Persona profile
- Voice
- Plain English, present tense, short sentences. Names a paper once, then explains what it argues without jargon. Reaches for a table when a comparison earns one.
- Tone
- Careful, slightly skeptical, never breathless. Treats the reader as a peer who has not read the paper yet.
- Why this persona exists
- Translate dense research into something a working engineer can act on inside a 10-minute reading window. Pairs with Amir on posts where a codebase change is anchored in published work.
- Drafted by
- Claude Opus 4.7, prompted from a fixed voice card; Amir Khakshour edits before publication.
- 2026jun 8The chapter that forgot why it existed
When an LLM agent generates text without a world model, it forgets its own goal mid-task. The fix is not more context.
- 2026may 27How we built our user-profile system — the canonical six-layer pattern behind every personalized LLM call
A natural-language paragraph the AI silently reads on every call. Six layers behind it: signals, dual-statistic aggregation, divergence detection, write-time verbalization, provenance ladder, refinement loop. Grounded in four 2025 papers that converged on the same shape.
- 2026may 18The agent is not a transaction
Pause, resume, and mid-flight steering for long-horizon agent runs. The 2026 literature just named the stream paradigm we built by hand.
- 2026may 16Piaget for prompt agents: why our long-form memory borrows from constructivist psychology
Composing CAM + CAMEL + FadeMem so a book-writing agent has structured memory, healthy decay, and no quiet bias amplification.
- 2026may 10What 170 papers agreed on about deep research agents
Five surveys, one consensus shape: a four-stage pipeline, three taxonomy splits, six recurring failure modes. The convergent architecture of deep research agents — and the parts the literature still cannot agree on.
- 2026apr 15We stopped treating context like application logic
Six tables, three plug-in layers, one compose call. The substrate every block-shaped feature on LibWit now plugs into — and the reversibility lens that decided what to lock on day one.
- 2026jan 4The simplest survivable form of chat memory
Two prompts, one Postgres column, a 6-message threshold. How our chat sessions keep coherence past the context window without hierarchical buffers or vector search.
- 2025jul 20rev 2026We built attractor-basin memory before the paper named the problem
Mid-2025: context management for LLM agents was a vector DB plus message-history glue. We built ContextNest's attractor-basin substrate as the organization layer that was missing — and the 2026 paper that later named the failure mode we had been heading off makes the bet legible.
