Runtime vs Factory

Factory and Runtime at a glance

Factory builds Droids, AI agents that implement, test, review, and maintain software across the development lifecycle. Large engineering organizations use them for migrations, code review, documentation, and incident response, from the IDE, CLI, Slack, or Linear.

Runtime is the AI agent harness for payment teams. From payment ops to risk, compliance, and support, anyone on the team can build agents that work their queues on their own computers inside your cloud, called from Slack, Teams, email, SMS, or voice, with approvals and a full audit trail.

Factory is for engineering organizations shipping software. Runtime is for the payment, risk, and finance teams that run the business on top of it.

How they differ

Fintech operations, not the SDLC

Droids are tuned for the software lifecycle. Runtime agents are built for money movement: processor reason codes, ACH returns, bank files, network rules, reserves, and settlement. The users are ops analysts writing SOPs, not engineers writing tickets.

Bring your own cloud, sandbox, and models

Runtime runs agent computers in your AWS, GCP, or Azure account, or fully self-hosted via Helm. You can use your own sandbox provider and any model, including open-weight models served in your cloud for PCI and PII work.

Harness and model routing

Runtime routes work across Claude Code, Codex, and OpenCode and across models, with fallbacks when a provider goes down. Engineering can use the same harness for coding tasks while ops teams run their agents on it.

Guardrails and an FDE who knows payments

Ops agents act on money, so Runtime agents start read-only, ask for approval before anything moves money, and record every query, tool call, approval, and cost. A forward-deployed engineer with a payments background maps your processes and builds the first agents with your team.

Where Factory is stronger

• Software engineering depth. Purpose-built Droids across implementation, testing, review, and maintenance.
• Engineering workflows. Migrations, code review, documentation, and incident response.
• Developer surfaces. Works from the IDE, CLI, Slack, and Linear.
• Large engineering organizations. Built for engineering productivity at scale.

Which should you choose

Choose Factory if

• Your users are software engineers
• The work is code: features, migrations, reviews, incidents
• You want agents across the full development lifecycle
• Engineering productivity is the primary goal

Choose Runtime if

• Your users are payment ops, risk, compliance, finance, and support teams
• Agents need to work your ledger, processor, and bank data in your cloud
• You want harness and model routing instead of one vendor's agent
• You need approvals on money movement and an audit trail your sponsor bank will accept

Frequently asked questions

Is Factory good for fintech companies?

Factory is a strong choice for fintech engineering teams that want agents across the development lifecycle. Its Droids are built for software engineers. Runtime is built for the operations teams around the code: payment ops, risk, compliance, finance, and support.

Can non-engineers use Factory or Runtime?

Factory is engineer-facing. On Runtime, ops analysts build agents from their SOPs in plain English, while engineering controls credentials, access, and any code the agents write.

What is the best Factory alternative for payment operations teams?

For payment operations work like held payouts, ACH returns, disputes, and recon breaks, Runtime gives ops teams agents that investigate across your ledger and processor, with approvals before money moves and a full audit trail.

Can Runtime run in my own cloud with my own models?

Yes. Runtime agent computers run in your AWS, GCP, or Azure account, or fully self-hosted, with your own sandbox provider and any model, including open-weight models served in your cloud.