Software Factory¶
Metaphor — borrowed from physical manufacturing — for a codebase + infrastructure + agent-fleet setup where software production runs semi-autonomously. Zakariasson's framing at AI Engineer 2026.
The image¶
"Look at real-life factories producing hardware. There's a lot of assembly lines. There's a lot of people that goes into this, a lot of managing, observability and all that. There's a lot of concepts we can borrow from that world and put into the software world."
The factory produces code the way a real factory produces cars: assembly lines (pipelines), guardrails, verification stations, supervisors, and eventually a "dark factory" (Dan Shapiro's term) where the floor runs largely unattended.
Four components¶
- Primitives & patterns — modular codebase, colocated code, consistent startup/test/auth conventions. Agent-friendly = onboarding-friendly.
package.jsonstart scripts are "so in-distribution" that agents self-orient immediately. - Guardrails — hooks blocking sensitive paths (auth, encryption), emergent-cursor-rules that form as you observe failure, tests the agent can self-verify against.
- Enablers — skills/MCPs that expand agent capability (e.g. an "add feature flag" skill so agents ship gated PRs autonomously), external context (Linear, Notion, Datadog, Slack), ability to spawn full dev environment.
- Verifiable systems — the underappreciated one. Agents need to check their own work — unit tests, integration tests, UI tests clicking around the DOM. Backend easy (clear contracts), UI hard (requires computer-use verification).
Why build one¶
- Throughput — agents run 24/7, don't sleep.
- Consistent output — assembly lines produce predictable artifacts if wired right. Without guardrails, agents feel probabilistic and drift.
- Taste leverage — human creative input gets amplified rather than bottlenecked by typing speed.
Running vs building¶
Once built, the job is manager, not worker: look less at code, aggregate agent outputs, catch off-rails behavior, feed the deviations back into rules/skills (the flywheel).
Scaling means nested management — "you still have a small team, then add more people because you need throughput, then need a manager, then a manager of the manager. Same with agents — you just keep going up levels of abstraction."
Cross-references¶
- levels-of-autonomy-shapiro — the 6-stage ladder toward the "dark factory"
- agentic-engineering — Karpathy's adjacent professional-counterpart framing
- agent-as-junior-engineer — Hashimoto's human-model for the same shift
- sync-plan-async-execute — the manager's operating rhythm
- isolated-agent-vms — the scaling substrate
- emergent-cursor-rules — the guardrail-growth mechanism