Pure Inference Software studio
Atlanta, Georgia

Writing on spec-driven verification.

Testing method, spec-to-code correctness, search-based validation, dimensional test design. Not general commentary on AI writing code.

All writing

mutation testing kepler
8 Sep Test the Design, Not Just the Code
When whether something works depends on its design rather than its code, a green test suite can sit on top of a puzzle nobody can solve.
Four properties have to hold together, and most of an app fails one
4 Apr Where Specs Work and Where They Don't
Full spec-driven verification only earns its cost where four properties hold at once: deterministic, calculable, enumerable, and objectively provable.
The kind of gap decides the fix — triage stops being a negotiation
3 Apr Bugs Are Missing Scenarios
When a system is built from a spec, a production bug isn't a coding mistake — it's a gap in the spec's coverage, and the fix belongs there, not just in the code.
Nobody imagines the edge cases — the matrix generates them
2 Apr Humans Think in Dimensions, Not Test Cases
Domain experts describe a system as axes of variation, not a list of scenarios, and the test cases worth writing are the intersections of those axes.
Drop the middle leg and the spec is only being compared to itself
1 Apr Agentic Engineering Is Pattern Engineering
A green test suite an AI agent wrote doesn't prove it built what the spec asked for — it can compare a value to itself and still pass.
Starting the second recognition task cancels the first, silently
31 Mar The Undocumented iOS Limit That Rewrote My Architecture
An undocumented platform limit — Apple's SFSpeechRecognizer silently kills a second concurrent session with no error — took an AI research agent two minutes to find and explain.
A pipe, a timeout heuristic, and sixteen orphans — none of it raising
23 Mar Designing a Test Runner for AI Agents
An AI agent doesn't perceive a hung process the way a human does — no progress dots, no felt sense the machine has slowed.
Structure Over Prompts
8 Mar Structure Over Prompts
A decision that's actually deterministic — did this stage pass, should the pipeline advance — is where an AI orchestrator can hallucinate a transition and silently break a pipeline.