Agentic Index
Bretton AI vs Sardine (2026)
Both vendors last verified
Bretton AI adds investigation agents on top of the compliance systems a bank already runs, while Sardine is the fraud and AML platform itself, with agents working the alerts it generates. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Both draft cases and recommend dispositions for analysts to approve, and both count Gusto as a customer. Bretton, formerly Greenlite, overlays tools such as NICE Actimize, Oracle and ServiceNow. It drafts each AML, KYC or sanctions case from the institution's records and more than 180 data sources, and its Workflows chain agents into one investigation. Payward, the parent of Kraken, reports 52,000 hours saved with Bretton. Bretton deploys on its shared platform, on dedicated infrastructure or in the bank's own cloud. Sardine detects fraud with device intelligence, behavior biometrics, a connections graph and a rules engine, then runs agents for screening, due diligence and SAR drafting. It says it serves more than 450 enterprises, including FIS and Nubank, and it keeps LLM processing in the customer's region in Australia, Canada or the EU. Both hold SOC 2 Type II and offer roles. Bretton sells its platform by demo and its Managed Services per finished case, while Sardine bills a monthly platform fee plus usage. Choose Bretton to keep your stack and add investigators. Choose Sardine to run detection and investigation on one platform.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Bretton AI and Sardine 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 Bretton AI if
- You keep NICE Actimize, Oracle or ServiceNow and want agents that work the cases those systems raise.
- Your bank needs the agents running in its own cloud account, on its own keys and identity provider.
- You want each investigation drafted in full, with evidence and narrative, for the compliance team to approve.
- Investigators on call would help, and paying per finished case through Managed Services suits you.
- Independent validation matters, and Kaufman Rossin has validated the KYC, AML and sanctions agents.
Choose Sardine if
- You want fraud detection, AML monitoring and screening on one platform rather than layered on other tools.
- Device intelligence and behavior biometrics from one SDK should feed your fraud decisions.
- Risk analysts should build and backtest rules over more than 12,000 features without engineering help.
- You want agents for anomaly detection and dispute filing as well as screening and SAR drafting.
- Developers will integrate through a documented API and SDKs, with sandbox access on request.
| Feature | B Bretton AI |
S Sardine |
|---|---|---|
| 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. |
||
|
Bretton AIIntegrations & Tool Calling Bretton works as an overlay on the case management, core banking and screening systems the institution already runs, shown on its site as NICE Actimize, Oracle, ServiceNow, nCino, FICO and ICE, and Workbench connects to the customer's tools and can take action on a case. Native connectors added in 2026 cover Persona, Unit21, Sumsub, Google Drive and Databricks Delta Share, and data partnerships bring Equifax and LexisNexis Risk Solutions data into investigations. Sourcebretton.com/platformread 2026-11-03 |
||
|
SardineIntegrations & Tool Calling Sardine names integrations with FIS, Fiserv, Akamai, Cloudflare, Snowflake, Google Cloud, Moody's, Equifax, Experian, Visa, Modern Treasury and Episode Six, and agents research businesses across registration records, filings, licenses and online sources. These bring data and signals into Sardine, which returns decisions and routes cases through its own case management. A Dispute Filing Agent is listed, but no page describes how agents act in outside systems or how customers add their own tools, and the integration guides sit behind the documentation login. Sourcesardine.ai/custom-risk-agentsread 2026-11-03 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
Bretton AIWorkflow Orchestration Agents run the whole investigation, not just the alert. They gather evidence, apply the customer's policy and draft the full case, across enhanced due diligence, scam reviews, SBA loan review, merchant and third party risk, HMDA validation and underwriting. Since October 2026 Workflows link agents into one investigation of several steps, where the outcome of each step decides which agent runs next and that agent picks up the earlier documents, findings and analyst notes, and an agent harness holds a long investigation together from intake to disposition. Sourcebretton.com/changelogread 2026-11-03 |
||
|
SardineWorkflow Orchestration Agents are composed for each workflow. Alert reviews run the Doc KYC, PEP Screening, OSINT Search and Sanctions Screening agents together, business verification runs Business Due Diligence, OSINT, Graph Analyst and Doc KYC, and the Data Analyst and Rule Assistant agents pair on rule creation. Rules, workflows and case management route cases and follow ups, and Sardine Flow, launched in September 2026, automates the work between a team's data providers, rules, scripts and reviews. Sourcesardine.ai/agentic-ai-for-amlread 2026-11-03 |
||
|
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. |
||
|
