vs Factory

Forge vs Factory

Factory's Droids already do adjustable autonomy, model routing and custom subagents — so this is not a feature-gap argument. The difference is that Forge puts an independent management agent between roles and commits every handoff to your repository, and runs work that is not software at all.

A subagent is delegated to; a Forge role is reviewed

Factory's custom Droids are reusable subagents with their own prompt, tools, model and autonomy level — a lead agent calls one and decides whether the result was good. In Forge, an independent management agent reads the handoff and can send it back with enrichment instructions before anyone builds on it.

Permission before a change, versus a record after it

Factory's explicit permission model lets you review every modification before it touches your codebase, which is the right control. Forge answers a different question: months later, why was it done this way? The spec, the brief and each role's reasoning are commits in your repository.

A count, not an ROI percentage

Factory's enterprise page advertises multiples and percentages with no published methodology. We answer with a count and its method: in twelve weeks of Forge building Forge, a management agent judged 1216 handoffs and stopped 80 of them. No invented baseline, no productivity multiple.

Software is one archetype, not the product

Factory is an autonomy stack for software development. The same Forge engine runs research, content and operations teams — different roles, identical mechanics.

What Factory is, in its own words

Factory positions itself as “THE INDUSTRIAL REVOLUTION FOR SOFTWARE DEVELOPMENT” and “THE AUTONOMY STACK FOR ENTERPRISE TEAMS.” Its agents are Droids: “Give Droids a task in natural language and they plan, write, test, and ship code.” The product spans surfaces — “Terminal and IDE to collaborate. Browser, Slack, Jira to delegate. CLI to automate”, working “natively in VS Code, JetBrains, Vim, the browser, Slack, and the terminal” — and “Droids keep their knowledge across tools and platforms.” Control is explicit: a section headed “Adjustable autonomy” promises “From fully supervised to autonomous execution, you control the boundaries for edits, execution, and approvals”, and “Secure by default” with an “Explicit permission model” so you “Review every modification before it touches your codebase.” Models are not locked in — “Choose Claude, GPT, Gemini, or any model per task”, “No vendor lock-in.” Its enterprise page lists SOC 2, ISO 42001, GDPR and CCPA, SSO/SAML, dedicated compute, and native integrations with GitHub, GitLab, Jira, Linear, Notion, Sentry, PagerDuty, Slack and others. Custom Droids are reusable subagents defined as Markdown files under .factory/droids/, each with “its own system prompt, tool policy, model, and autonomy level.” (Sources: factory.ai , factory.ai/product/droids , factory.ai/enterprise .)

Model choice, adjustable autonomy, subagents with their own tool policy and delegation from Slack and Jira are all there, so a feature checklist will not decide this one.

So this comparison comes down to two narrower things: who judges a handoff, and where the reasoning ends up.

The difference in one table

FactoryForge
The agent unitA Droid; custom Droids are reusable subagents with their own prompt, tools, model and autonomy levelA named role in a team — PM, architect, developer, tester, reviewer, researcher, writer
Who judges a stepThe calling agent, plus you, through the permission model before a change landsAn independent management agent on every edge: pass, return with enrichment instructions, or escalate to a person
When review happensBefore a modification touches the codebaseBetween roles, on the work product, before the next role builds on it — and again at the pull request
A rejected stepRe-prompt or deny the changeA new commit; the earlier attempt stays in history and git diff shows what changed
The recordSessions and knowledge carried across Factory’s surfacesA branch in your repository — spec, brief and every handoff as commits, Co-authored-by the persona
Models“Claude, GPT, Gemini, or any model per task”A routing gateway across a provider pool with priority weights and automatic failover, including self-hosted models
Where it runsFactory’s platform, with dedicated compute for enterprisesManaged SaaS, or self-hosted runners on your own hardware; the toolchain is open source
ScopeSoftware developmentSoftware delivery (most mature), plus research, content and operations

Where Forge is different

An independent judge, not the caller’s opinion. Factory’s custom Droids are delegation targets: a lead agent invokes one, gets a result, and decides what to do with it. Forge inserts a separate management agent on the edge whose only job is to evaluate the handoff — it can pass it, return it with specific enrichment instructions, or escalate to a person. The difference shows up when the calling agent is the one that is wrong. See Multi-Agent Pipeline .

Permission and provenance are different controls. “Review every modification before it touches your codebase” answers “should this change land”. It does not answer “six months from now, why did we build it this way, and what did the reviewer object to”. Every Forge run leaves a branch holding the spec, the original brief and each role’s structured and freeform handoff as commits, authored by the persona — readable with git log by someone who was not there. See Git-Backed Audit .

Your infrastructure, and an open-source toolchain. Self-hosted runners keep execution on your machines, and inference is routed across a provider pool you control, including self-hosted models and any OpenAI-compatible endpoint. See Bring Your Own Hardware and Multi-Provider Routing .

Not only software. The same engine, validation loop and audit trail run a research team that verifies its own sources, a content team, or an ops rotation — same mechanics, different roles. See the use cases .

The one number a single agent cannot report

Factory’s enterprise page advertises a multiple on delivery speed, a percentage cut in migration time and a percentage of on-call time saved, with no sample size, baseline or method beside them. We will not answer that with a percentage of our own. We will answer it with a count, and with where the count came from.

Twelve weeks of Forge building Forge
Runs dispatched322
Handoffs judged by a management agent1216
Sent back to their author for rework56
Escalated to a human24
Runs where the supervisor stopped at least one handoff51
Runs that completed215
Runs that failed, escalated or were cancelled103
Median wall-clock, dispatch to finished run39 minutes
Median handoffs per completed run5
Pull requests merged, across 7 repositories202

Where these came from. One workflow — Main Forge SDLC, the one that builds Forge — every run it made in twelve consecutive weeks, counted from the control plane’s own records. Not a sample, not a pilot, not a customer case study we cannot show you.

Forge stopped its own work 80 times. 56 handoffs went back to their author with specific rework instructions; 24 went to a person. One run in six was interrupted by its own supervisor before any human looked at it. That is precisely the review a single-agent tool leaves on your desk — here it is priced at one model call per edge, and counted.

It merged 202 pull requests across 7 repositories in the same period — roughly 17 a week, into the platform you are reading about, with a human performing every merge. Organisation-wide, agent-authored work merged at 773 of 875 opened. Forge is not a demo running beside the product; it is how the product gets built, and these are its commits.

A finished run takes about 39 minutes and 5 handoffs. Median dispatch-to-done — and inside those 39 minutes sit the reviews that stopped 80 pieces of work from reaching the next role in the state they were first written in.

Note what is missing: no productivity multiple, no saved-hours figure. Producing one would require inventing a baseline. A count of what the system did can be checked in principle; a percentage improvement over an unstated counterfactual cannot be checked at all — and a custom Droid, being judged by the agent that called it, has no edge on which a number like the 56 could even be recorded.

Ask us to walk you through the runs themselves — the branch, the handoff commits, the verdicts that sent work back, and the ones that went to a person. Every other number on this site belongs to a named run and says so: 18 sources gathered, 11 verified by direct retrieval, 4 corroborated and 2 shipped marked unverifiable, on the research use-case page .

Sources

  • factory.ai — positioning, customer names.
  • factory.ai/product/droids — what a Droid is, adjustable autonomy, permission model, model routing, surfaces.
  • factory.ai/enterprise — integrations, compliance frameworks, support, and the ROI figures discussed above.
  • Forge claims on this page link to the corresponding feature pages , which describe the mechanism in detail.

Evaluating an enterprise autonomy stack?

Ask both of us for the audit trail of a real run. Forge proposes the team and waits for your approval before spending anything.