Answers to

Questions we hear most about AI agents

Ways to work with us

Internal agents are AI agents that handle work inside your own organization, such as paying invoices, triaging support tickets, or onboarding new hires. Agentifiers sets up the platform in an AWS account in your AWS Organization, brands it as yours, and builds supervised agents for your processes with your team.

Agents in your product are for product teams building AI agents into their own product for their own customers. The platform is multi-tenant, so each of your customers can be an isolated tenant. You can self-host it once the source is released (coming soon), have us set it up in an AWS account in your AWS Organization, or use the hosted Deployments.ai service in our AWS account. Offering the platform to your customers under your brand is covered by a commercial license from us.

Choose internal agents to take repetitive work off your own staff in an AWS account you control, AI agents for small businesses if you want us to set up and run them with no cloud account or IT team on your side, and agents in your product to ship agent features to your customers. Internal agents work for organizations on AWS from small businesses to enterprises, with the same architecture and safeguards at every size.

If you are not sure, tell us what you are exploring and we will say plainly which path fits. If you are still weighing other routes, see the ways to get AI agents into production.

Not for small-business setups. For AI agents for small businesses, we build bespoke agents for your processes, usually in Slack or a simple internal tool, and run them for you on hosted Deployments.ai in our AWS account. Internal agents engagements run in an AWS account in your own AWS Organization (BYOC), which we help you create if you need one.

Yes. Both paths run on the same source-available, multi-tenant platform, so the agent code, tools, and review practices carry over from one to the other. You can start with either and add the other later. We will plan how they fit together in your AWS Organization.

Internal agents

To agentify a workflow is to rebuild a real, recurring piece of work, such as paying invoices or triaging support tickets, so that supervised AI agents do the reading, looking up, drafting, and routing while people keep the decisions that carry risk. Agentifiers maps the workflow, places approval points on purpose, builds narrow agents for each step, evaluates them against your own past work, and ships them as versioned releases you can measure.

Read more about agentification and how we agentify a workflow, or see internal agents for how an engagement runs.

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

We pick one workflow, get it working well, and expand from there. See all AI agent use cases.

People stay in control through approval points: risky actions, such as releasing a payment, changing access, or sending a first message to a customer, are tool calls that require a person's 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. Read more in human-in-the-loop AI agents, by design.

Approval points catch a wrong proposal before it becomes a wrong action, and traces show why the agent made its call. The case is then added to your evaluation set, so the next release is tested against it before promotion, and because releases are immutable and versioned, a change that makes things worse can be rolled back.

Agents in your product

Each of your customers can be an isolated tenant with its own agents, memory, credentials, and audit trail. The platform isolates tenants at three levels (organizations, projects, and environments), so no customer sees another's work, and it handles retention, tenant export, and erasure per tenant, which makes each customer's data requests simpler to answer.

See agents in your product for what your engineers get.

Choose by who should operate the platform. Self-host if you have platform engineers and want full control (free for your own use once the source is released, coming soon). Have us set it up in an AWS account in your AWS Organization if you want BYOC without the platform work. Use Deployments.ai hosted and managed by us in our AWS account if you don't want to run infrastructure. All three run the same platform, Deployments.ai, with the same API:

  • Self-hosted (coming soon). Run the platform yourself once the source is released, 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 the hosted Deployments.ai service, which we run in our AWS account, and skip running infrastructure.

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

Plan it before you start. Hosted Deployments.ai is the same platform, with the same API, as a self-hosted install, so your agents, defined as code, are portable; moving tenant data and configuration into an AWS account in your own AWS Organization is something we plan with you up front rather than a one-click switch. If you may want to move later, talk to us before you start.

Your customers see 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.

Your cloud & security

BYOC (bring your own cloud) means the agent platform runs in a cloud account you own instead of the vendor's. With Agentifiers, you create a dedicated AWS account inside your own AWS Organization and give us scoped access, and we deploy the platform there with OpenTofu. The account sits under your service control policies and consolidated billing, so you own the infrastructure, the keys, the data, and the bill.

Read more: BYOC for AI agents.

In a BYOC setup, your AWS account runs 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.

Agentifiers needs 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 hosted Deployments.ai, you can export your tenants' data before you leave.

Platform & license

Deployments.ai is the platform, and Agentifiers is the company that builds it. Deployments.ai is a source-available (FSL-1.1-ALv2), multi-tenant AI agent platform; its source release is coming soon. Agentifiers also runs Deployments.ai as a hosted, managed service in Agentifiers' own AWS account.

You can run Deployments.ai three ways: self-hosted (coming soon), set up white-glove by Agentifiers in an AWS account in your own AWS Organization (BYOC), or hosted and managed by Agentifiers in its AWS account. For internal agents, Agentifiers installs Deployments.ai in your AWS Organization, white-labels it, and builds the agents with your team. Squadmates is also built on Deployments.ai. See the platform and about Agentifiers.

Amazon Bedrock AgentCore is a set of AWS-managed agent services, such as runtime, memory, gateway, and identity, that your team assembles into a platform. Deployments.ai, the platform Agentifiers sets up, is a complete multi-tenant agent platform (releases, approvals, evaluations, traces, metering, and channels) that runs in an AWS account in your AWS Organization, and for internal agents we also build and operate the agents with you.

See the full comparison: Agentifiers and Amazon Bedrock AgentCore.

No, not yet: the platform's public source release is coming soon. The platform will be 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 will be MIT licensed. If you want to hear when it is out, let us know.

The platform's license, FSL-1.1-ALv2, lets you 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.

A white-label agent platform runs under your brand instead of the vendor's. With Agentifiers that covers your name, logo, and colors on the interfaces your team uses; your own domain for the platform and for agent email; and 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. Your engineers can extend the platform: agents are defined as code, with immutable, versioned releases, canary rollout, and promotion between environments, and 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.

Pricing & billing

Agentifiers bills by invoice only. We bill our fees by invoice, itemized against the scope we agreed. Access to hosted Deployments.ai 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.

An internal agents engagement takes one of three shapes: Launch, a fixed-scope project that deploys the platform in your AWS account, brands it, and agentifies one or two processes; Scale, a monthly embedded pod that keeps agentifying workflows with you; or Enterprise, a planned program across departments.

  • Launch. A fixed scope: set up the platform in your AWS account, brand it, agentify one or two processes end to end, 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 internal agents engagements and pricing for both paths.

Yes, self-hosting is free for your own use under the platform's source license (FSL-1.1-ALv2), once the source is released (coming soon). You pay us only if you want us to set it up in your AWS account, want access to the hosted Deployments.ai service, or need a commercial license to offer the platform to your customers under your brand.

To get started, 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.