Bretton AITriggers & Channel Coverage Work arrives from the institution's own alert systems and on a schedule. It reaches the agents from the existing screening and monitoring systems that the platform overlays, and agents work 24/7 on customers flagged by AML systems. Merchant and third party risk reviews run at onboarding and on a regular cadence. Bretton does not say whether customers can set further schedules or inbound channels. SourceBretton AI, bretton.com/platform and bretton.com/blogread 2026-09-06 |
||
|
SardineTriggers & Channel Coverage Events inside the platform hand work to the agents. Transaction monitoring, sanctions, PEP and KYC alerts generated by the rules engine and screening are handed to the agents for triage, onboarding applications submitted through the customer's integration are reviewed in real time, and rules fire on transactions across onboarding, login and payment flows. Customer testimonials describe alerts handed off automatically in real time. Starts are event driven, from the platform's own detection and the web application. The public pages show no schedule or webhook surface a customer can configure. SourceSardine, sardine.ai/agentic-ai-for-aml and sardine.airead 2026-09-06 |
||
| 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. |
||
|
Bretton AIKnowledge Grounding & RAG The customer's own policies and standards are held as a persistent structure applied to every case. The platform runs on the customer's data and policies, so every case is decided the organization's way, the same way every time. Builder captures the analysts' judgment and workflow standard and runs it at scale. Agents combine records the customer provides with government, registry and reference data. How the customer's records are indexed is not described. The 200 plus external data sources add reach beyond the customer's own records and policies. SourceBretton AI, bretton.com/platformread 2026-09-06 |
||
|
SardineKnowledge Grounding & RAG The platform maintains a connections graph mapping relationships between users, devices, IP addresses, phones, emails and transactions that the Graph Analyst Agent queries to surface mule rings and relationships. It also keeps a case store holding customer history and prior findings the agents draw on, and consortium fraud intelligence across billions of devices. These persist, scale past a context window and stay queryable. The OSINT research an agent does for each case is context assembled per run, not a store Sardine keeps. SourceSardine, sardine.ai and sardine.ai/agentic-ai-for-amlread 2026-09-06 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
Bretton AIMemory & State Persistence Every case makes the next one sharper, Bretton says, and performance compounds the longer the agents run, under a module it calls Compounding intelligence. Production failures become permanent regression tests. That learning goes into the agents and Bretton's test library, and customers cannot scope or inspect it. There is no memory layer with a set scope and lifetime, and Workbench has no session state for conversations. SourceBretton AI, bretton.com/platformread 2026-09-06 |
||
|
SardineMemory & State Persistence Case management centralizes alerts, transactions, customer history, investigation findings and decisions, and agents draw on that history when summarizing a case. That is the application's data model and audit record, not a memory layer. There is no memory with a stated scope and lifetime, and no conversational session state. SourceSardine, sardine.ai/agentic-ai-for-aml and sardine.airead 2026-09-06 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
Bretton AIHuman Oversight & Guardrails A person approves every case. Agents gather evidence, apply the customer's policy and draft the full case for the customer's team to approve, and exceptions are flagged before they reach a reviewer. Risk based decisions stay with the institution's own staff. All of this happens inside Bretton's Workbench and app, with escalation to the customer's people. SourceBretton AI, bretton.com/platformread 2026-09-06 |
||
|
SardineHuman Oversight & Guardrails Every alert triage arrives as a disposition recommendation with rationale for human review. Business verification packages findings so analysts approve low risk cases and review higher risk ones, and the SAR agent drafts only if the analyst decides to file. Agents work within defined workflows under structured human oversight, not in place of analyst judgment. The review and approve step sits in Sardine's own case management. SourceSardine, sardine.ai/agentic-ai-for-amlread 2026-09-06 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
Bretton AISecurity, Identity & Governance Bretton holds a SOC 2 Type II report covering January 2025 to January 2026, available on request through its trust center, and states GDPR compliance and zero data retention with its model providers. Role based access control limits users to the data and functions their roles need, customers have managed their own custom access roles since October 2026, and in dedicated or own cloud deployments Bretton runs on the institution's own identity provider. Single sign on, SAML and SCIM are not named on the public pages. Sourcetrust.bretton.comread 2026-11-03 |
||
|
