No Closed Form
Notes

Notes, essays, and things I don't fully understand yet.

Writing that ranges from finished argument to seedling. Filter by topic; maturity shows on each card.

AI Systems

Why Most Agent Demos Stop Before the Hard Part

The gap between doing a task once and operating the same workflow repeatedly.

evergreen 2026-07-14
Building

Don't Write Fallbacks

A fallback postpones an error to where it's harder to diagnose; orthogonal modules remove the class.

evergreen 2026-07-10
AI Systems

The MCP Surface and the Exec Surface

Why every LLM-generated tool call should cross one audited surface — and what stays in code.

growing 2026-07-06
AI Systems

List the Excuses an Agent Will Use to Skip a Step

Models don't cut corners; they generate a reason to. Name the rationalizations up front.

growing 2026-07-02
Finance & Models

Financial RAG Is Not Just Document Search

Filings, market data, calculations, and provenance each want a different system layer.

growing 2026-06-24
Finance & Models

Model Risk as a Knowledge Representation Problem

What's lost when a model inventory is treated as a spreadsheet, not a graph.

seed 2026-06-15
Building

A Standard for Agent-Built Projects

Separate project facts, agent behavior, rules, and execution — before implementation begins.

evergreen 2026-06-06
Finance & Models

Evidence That Can Be Traced

Traceability isn't a source column; it's every number reaching back to its raw fact.

seed 2026-05-28