L5: The dark factory
Agents building the software with humans out of the loop. Shapiro reports it working only for teams under five people, and calls it likely our future.
The path.
- Swarms & fleets In Orchestration Patterns Once one agent works, the obvious move is to run several. This is where the biggest gains and the biggest self-inflicted wounds both live.
- The factory model In Agentic Engineering: Core Ideas "Agentic coding" is an overloaded term.
- Human factors The techniques above make you faster. This chapter is about what they can quietly cost you, and how not to pay it.
Check yourself.
One question per step. Take it cold to find where to start, or after reading to see what stuck. Nobody's grading you.
Best so far:
Question 1 of 3
-
When should you split work across multiple agents?
The heuristic is to go multi-agent only when a single agent hits a real wall: context overload, missing specialization, or no coordination primitives. Otherwise it's pure overhead and small mistakes compound.
Covered in step 1 · Swarms & fleets -
In the factory model, what happens to a muddy spec fed to thirty parallel agents?
The factory model's sharpest warning is that vague thinking no longer just slows you down. It multiplies, producing a variously-wrong artifact from every parallel agent.
Covered in step 2 · The factory model -
Agents ship clean, passing code all week. What can still be quietly accruing?
Comprehension debt is the growing gap between how much code exists in the system and how much of it any human genuinely understands. It accrues invisibly while the code is clean and the tests pass.
Covered in step 3 · Human factors
-
L0: Manual
The ground floor: AI as a search engine and occasional tab-complete. No real productivity change.
Everyone starts here. There's nothing to unlock yet.
-
L1: Discrete task offloading
You hand the AI small, self-contained jobs: write the unit tests, draft the docstring, generate one well-scoped function. The real work is still yours.
Chat assistants · Prompting 101 · IDE assistants
Explore path -
L2: Active pairing
The AI writes alongside you all day, handling the boring parts while you steer and review everything as it lands. Shapiro estimates about 90% of AI-native developers live here.
CLI agents · AGENTS.md & CLAUDE.md · What an agent actually is
Explore path -
L3: Human-in-the-loop management
You mostly stop typing code. Agents run several tasks at once and your day becomes reviewing their work. Most people never go past this level.
Own the outer loop · Agentic code review · Role separation · MCP & tools
Explore path -
L4: Specification-driven
You define what to build instead of building it: write the spec, set the tests, judge the results. Leave for twelve hours and come back to a green suite.
The harness as an artifact · Evals-as-tests · LLMOps & guardrails
Explore path -
L5: The dark factory
Agents building the software with humans out of the loop. Shapiro reports it working only for teams under five people, and calls it likely our future.
Swarms & fleets · The factory model · Human factors
You're on this rung