SardineSecurity, Identity & Governance Sardine shows SOC 2 Type II and ISO 27001 badges and claims zero data retention, and its security page points to a Vanta trust center holding SOC 2 and penetration test reports, with no report type, date or auditor published outside it. The dashboard offers roles with different levels of access, set on its Admin page, and permissions govern data access, so each analytics data source needs the analytics permission plus the matching case, activity report or risk rating permission. Single sign on, SAML and SCIM are not named on the public pages. Sourcesardine.ai/custom-risk-agentsread 2026-11-03 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
Bretton AIObservability & Auditability Every action is logged, cited and explainable, built to federal banking guidelines, and every output is traced and cited, so the record is ready for audit. The Bretton Evaluator reviews sampled production traces against a rubric, so a run trace exists for every agent. Bretton does not say whether the log can be exported outside the platform. SourceBretton AI, bretton.com/platform and bretton.com/blog/moving-an-agent-to-productionread 2026-09-06 |
||
|
SardineObservability & Auditability There are defensible audit trails at every step, audit ready documentation kept by the agents, a rationale attached to each disposition recommendation, and case summaries that link transactions, alerts, customer history, findings and supporting evidence in one view for governance and regulator review. The public pages show no exportable log of user actions. SourceSardine, sardine.ai/agentic-ai-for-amlread 2026-09-06 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
Bretton AIDeployment & Data Residency Bretton offers three deployment options, its shared platform, dedicated infrastructure, or the institution's own cloud account. In the customer controlled options it runs on the institution's own compute, storage, encryption keys, identity provider and monitoring, customer data stays in that environment, and models are called only in the approved region. No named region list is published for the shared platform. Sourcebretton.com/blog/bretton-enterprise-deploying-agents-inside-the-biggest-most-secure-global-banksread 2026-11-03 |
||
|
SardineDeployment & Data Residency Since September 2026, LLM requests from Sardine's AI features stay in the same region as the customer's production environment, with Australia, Canada and the European Union named. Sardine does not publish where customer data is stored or how a production region is chosen, its privacy policy names no storage region, and a 2021 engineering post says it hosts on Google Cloud. Sourcesardine.ai/blog/product-updates-september-2026read 2026-11-03 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
Bretton AIPrebuilt Agents, Templates & Packs A Templates module offers prebuilt skills and agents for EDD, monitoring, sanctions, SAR drafting, KYB, HMDA and CRA, live in minutes. Ready agents cover enhanced due diligence, scam and authorized fraud review, SBA loan review, merchant risk review, third party risk, product line assessment, HMDA and underwriting. Each does a whole job on its own, so SAR drafting still works without sanctions, and the customer picks the agents it needs. SourceBretton AI, bretton.com/platformread 2026-09-06 |
||
|
SardinePrebuilt Agents, Templates & Packs Prebuilt agents are offered for customers to adopt in Agent Hub, among them OSINT Search, Data Analyst, Rule Assistant, Transaction Monitoring, Business Due Diligence, Doc KYC, PEP Screening, Graph Analyst, Sanctions Screening, SAR Generation, Anomaly Detection, Dispute Filing and Compliance Screening, sold as Agentic Fraud Ops and Agentic AML Ops over modular products across onboarding, fraud prevention and AML compliance. Each agent works on its own, so without the SAR Generation Agent the screening and research agents are still whole. Sourcesardine.airead 2026-11-03 |
||
| 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. |
||
|
Bretton AIModel Flexibility & Routing In dedicated and own cloud deployments the agent can only reach providers the institution has approved, each deployment keeps a single list of approved models, and inference can run through an approved Amazon Bedrock endpoint. On the shared platform Bretton chooses the models, its providers are not named, and no model picker is offered. Sourcebretton.com/blog/bretton-enterprise-deploying-agents-inside-the-biggest-most-secure-global-banksread 2026-11-03 |
||
|
SardineModel Flexibility & Routing Sardine does not name the language model behind the agents, and there is no customer or admin model selection or routing across providers on Sardine's side. The platform's own fraud and credit models, which customers can build, test and deploy and, in a testimonial, train, are machine learning tooling, not a choice of the model the agents run on. SourceSardine, sardine.airead 2026-09-06 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
Bretton AIAPIs, SDKs & MCP Extensibility Documentation sits at docs.bretton.com behind an access code, and the changelog mentions API access for payment screening, but no readable page describes what an API for the Bretton platform covers. Business Due Diligence runs inside Alloy as a partner integration, and no public SDK, MCP server or agent card is published. Sourcebretton.com/blogread 2026-11-03 |
