Pick the path, then pick how hands-on you want us to be

It means taking a real, recurring piece of work and rebuilding it so supervised software agents do the reading, looking up, drafting, and routing, while people keep the decisions that carry risk.

We map the workflow, place approval points on purpose, build narrow agents for each step, evaluate them against your own past work, and ship them as versioned releases you can measure. See internal agents for how an engagement runs.

The best first candidates are repetitive, high-volume, and mostly about reading and matching, with a few clear decisions. Common starting points:

• Accounts payable and invoice matching
• Customer support triage and reply drafting
• Lead research and CRM hygiene
• Employee onboarding across HR and IT
• Scheduling and dispatch

We pick one workflow, get it working well, and expand from there.

Risky actions, such as releasing a payment, changing access, or sending a first message to a customer, are tool calls that require approval before they run. The platform enforces this, so an agent cannot skip it.

Approval requests arrive in Slack or email with a plain summary and a link to the full trace. Every run is recorded, so you can see what each agent read, what it proposed, and who approved it.

It will happen sometimes, and the system is designed for it. Approval points catch wrong proposals before they become wrong actions, and traces show why the agent made its call.

We add the case to your evaluation set, so the next release is tested against it before promotion. Releases are immutable and versioned, so a change that makes things worse can be rolled back.

The platform is organized as organizations, projects, and environments. Each level isolates agents, data, and credentials, so each of your customers can be its own tenant without seeing anyone else's work.

Retention, tenant export, and erasure are handled per tenant, which makes it simpler to answer your customers' data requests.

All three run the same platform:

• Self-hosted. Run the platform yourself from the source, free for your own use. Serving it to your customers under your brand needs a commercial license from us.
• Set up in your AWS account. We deploy and configure the platform in an AWS account in your AWS Organization, for a fixed scope. You run it from there.
• Hosted & managed. Use our hosted, managed platform and skip running infrastructure.

See agents in your product and pricing for how each one works.

The hosted platform is the same platform and API as the self-hosted version. If you think you may want to run it in your own AWS account later, talk to us about moving later before you start, so we can plan for it together.

Your product and your brand. Agents reach your customers through your own app and API, using client-executed tools that call functions inside your app, and through channels such as Slack, email on your own domain, Telegram, and RCS business messaging. Agentifiers stays in the background.

Yes. The platform includes usage metering, so you can see what each tenant uses and feed it into your own billing. How you price and bill your customers stays yours. We do not sit between you and them.

Bring your own cloud. You create a dedicated AWS account inside your own AWS Organization and give us scoped access to it. We deploy the platform there with OpenTofu. The account sits under your service control policies and your consolidated billing, and you own the infrastructure, the keys, the data, and the bill.

The agent runtime, workflow state, schedules, memory, traces, and audit trail. It is built on standard AWS services such as Lambda, ECS on Fargate, DynamoDB, S3, KMS, EventBridge, SQS, and API Gateway.

Retention, export, and erasure are policies you set. Audit logs can be exported with signatures for reviews. Dev and prod can live in separate AWS accounts.

The platform is model-agnostic. A model gateway routes requests only to the model providers you approve, under model policies you control, using your own provider keys.

Agents send model providers the content needed for each step. Everything else, including runtime, state, traces, and the audit trail, stays in your AWS account. Traces show exactly what was sent to which provider.

We need scoped roles in the dedicated AWS account, with only the permissions the work requires. Your team can review them before granting them, and our activity is logged in your account like any other.

You can revoke our access at any time, and we remove it at the end of an engagement unless you ask us to keep operating.

In a BYOC setup, you keep everything. The platform keeps running in your account, the agents are code in your repository, and the evaluation sets, runbooks, and audit trail are yours. You can operate it yourselves, extend it with your own engineers, or work with someone else.

On the hosted platform, you can export your tenants' data before you leave.

Yes. The platform is source available in the Agentifiers/deployments repository under the Functional Source License, Version 1.1, with the Apache License 2.0 as its future license (FSL-1.1-ALv2). FSL is a Fair Source license rather than an OSI-approved one. Each release becomes available under Apache 2.0 two years after it is published. The platform's TypeScript SDK and CLI are MIT licensed.

You can read the code, self-host the platform, and modify it for your own use, including commercial use inside your business. You cannot offer it to others as a competing commercial product or service. White-labeling the platform for your customers or reselling it is a competing use, and we offer it under a commercial license. If you are unsure whether your use competes, ask us before you build on it.

The platform runs under your brand, not ours:

• Your name, logo, and colors on the interfaces your team uses
• Your own domain for the platform and for agent email
• Agent identities you choose, such as the name and icon an agent uses when it posts in Slack

To your staff, the agents are part of your organization. For internal agents, white-label setup is part of the engagement. Putting the platform in front of your own customers under your brand is offered under a commercial license.

Yes. Agents are defined as code, with immutable, versioned releases, canary rollout, and promotion between environments. Your engineers build on the platform through its public API, SDK, and CLI.

Tools can come from MCP servers, HTTP callbacks, or the integration catalog, or be client-executed tools that call functions inside your own app. We hand over runbooks so your team can make changes with the same review and evaluation process we use.

Invoice only. We bill our fees by invoice, itemized against the scope we agreed. Hosted platform access is also invoiced by us.

In a BYOC setup, your AWS infrastructure is billed directly by AWS on your own account, with no markup from us, and model usage is billed by the providers you choose, on your own keys.

There are three common shapes:

• Launch. A fixed scope: set up the platform in your AWS account, brand it, agentify one workflow, and hand over code and runbooks.
• Scale. A small embedded pod of ours, billed monthly, keeps operating the platform and agentifying more workflows with you.
• Enterprise. A planned program across departments, with separate environments, governance reviews, and your internal teams involved throughout.

See pricing for both paths.

Yes, for your own use under the platform's source license. You pay us only if you want us to set it up in your AWS account, want access to our hosted, managed platform, or need a commercial license to offer the platform to your customers under your brand.

Reach out through our contact page and tell us whether you are exploring internal agents or agents in your product. Bring the workflow that costs your team the most time, or the agent feature you want to ship. We will tell you plainly whether it is a good fit and what a first step would involve.