding, reviewing and deciding. SourceNominal, nominal.so/blog/ai-agents-in-finance-accounting and nominal.so/our-platformread 2026-09-07 |
||
|
RilletHuman Oversight & Guardrails Oversight is built into the product. Nothing posts automatically without approval, and every agent action is proposed to a human and posts only once approved. Approval workflows are tiered to materiality with configurable dollar thresholds, such as fifty thousand dollars to the Controller and five hundred thousand to the CFO. AI agent proposals are routed through the same workflows as journal entries and sync events, and under segregation of duties agents prepare and humans authorize, with role-based access. Every step can be approved and edited. The customer configures that gate, and it sits on the action that matters, posting to the general ledger. SourceRillet, rillet.com/product/security-and-permissions and rillet.com/product/aura-airead 2026-09-07 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
NominalSecurity, Identity & Governance The platform is SOC 1 compliant, the standard required for public accounting, and meets SOC 2 security standards, with an AICPA SOC 2 Type II badge. Nominal calls it a SOC 1 certified platform. Intelligent authentications and user management are mentioned, but no mechanism is named, and Nominal names no SSO, SAML, SCIM, role model or permission scheme. Read only mode protects the integrity of the customer's ledger data and does not govern who inside the organization can do what. SourceNominal, nominal.so/company/securityread 2026-09-07 |
||
|
RilletSecurity, Identity & Governance Rillet holds SOC 1 and SOC 2 Type II, with annual third-party audits and reports available for review. It encrypts data with AES-256 at rest and TLS 1.2+ in transit, runs continuous monitoring with penetration tests and commits to GDPR. Controls include enterprise SSO via Google, Microsoft Entra and Rippling, three-tier role-based access (Owner, Admin, Accountant plus view-only) with no seat limits and immediate permission changes under full audit history, segregation of duties enforced for AI agents as for people, period locking and subledger locks for each entity. Audit logging is part of the same controls. SourceRillet, rillet.com/product/security-and-permissionsread 2026-09-07 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
NominalObservability & Auditability Agents log every step they take, documenting what was analyzed, what logic was applied and what conclusions were reached. Every proposed entry carries the matching logic, source transactions and recommended treatment through to the approval record. A detailed audit trail and a read only mode are standing platform properties. Every action includes documentation, traceability and human approval workflows that Nominal says support internal controls and external audit. The record shows why an agent acted, not just that it did, and it is Nominal's own record, not logs from the customer's ERP. SourceNominal, nominal.so/company/security and nominal.so/blog/ai-agents-in-finance-accountingread 2026-09-07 |
||
|
RilletObservability & Auditability One hundred percent of AI actions are logged, with every query, proposal, approval and rejection recorded with timestamp and reasoning, every read access logged with full attribution, every permission change under full audit history, and every period lock and unlock logged with reason and timestamp. Together these reconstruct what an agent did, why, and who authorized it, alongside an audit trail by default and the accrual agents' plain-language rationale. SourceRillet, rillet.com/product/security-and-permissions and rillet.com/product/aura-airead 2026-09-07 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
NominalDeployment & Data Residency No hosting region is published, and Nominal names no region choice, customer cloud or on premises option. On hosting it says only that from hosting to user management, private data stays private. The privacy policy covers the website only, and it says Nominal does not access or interact with customer systems through it. No data processing addendum or subprocessor list is published, and there is no trust center, gated or public. SourceNominal, nominal.so/company/security and nominal.so/legal/privacy-policyread 2026-09-07 |
||
|
RilletDeployment & Data Residency The platform is hosted on AWS and delivered as a cloud application with no local install. That is one hosting arrangement with no region list, no customer environment option and no selection surface. The GDPR commitment is a privacy posture, not a residency option. SourceRillet, rillet.com/product/security-and-permissions and info.rillet.comread 2026-09-07 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
NominalPrebuilt Agents, Templates & Packs Five agents ship as named products, each with its own page and its own job. Flux Analysis agents explain variance, Bank Reconciliation agents match bank activity continuously, and Transaction Matching agents match across ledgers, entities and systems including intercompany. Trigger agents activate next steps when thresholds are crossed or anomalies appear, and Transaction Patrol agents monitor activity. SourceNominal, nominal.so/our-platformread 2026-09-07 |
