Where your data goes, and what is written down.
Every statement on this page describes what the system does today, checked against the code or the live configuration that does it. Where something is not true yet, it says so rather than being written in the future tense.
SOC 2 and ISO 27001 are in progress: we are not certified today. If your process needs a report before you can proceed, tell us where you are in your evaluation and we will tell you honestly whether our timeline can meet it.
Live control status on our trust centerWhat runs today on the hosted service, in the United States and Australia.
- Databases, file storage, disk volumes and container images are encrypted at rest.
- The service is served over HTTPS only; plain HTTP is redirected.
- Secrets are held as encrypted parameters, never in the image or the task definition.
- API keys are stored hashed; the plaintext exists only when a key is created.
- Cloud access goes through single sign-on. There are no long-lived cloud user accounts.
- Multi-factor authentication is required on the cloud root account and on every member of our code organisation.
- Production databases are not publicly reachable.
- Every code change is peer-reviewed before it merges.
- Changes to production need an additional, named approver before they merge.
- Platform and engine code is scanned for committed secrets on every pull request.
- Cloud API activity is recorded in an audit trail.
- Network flow logs are kept for every production network.
- Managed threat detection runs in every region we host in.
- Each production deployment of the US service notifies our on-call channel.
- Container images and compute are scanned continuously for known vulnerabilities.
- Dependency vulnerability alerts are on for the Studio platform, engine and mobile app.
- Independent penetration test — in progress.
- Databases are backed up automatically, with point-in-time recovery over a 7-day window.
- Restores are tested; the most recent, in October 2026, produced a working encrypted copy in under 13 minutes.
Core providers used by the hosted service, on the standard US deployment and on our Australian deployment for customers whose data must stay in Australia. Services connected by a customer depend on that workspace’s configuration.
ECS Fargate runs the application; RDS Postgres holds tenants, policies, traces and the usage record and is not publicly reachable; Cognito authenticates console sessions; SSM SecureStrings hold secrets; CloudWatch holds application logs. Amazon Bedrock also provides managed model inference for configured models. The Australian deployment keeps its database, backups, files, sign-in, logs and code tools in Sydney; its role is denied every AWS call outside Sydney, and it calls only Bedrock’s Australian inference profiles, which run in Sydney and Melbourne.
A model-routing service used alongside Amazon Bedrock. Not used on the Australian deployment, which refuses any model outside Bedrock’s Australian profiles, even with a customer’s own key. Inputs, selected images, conversation history and retrieved library content may reach a model through it. Every OpenRouter request asks OpenRouter for providers that do not train on prompts and for zero-data-retention endpoints only, on every workspace, with no setting to turn it off. A model no provider serves that way is refused when it is chosen, not on the turn it would have failed. On a bring-your-own-key workspace this is your account and your contract, not ours.
Holds the subscription outright — checkout, invoices, payment methods, cancellation. Card details never reach us. No mirrored copy of subscription state is kept here.
An agent turn can involve multiple model calls. Guardrails, memory, evaluations and connected tools may also process content outside the application.
The request arrives
Studio authenticates users with Cognito-backed sessions and checks workspace access in the application. The mobile app uses an authenticated session. Integration API keys are stored hashed; the plaintext is shown when a key is created.
The question is screened
Configured input guardrails check a request before the agent answers. Guardrails may make model calls, so a declined request may still send input to a model provider.
The library is navigated
The agent walks an index of your documents and opens pages by name. There is no embedding step and no vector store, so your library is not copied into a second representation held somewhere else.
The model is called
Through Amazon Bedrock or OpenRouter, according to the configured model and credentials. A workspace may use its own OpenRouter account. A regional deployment calls only models served in its region. Inputs, conversation context, selected images and retrieved documents can be included in the request.
Output guardrails check the answer
Configured output guardrails check the response. Some checks are deterministic; model-based checks and evaluations can make additional provider calls. Their outcomes are recorded with the run.
The response carries its own evidence
A decision — answered, declined or escalated — the pages it opened, the guardrails that ran, and the usage that will bill. The same number your invoice is built from.
Use your own model provider account.
Krazimo does not use your data to train foundation or fine-tuned models unless you agree in writing.
Point a workspace at your own provider key and inference is billed to you directly, at whatever rate you have negotiated. More importantly for this page: the question text and the retrieved library content then travel under your contract with that provider, on your terms. OpenRouter requests still require no provider data collection and zero-data-retention endpoints. Studio’s own conversation and run records have separate retention.
We take no share of model spend in either arrangement. When you do not supply a key it is passed through at what it cost us, which is the only reason our own route exists.
Content and metadata can both contain personal information. Retention depends on the record and its purpose; the debugging window does not govern every record.
A conversation is your record of what your users asked and what your agents answered, so it is not on a timer. Contact your workspace administrator or support@krazimo.com to request export or deletion.
A run's input, each step's input, output and logs, and the run's result. A failed run keeps them longer because that is the one someone comes back to debug. A Machine block's task output is kept 30 days either way, because the block's next runs are given its past results. The run's status, timings, errors and cost are kept: they are its record, not its content.
This setting applies only to captured model-request bodies used for debugging. Setting it to zero does not prevent Studio from storing conversations, run inputs and outputs, or attached images.
Model, timing, token counts and cost per call. It is what the monitoring screens and the cost accounting read. It is metadata about a call, not the content of one.
It is the billing record and the only one. The number a turn is metered on is the number you are invoiced for, which is why there is no separate counter that could disagree with it.
Your documents support retrieval by your agents. Removing a source document does not automatically remove excerpts already recorded in conversations, run results or backups.
Shared with customers and prospects for a security review, usually under NDA.
- Information security policies
- SOC 2 readiness assessment
- ISO 27001:2022 readiness assessment
If you believe you have found a security issue in Krazimo Studio, email us with the steps to reproduce it. Please give us a chance to fix it before telling anyone else.
security@krazimo.comQuestions this page did not answer?
Security review questions get a written answer from someone who has read the code, not a questionnaire response assembled from a template.