What is dark factory software development?
Where the term came from, what it means, and which claims about autonomous software production have evidence behind them.
Blog
FeedYour spec is an output, not an input
Level 4 tells you to write the specification first. Every specification worth having was extracted from a working implementation, and the tools all point the arrow the wrong way.
Your agent is secured at the wrong layer
Tool allowlists and OAuth scopes secure the verb. The exposure is the noun: which rows, which columns, which tenant. Your ORM already knows how to enforce that, and almost nobody is using it.
Most harness engineering is procrastination
Building the thing that builds the thing feels like leverage and is usually avoidance. The test is whether you can name one shipped outcome that exists because of your harness.
What your MCP server should refuse
Every destructive tool call has a blast radius, and almost no tool interface expresses it. The missing primitive is a contract that distinguishes deleting a row from deleting the row and every backup of it.
Stop treating agent memory like a database problem
Your harness already writes an append-only event store. Every agent memory tool worth keeping is a disposable read model over it, and treating memory as storage is why these systems rot.
The adapter is now cheaper than the library
A whole class of dependency, the thin wrapper that unifies several providers behind one interface, just flipped from asset to liability. A taxonomy of what the agent era kills and what it entrenches.
Two questions every agent session should end with
The end-of-session summary is the least useful artifact your harness produces. Replace it with a fixed interrogation, scripted rather than remembered.
The harness is the cost
Cost discourse in agentic coding fixates on model choice. The dominant cost term sits one layer down, it is roughly quality-neutral, and you cannot see it until you log the API boundary.
Agents need durable execution. Laravel already had it.
The hard part of agentic infrastructure is not the model loop. It is resumability, budget control, idempotent side effects, and auditable state, and Laravel shipped that layer years before anyone needed it for agents.
Four graphs are hiding inside one term
Graph engineering is a useful way to expose control, state, knowledge, and improvement relationships, but only when we stop treating every graph as the same thing.
The demo became the search
Writing a post about graph engineering forced the glossary to define graphs. Defining them produced a working one. Six hours later it replaced the search box. Receipts included.
Future posts we're working on
- Selection evals and acceptance evals are different jobs
- Token maxing, token anxiety, and the missing denominator
- Generation is cheap. Verification is the factory.