Featured7 min read
RightLayout: Shipping a Mac AI Tool, Then Letting Go
Why a solo Mac keyboard-layout corrector with a CoreML model trained from scratch beat a 10-person dictionary tool, and why I open-sourced it.
AI Systems
Notes
Notes on AI systems, retrieval, and the work that starts after the demo.
Notes on retrieval, evals, observability, and the engineering that starts once the demo is the easy part.
18 posts
13 min read
New
Forecasting Without Prophecy: a plain-text discipline
Why I leave the future to astrology and reach for reference classes, premortems, and calibration logs instead. Disciplined uncertainty in plain text.
4 min read
Need a job? Sip your drink. We'll look for you.
Why I stopped applying the LinkedIn way and built a quiet service that does the grind for me, and now for you. Drop a résumé once, get a ranked daily shortlist with a one-line pitch hint per role.
7 min read
I Ran 12 AI Agents for 47 Hours. Here's What Survived.
Open-source deterministic orchestrator for parallel CLI coding agents. Runs Claude Code, Codex CLI, Gemini CLI in parallel — zero coordination tokens, 37 adapters, janitor verification, git worktree isolation.
5 min read
Working Under Repeated Alarms
A short note from Israel on what repeated alarms do to attention, engineering judgment, and team habits — and which working practices make interruption easier to absorb.
+2
22 min read
How to Build Legal Answering Systems That Can Be Trusted
A practical blueprint for legal QA, shaped in part by work around the Agentic RAG Legal Challenge: document identity, hybrid retrieval, structured answers, page-level grounding, telemetry, and evals.
+2
5 min read
LLM Product Safety Without Theater
A practical guide to LLM product safety: prompt injection, excessive agency, unsafe outputs, evals, and sober boundaries.
+2
7 min read
Interface Design for Serious Products
A practical memo on calm authority, visible product care, restrained motion, and why trustworthy interfaces feel expensive.
5 min read
Getting AI-Assisted Development to Green Without Breaking the Code
Repair loops, small diffs, test trust, and how to get CI back to green without trashing the codebase.
+2
5 min read
Building Agentic AI Systems That Hold Up
Practical guidance on tool contracts, context engineering, evals, approvals, and telemetry.
6 min read
Which Query Transformation Techniques Actually Help RAG?
Query rewrite, decomposition, step-back prompting, HyDE, fusion, and when each one is worth the extra latency.
+2
5 min read
Preventing Hallucinations in LLM Systems
How to reduce hallucinations in LLM systems with better retrieval, abstention, verification, evals, and guardrails.
+2
5 min read
Most RAG Failures Start in the Documents
Chunking, titles, metadata, parent-child structure, reranking, and corpus QA for RAG systems.
+2
5 min read
Spec-Driven Development: the workflow I actually use
How I use a lightweight spec-driven workflow in real projects, what SDDRush automates, and where Kotef fits if you want a stronger agent layer.
+1
6 min read
How to Run LLM Evals in Production
How to run LLM evals in production with gold sets, graders, trace checks, online signals, and release gates.
+1
4 min read
Prompt Engineering: From Phrasing to Policy
Prompt design now means response formats, examples, tools, and eval loops, not incantations.
+1
4 min read
BI Storytelling That Actually Moves Decisions
How to make BI pages support decisions through narrative, visual hierarchy, and trust.
+2
8 min read
SYNAPSE: adaptive-control software engineering, prototyped
SYNAPSE was a 2025 framework for AI agents that adapt their own success criteria via MCDM. The deterministic-control-plane idea later shipped as Bernstein.
+1