# Lumtry: refund automation with policy and human approval > Decide refunds by a versioned policy, send the exceptions to your team in Slack or the dashboard, and keep every step on the record. Start free. - Canonical URL: https://lumtry.com/ - Last updated: 2026-09-24 ## Refunds decided by policy. Exceptions decided by you. Lumtry applies your refund policy to every request, asks a person on the close calls, and records every step. ## What do you want to fix first? Start with the problem that costs you the most. The rest runs on the same policy, approvals and audit trail. - **Refund decisions**: Decide every request the same way, and send the close calls to a person. - **Returns and labels**: Get the item back before the money goes out, or decide it does not need to come back. - **Disputes and chargebacks**: Answer chargebacks with the record you already have. - **Retention and abuse**: Keep the customers worth keeping, and catch the patterns worth stopping. ## Policy decides. AI advises. You stay in charge. Every refund takes the same path. AI reads the case first and hands the policy engine signals. Your pinned policy makes the call, and a person signs off whenever the rules say so. If AI is off or fails, the outcome is the same. The policy engine decides. - **Intake**: Store, marketplace and helpdesk webhooks, the returns portal or the public API. - **AI signals**: Classification and sentiment run in parallel, beside abuse-risk, fraud-network and payment-hold checks. - **Policy engine**: Deterministic rules, first match by priority. The policy version is pinned when the case starts. - **Outcome**: One of four paths, never a guess. - **Execution**: Refund through Stripe or PayPal with an idempotency key. - **Audit trail**: Every transition is written to an append-only record with its correlation id. - **Auto-approve**: The rules clear it, so it executes. - **Human approval**: Dashboard, Slack or a voice call. The first answer wins. - **Deny**: A policy denial ends the run. People can deny too. - **Manual action**: Anything unresolved fails closed to a person. - Dashboard - Slack - Voice Every AI call goes through one router. It is not a step in the decision. Routing today Not yet cleared Google and xAI are skipped at route time until their sub-processor review clears. - Per-task model assignments by plan - Automatic failover to the next vendor - Every call logged with model, tokens and cost - Prompt-injection screen that fails closed - **Policy decides, AI advises**: Signals feed your rules; they never overrule them. An unavailable model cannot change a decision. - **Never stuck on one vendor**: Three model vendors route today, with failover between them and a weekly check for retired models. - **Every step on the record**: The pinned policy version, each state change and who signed off, in one audit trail. ## Built so you stay in control. Your refund policy lives on a visual rule builder. Every rule is a block you can read, test and version, and nothing reaches a customer until you publish. ### Approve where your team already works Close calls go to a person. Each approval is checked against the case before anything moves. - **Dashboard**: The source of truth for every case. - **Slack**: Approve or decline from the message. - **Helpdesk**: Gorgias and Zendesk notes on the ticket. - **Voice**: An outbound call for the urgent ones. - **Reverse what already happened**: Each step that moves money or stock has a matching reversal, so a failure never leaves a case half done. - **Keep an append-only record**: Every action writes an audit row with a correlation ID. Nobody can edit or delete it. - **Every edit is a new version**: You work on a draft. Published versions never change, and each case stays pinned to the version it started on. - **A safe default**: When no rule matches, the case gets your default outcome, such as manual review. Nothing slips through unhandled. - **Rules are blocks**: Each rule is conditions plus one outcome. Rules run in priority order, and you drag a block to change it. - **Start from a signal**: Pick what the rule looks at: abuse risk, refund reason, order age, proof of purchase and more. - **Stack the conditions**: Combine amount, currency and the AI classification label with All, Any or Not. - **Choose the outcome**: Auto-approve, send to manual review or offer store credit first, with a default for everything else. ## What it will never do. Some lines are built into Lumtry, not left to settings. - **Never override your policy**: Model output informs a decision. Your published rules make it. - **Never store card data**: Lumtry keeps processor tokens only, never card numbers. - **Never release a hold on model output alone**: A held case waits for a person, whatever a model suggests. - **Never rewrite history**: Audit and webhook records are append-only. ## Pick the plan that fits your volume Start on Free or a 14-day Growth trial today, no card needed. Paid plans open at launch: reserve a price and we tell you when checkout goes live. - Policy decisions and a dashboard to try it on real cases. - Slack approvals and AI rationale for a growing store. - More volume and more channels for a busy support team. - Dispute automation and Abuse Shield included. - Custom terms, SSO and guided