||
|
RilletPrebuilt Agents, Templates & Packs Rillet ships named specialized agents a customer puts to work on each workflow. A suite of specialized accounting agents covers flux, accruals, reconciliation and revenue, each scoped to one accounting workflow, alongside the Aura assistant and plain-English workflow agents. Each agent does its own job, so an accruals agent stays whole without the flux agent, and the agents ship as adoptable units inside the product, not as a pricing structure. SourceRillet, rillet.com/product/aura-ai and rillet.com/product/security-and-permissionsread 2026-09-07 |
||
| 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. |
||
|
NominalModel Flexibility & Routing No model provider is named, and Nominal names no model choice or routing for customers or admins. It describes its agents as deterministic AI agents built for accuracy, auditability and control. SourceNominal, nominal.so/our-platform and nominal.so/legal/privacy-policyread 2026-09-07 |
||
|
RilletModel Flexibility & Routing No model provider is named, and customers and admins have no choice of model. Under its model change management commitment Rillet manages its own model stack, with swaps flowing through Rillet's change controls, which is neither disclosed routing across providers nor a customer selection surface. SourceRillet, rillet.com/product/security-and-permissions and rillet.com/product/aura-airead 2026-09-07 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
NominalAPIs, SDKs & MCP Extensibility Every named connection runs outward into the customer's ERPs, banks and procurement systems. There is no published way to call Nominal from outside. No API, SDK or MCP server is published, and the site has no developer section. SourceNominal, nominal.so/our-platformread 2026-09-07 |
||
|
RilletAPIs, SDKs & MCP Extensibility There are two routes for calling the platform from outside. Through MCP, Aura connects to Salesforce, Snowflake, Claude or any BI tool with one secure surface for reads and writes, so an outside agent or tool can drive Rillet in both directions. A public API has documentation at docs.api.rillet.com with a getting-started guide. SourceRillet, rillet.com/product/aura-ai and docs.api.rillet.comread 2026-09-07 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
NominalTesting, Debugging & Optimization The agents learn from historical data and user interactions to improve accuracy over time and get better every cycle, Nominal says. It names no test harness, scored cases, release gate or controlled test loop, whether run by the customer or reported to it, and publishes no test results. Confidence thresholds clear high confidence matches automatically, one output at a time, and the audit trail records what the agents did. SourceNominal, nominal.so/blog/agentic-ai and nominal.so/our-platformread 2026-09-07 |
||
|
RilletTesting, Debugging & Optimization Nothing puts a change to the customer's agents under test. Under its model change management commitment, Rillet's own model swaps go through IT general controls with testing, approval and rollback under SOX 404, but that tests Rillet's release practice, not the customer's agents. Anomaly and error detection runs on the books, the customer's data, not the agent, and there is no harness, scored test set, live agent metric or release gate for the customer. SourceRillet, rillet.com/product/security-and-permissions and rillet.com/product/aura-airead 2026-09-07 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
NominalBrowser & Computer Use Agents work over structured financial data pulled from connected ERPs, ledgers and bank feeds and write adjustments back through those connections. They reach systems through programmatic integrations, not by operating an interface. Nominal names no browser, desktop or remote computer control. SourceNominal, nominal.so/our-platformread 2026-09-07 |
||
|
RilletBrowser & Computer Use The agents work inside the general ledger and through native integrations, syncing banks and processors and pulling data over connected systems. There is no browser, desktop or computer control operated by an agent, and no open research for each case at run time. The anomaly and flux work runs over the customer's own ledger data. SourceRillet, rillet.com/product/aura-airead 2026-09-07 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | N Nominal |
R Rillet |
|---|---|---|
|
Entry price Lowest public entry point |
Contact for pricing | Contact sales |
|
Pricing confidence How public the numbers are |
Contact only | Contact only |
|
Billing Primary billing axis |
not disclosed | flat |
|
Variable cost Workload / overage exposure |
Low 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 |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
More comparisons with Nominal or Rillet
Other matchups in enterprise operations agents
Not the pairing you were after? These compare a different set of enterprise operations agents on the same 14 capabilities.