Ideas for AI

Idea #1The progression from in-loop to near-loop to out-loop is a concrete, actionable framework for measuring agentic engineering skill — and the right measure of skill is now how many…

Idea #1We are stuck in a structurally worst-of-both-worlds moment with AI agents — call it the 'awkward in-between' — and understanding it as a phase (not a permanent condition) changes…

Idea #1Production agents should run two distinct continuous improvement loops, not one: a real-time memory/escalation loop and a retroactive harness-update loop driven by trace data. These loops are architecturally different…

Idea #1Future knowledge leakage is the central validity threat when backtesting any AI agent that uses web search, and it is easy to miss because it manifests as suspiciously good…

Idea #1Model benchmark scores are widely misread, and the misreading causes bad product decisions. Leaderboard Elo differences of 80–90 points between frontier labs do not mean one model is 80…

Idea #1Intent engineering — the skill of precisely communicating what you want to an agent — becomes more important as LLMs get more capable, not less. The mechanism is straightforward:…

Idea #1Every LLM call in a production workflow should be wrapped in a larger deterministic process, not exposed directly to user input. The tendency is to treat an LLM like…

Idea #1For deduplication — detecting whether incoming information has already been processed — a decision model outperforms vector similarity search in both accuracy and confidence. The standard approach is embedding…

Idea #1Pre-rendering document pages to screenshots during the indexing pipeline — and storing those screenshots alongside text chunks — is a meaningful quality lever for enterprise RAG on complex documents,…

Idea #1A coding agent can be used to deploy its own infrastructure, collapsing multi-hour manual VPS setup into a guided conversation — but the pattern only works cleanly when the…