Notes

Notes on AI systems, retrieval, and the work that starts after the demo.

Practical writing on retrieval, evals, observability, constraints, and the engineering work that starts when the demo is no longer the hard part.

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.

DeliveryIsraelWorkflow
14 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.

RAGLegalReliability
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.

DesignSafetySecurity
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.

Design
6 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.

DeliveryTestingWorkflow
6 min read

Building Agentic AI Systems That Hold Up

Practical guidance on tool contracts, context engineering, evals, approvals, and telemetry.

Agents
7 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.

RAGRetrievalPrompting
6 min read

Preventing Hallucinations in LLM Systems

How to reduce hallucinations in LLM systems with better retrieval, abstention, verification, evals, and guardrails.

RAGReliabilitySafety
6 min read

Most RAG Failures Start in the Documents

Chunking, titles, metadata, parent-child structure, reranking, and corpus QA for RAG systems.

RAGRetrievalGrounding
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.

AgentsWorkflow
7 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.

EvalsReliability
5 min read

Prompt Engineering: From Phrasing to Policy

Prompt design now means response formats, examples, tools, and eval loops — not incantations.

AgentsPrompting
4 min read

BI Storytelling That Actually Moves Decisions

How to make BI pages support decisions through narrative, visual hierarchy, and trust.

BIStorytellingDashboards