onboarding. ## Questions, answered. The questions merchants ask us most. ### Platform #### Does AI decide my refunds? No. Your published policy decides. AI explains gray areas and can recommend, but a case outside the rules goes to a person. ##### Can I try it without connecting a store? Yes. The demo workspace has sample cases you can click through, and the Free plan lets you set up a policy before you connect anything. ##### Which stores and marketplaces does it work with? Shopify, WooCommerce and BigCommerce stores, plus Amazon and eBay marketplace intake. ##### Which languages does the dashboard support? English, French (Canada) and Spanish (US). #### Money and approvals ##### Which payment processors are supported? Stripe and PayPal. Store credit is issued through the store platform. ###### What happens if a refund fails partway? Lumtry runs the compensation for the steps already taken and flags the case, so nothing is left half done. ###### Can I test a new policy before it goes live? Yes. Shadow mode runs a new policy beside the live one and shows where the outcomes differ. ###### Do you store card data? No. Lumtry stores processor tokens only. #### Account and billing ##### What happens when I hit my plan limit? New cases are held, not dropped. They wait until you upgrade or the next period starts. ###### When can I buy a plan? Checkout opens at launch. Leave your email on the pricing page and we will tell you when it does. ###### Do you support single sign-on? Yes. SAML SSO, OIDC and SCIM are available on Scale. ## Put policy on the volume. Keep people on the calls. Start free, or talk to us about your refund flow. - Free plan, no card - 14-day Growth trial, no card - Demo without an account ## Related - [Features](https://lumtry.com/features.md): Versioned refund policy, AI reasoning only where rules leave room, Slack and dashboard approvals, Stripe and PayPal execution and a full audit trail. See it all. - [Pricing](https://lumtry.com/pricing.md): Lumtry plans by case volume and seats, from Free to Enterprise, with add-ons and capped outcome fees. Start free or hear when billing opens. - [About](https://lumtry.com/about.md): Why Lumtry exists: refunds should be decided by a policy you can defend, reasoning you can inspect and approvals your team controls. Read the story. - [Privacy](https://lumtry.com/privacy.md): How Lumtry collects, uses, shares and protects personal information, isolates tenant data, records AI rationale and lists sub-processors. Read the policy. - [Terms](https://lumtry.com/terms.md): The binding terms for using Lumtry: policy plus AI reasoning with a human approval gate, plans and billing, and the limits of liability. Read them in full. - [Trust](https://lumtry.com/trust.md): How Lumtry secures merchant data, keeps AI inside a deterministic refund policy, lists every sub-processor and explains data flow and retention. Review it. - [Solutions](https://lumtry.com/solutions.md): Four ways Lumtry puts policy, approvals and an audit trail around the money you give back: refunds, returns and labels, chargebacks, retention and abuse. - [Demo](https://lumtry.com/demo.md): Run a sample refund through intake, AI signals, policy, approval and audit in your browser. Change a rule, rerun the case and share the link. Try it now. - [Integrations](https://lumtry.com/connectors.md): Connect Lumtry to Shopify, WooCommerce, BigCommerce, Amazon, eBay, Stripe, PayPal, Slack, Gorgias, Zendesk, EasyPost and Shippo. Browse every integration. - [Contact](https://lumtry.com/contact.md): Questions about Lumtry, launch pricing, integrations or security? Send a message and the team replies by email. Tell us about your refund volume. - [Get started](https://lumtry.com/get-started.md): Pick the refund problem to fix first, choose a plan and create your Lumtry account. Start on the Free plan and connect your store when you are ready. - [Developers](https://lumtry.com/developers.md): Send signed refund webhooks to your tools, call the REST API and let your AI assistant work with Lumtry cases over MCP. Explore the developer tools. - [Refund cost calculator](https://lumtry.com/calculator.md): Estimate a year of manual refund handling and return abuse leakage from your own numbers, then see which Lumtry plan fits your volume. Run the numbers. - [Roadmap](https://lumtry.com/roadmap.md): What Lumtry has shipped, what is coming next and what is further out across refunds, returns, disputes and integrations. Get notified when items ship. - [Compare](https://lumtry.com/compare.md): Lumtry side by side with the tools SMB merchants use for refunds today, built from each vendor's own public pages. Find the right fit for your store. - [Guides](https://lumtry.com/guides.md): Answer-first guides to refunds, returns, chargebacks, approvals and audit trails for Shopify, WooCommerce and BigCommerce merchants. - [Glossary](https://lumtry.com/glossary.md): Plain definitions of refund, return, chargeback, RMA, store credit, audit trail, idempotency key, MCP and other refund operations terms. - [MCP server](https://lumtry.com/developers/mcp.md): Connect an AI assistant or your own agent to your refund workspace through the Model Context Protocol. Read cases and propose actions, never move money. - [llms.txt](https://lumtry.com/llms.txt)