||
|
SardineAPIs, SDKs & MCP Extensibility Sardine is sold as an API and SDK platform with a developer portal at docs.sardine.ai and a public status page. The documentation covers an API Reference for detecting fraud and risk and integration guides for onboarding users, and the public tier covers getting started, sandbox access and the integration timeline. The full API reference and integration guides sit behind a dashboard login, which is the access path customers use. SourceSardine, docs.sardine.ai and docs.sardine.ai/llms.txtread 2026-09-06 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
Bretton AITesting, Debugging & Optimization Every agent is tested by Bretton before and after it ships, under a four layer validation framework. Scenario and regression testing runs against a maintained library of failure cases before material changes ship. Ground truth benchmarking against human validated cases reports precision, recall, F1 and accuracy, with unsupported outputs tracked separately. In production, the Bretton Evaluator scores sampled traces against a rubric, and people adjudicate the judge. Material changes or degradation trigger revalidation. Bretton sells this as the Trust Infrastructure module, with continuous evaluations and independent model validation on every agent. Production failures become permanent tests. Bretton's Applied AI team runs the harness, and recurring performance reports for customers are still being built, so customers neither run it nor receive its output today. SourceBretton AI, bretton.com/blog/moving-an-agent-to-production and bretton.com/platformread 2026-09-06 |
||
|
SardineTesting, Debugging & Optimization A customer can create, test and roll out transaction monitoring rules on the platform without engineering support, and the Rule Assistant Agent tunes rule thresholds to improve alert quality, fire rates and monitoring coverage. That evaluates a change to the customer's detection logic against measured outcomes before and after release, on Sardine's own surface. SourceSardine, sardine.ai/agentic-ai-for-amlread 2026-09-06 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
Bretton AIBrowser & Computer Use The Research Agent reads the open web at run time. It confirms identity and geographic attributes for each entity by combining customer records, official government and registry data, open web sources and reference databases as part of the investigation, not to build an index. How the agent reaches the open web is not described. No agent controls a browser, desktop or computer. SourceBretton AI, bretton.com/blog/moving-an-agent-to-productionread 2026-09-06 |
||
|
SardineBrowser & Computer Use The OSINT Search Agent searches online sources, social media and public databases at run time for each alert or case, so the agent does its own web research instead of drawing on a prebuilt index. Sardine does not say what mechanism it uses. The device intelligence and behavior biometrics SDK runs inside the customer's own application, which is the product running in a browser, not an agent operating one, and bot detection detects agentic automation instead of performing it. There is no browser, desktop or computer control that the agent drives. SourceSardine, sardine.ai/agentic-ai-for-aml and sardine.airead 2026-09-06 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | B Bretton AI |
S Sardine |
|---|---|---|
|
Entry price Lowest public entry point |
Contact for pricing | Contact for pricing |
|
Pricing confidence How public the numbers are |
Contact only | Contact only |
|
Billing Primary billing axis |
— | Monthly platform fees plus usage charges by product, counted per API call or monthly active user, per transaction, per verification attempt or per screened identity. |
|
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 |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Bretton AI
-
· Workflow orchestration
Bretton agents can now be linked into one multi step investigation, where the outcome of each step decides which agent runs next.
Source -
· Security / enterprise
Authorized administrators can now create custom access roles directly in Bretton, rather than choosing from a fixed set of existing roles.
Source
Sardine
-
· Workflow orchestration
Sardine launched Agent Hub, a central place to manage, evaluate and work with all of its AI agents, including Doc KYC and OSINT Search, with context available to investigators during a case.
Source -
· Observability / auditability
Screening widgets now support batch entity resolutions across sanctions, PEP, and adverse media lists.
Source -
· Workflow orchestration
Business Details headers became configurable with up to 12 fields and org-wide/default layouts.
Source
Neither vendor publishes a price or names the language models behind its agents, and neither documents single sign on publicly. Bretton keeps its API documentation behind an access code and names no region for its shared platform. Sardine does not say where customer data is stored or how a region is chosen, and it shows its SOC 2 report only as a badge, with no date. Ask Bretton for a platform quote and its API reference. Ask Sardine for its data hosting regions, its SOC 2 report and its platform fee.
More comparisons with Bretton AI or Sardine
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.