Bretton AI
Also known as: Greenlite AI, Greenlite
Agentic platform for the financial back office, with AI agents and investigators that complete AML, KYC, KYB and sanctions reviews for regulated banks and fintechs, drafting each case for approval (formerly Greenlite AI).
Bretton AI, formerly Greenlite AI, combines AI agents with experienced investigators to complete AML investigations, KYC reviews and sanctions alert reviews for banks and fintechs. Customers include Paxos, Mercury, Gusto, Upgrade, Grasshopper, Coastal Community Bank, MVB Bank, Academy Bank, Blockchain.com, Freetrade and Zepz. Payward, the parent of Kraken, reports more than 52,000 hours and $3.8 million saved in its first year, and First Internet Bank cut review time by 87%. Bretton raised a $75 million Series B in February 2026, led by Sapphire Ventures with Greylock, Y Combinator, Thomson Reuters Ventures, Canvas and TIAA Ventures.
Its agents run whole investigations, not single alerts. They gather evidence from the institution's own records and more than 180 data sources, apply the institution's policies so every case is decided the same way, and draft the full case for the compliance team to approve.
More than 30 skill templates cover enhanced due diligence, monitoring, sanctions, SAR drafting, KYB, HMDA and CRA, and ready agents handle scam reviews, SBA loan review, merchant and third party risk and underwriting.
Builder captures a team's own workflow as a custom agent, Workbench gives analysts an AI companion that can take action on a case, and since October 2026 Workflows chain agents into one investigation, each step deciding which agent runs next.
The platform overlays systems the institution already runs, such as NICE Actimize, Oracle, ServiceNow, nCino, FICO and ICE, with native connectors for Persona, Unit21 and Google Drive and data partnerships with Equifax and LexisNexis Risk Solutions, and it is available inside Alloy for business due diligence. Bretton tests each agent against regression cases and human validated benchmarks before changes ship and scores production runs with its Evaluator, and Kaufman Rossin completed an independent validation of its KYC, AML and sanctions agents in October 2026. Every action is logged, cited and explainable.
Bretton holds a SOC 2 Type II report and offers role based access with custom roles. It deploys on its shared platform, on dedicated infrastructure or in the bank's own cloud account, and it keeps zero data retention agreements with its model providers. Bretton Managed Services runs monitoring and KYC work for a bank and is priced per finished case, and the platform is sold by demo with no published prices.
Vendor details
Canonical URL
https://www.bretton.com
Category
Enterprise operations agent
Subcategory
Finance — AML/KYC/sanctions compliance agents
Funding status
Venture backed. Bretton raised a $75 million Series B in February 2026, led by Sapphire Ventures with Greylock, Y Combinator, Thomson Reuters Ventures, Canvas and TIAA Ventures, after a $15 million Series A in May 2025 as Greenlite AI.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Integrations
Bretton overlays case management, core banking and screening systems such as NICE Actimize, Oracle, ServiceNow, nCino, FICO and ICE. Native connectors cover Persona, Unit21, Sumsub, Google Drive and Databricks Delta Share, data partnerships bring in Equifax and LexisNexis Risk Solutions, and business due diligence runs inside Alloy.
In practice
Your analysts spend their day writing up the same alert investigations by hand. Bretton's agents draw on the institution's records and more than 180 data sources to draft each case ready for audit, and the genuine risk decisions go to a person.
An examiner wants to see how each AML, KYC, KYB or sanctions decision was reached. Bretton's agents log, cite and explain every action, so every case leaves a record an examiner can follow.
A flood of sanctions and adverse media alerts buries the few that matter. Bretton works the screening across its data sources and surfaces the decisions that need human judgment, with the narrative already written.
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool Calling | Full |
|---|---|
|
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 |
|
| Workflow Orchestration | Full |
|
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 |
|
| Knowledge Grounding & RAG | Full |
|
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 |
|
| Human Oversight & Guardrails | Full |
|
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 |
|
| Security, Identity & Governance | Full |
|
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 |
|
| Observability & Auditability | Full |
|
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 |
|
| Memory & State Persistence | Not documented |
|
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 |
|
| Deployment & Data Residency | Full |
|
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 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
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 |
|
| Triggers & Channel Coverage | Full |
|
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 |
|
| Model Flexibility & Routing | Partial |
|
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 |
|
| APIs, SDKs & MCP Extensibility | Partial |
|
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 |
|
| Testing, Debugging & Optimization | Full |
|
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 |
|
| Browser & Computer Use | Partial |
|
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 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Bretton agents can now be linked into one multi step investigation, where the outcome of each step decides which agent runs next. The next agent picks up the earlier step's documents, findings, narrative, outcome and analyst notes. Analysts start and follow these runs from a new Workflows page.
Bears on: Workflow orchestration
View sourceAuthorized administrators can now create custom access roles directly in Bretton, rather than choosing from a fixed set of existing roles. Before this release, teams with access needs outside that set had to ask Bretton for a new role.
Bears on: Security / enterprise
View sourcePricing
Contact for pricing
What is public
There is no pricing page. The navigation carries Contact Us and an ROI calculator, and every page ends in Contact Us. No tiers, rate card, trial or free tier are published for the platform. Bretton Managed Services, a separate engagement, is priced per finished case on consumption, which is that engagement's model rather than a platform price.
Billing mechanics
Not disclosed for the platform. Managed Services, a separate engagement, is priced per finished case.
Additional watchouts
Pricing is quote only. The company rebranded from Greenlite AI in 2026, so older listings carry the old name.
Sales call required
Yes, required for paid access
Free / trial
None published
Lowest paid plan
Not published
Support SLA / resale
Enterprise security and governance, sold as audit ready Trust Infrastructure that integrates with existing compliance and screening systems. Bretton sells to institutions regulated by the OCC, FDIC and Federal Reserve.
Missing data
No pricing is published, with no tiers, rate card, trial or free tier for the platform.
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Abacum — FP&A platform for growing companies whose AI Modeler builds, edits…
- Adopt AI — AI native accounting and bookkeeping firm whose agents run…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
Alternatives to Bretton AI
The closest documented capability profiles to Bretton AI among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Adopt AI12.0 / 14Fuller documented coverage on APIs, SDKs & MCP Extensibility
- Leena AI12.0 / 14Adds documented Memory & State Persistence
- Auditoria10.5 / 14A lighter documented profile than Bretton AI
- Atomicwork12.0 / 14Adds documented Memory & State Persistence
- Beam AI12.0 / 14Fuller documented coverage on Model Flexibility & Routing and APIs, SDKs & MCP Extensibility
- dSilo12.0 / 14Adds documented Memory & State Persistence
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded