Rajiv Pant

A review of Richard Socher’s The Eureka Machine: scientific AI, experimental evidence, human judgment, and the work between prediction and discovery.

A review of Tiffany Xingyu Wang's The Trust Code: how AI earns trust, where human judgment matters, and what makes that judgment possible.

A real three-day upgrade with two AI vendors exposed the Built/Deployed Gap: controls and records that passed checks but never reached the running system.

A synthesis engineering pattern for staying in command of AI agents at speed: collect every decision they owe you into one honest, reviewable page.

A synthesis engineering story about Blind-Spot Rotation: how an AI reviewer with fresh context can find gaps the original inventory and checks missed.

Profile a computer, choose local open-weight models that fit, install them safely, and map exact artifacts to each machine with a reproducible workflow.

An AI agent's 'not found' is not 'does not exist.'

The thin instruction kernel: CLAUDE.md from 54,825 bytes to 21,026 with no rule weakened.

Why synthesis engineering exists: model, runtime, and state portability across Claude Code, OpenAI Codex, Cursor, Hermes Agent, and OpenClaw, without lock-in.

Ragbot and Ragenie, EA AI and chief-of-staff AI: why my executive assistant agent writes in its own voice while my chief of staff agent writes in my voice.

I documented why session-to-session agent messaging would fail, then built it six days later.

Tiered memory for a personal knowledge base: what MemGPT, Zep, and Mem0 teach about structuring two decades of notes so AI agents find the right ten files.

Enterprise workspaces hand you an account and take it back on departure.

Project state, methods, authority rules, coordination, and evidence: five things open agent infrastructure should preserve across AI tools and clients.

A green config is not a working agent.

AI agents as chief of staff: how I encoded absence coordination, notification tiers, send gates, and silent-failure validators into open-source config.

Removing names removes nothing; the scenario is the fingerprint.

A review of Jacques-Philippe Piverger's Inside Code: how values become everyday practice, what its framework offers, and where its claims need scrutiny.

AI review defaults to confirmation.

Honest labels for AI-assisted correspondence: three lanes that tell recipients whose words they're reading, from executive staff practice to Ragbot and Ragenie.

An AI agent deleted 474 files and its report was accurate.

A pre-commit guard printed its own failure and passed the commit anyway.

Name blacklists over-block your published biography and under-block real leaks.

Multi-agent AI coding creates failures solo sessions never see: a shared git index, one-shot briefs, report chains.

Three questions show why your AI coding assistant's built-in memory isn't a durable record — portable, synced, versioned — plus a worked audit proving it.

Google's knowledge-catalog repo shipped no standalone OKF validator, so I built a checker for the format's three hard rules.

Conversation, procedure, direct manipulation: why my AI setup runs three interaction modes over one substrate of plain files I own, not one chat box.

Your coding agent should watch its own work run: browser automation like Playwright turns 'it should work' into 'I watched it work' with evidence attached.

Where AI assistance ends and the writer begins: whose experience, whose position, whose voice.

Prompt discipline is engineering infrastructure: a forbidden-phrase catalog, hooks, and enforcement that catch AI coding agents dressing shortcuts as judgment.

A free, open-source tool that reads content along two axes: AI-provenance signal and slop-independence.

Multi-pass orchestrator, seven-layer hosted-tier safety, tools-router pattern, and the open-source license choices that keep a free LLM-mediated tool alive.

Why a methodology for detecting AI-generated content should keep the patterns it retires, not delete them.

A single CONTEXT.md carried an editor redesign across eight AI coding sessions.

A methodology tells practitioners what to do.

Reading Ragbot v3.3 (local Gemma 4 as first-class), v3.4 (the conversational-runtime release), and v3.5 (substrate cleanup) as one architectural arc — Ragbot becomes the conversational reference runtime of synthesis engineering.

The minimal patch is a habit from when understanding was expensive.

The technical fix was the easy part.

A silent sitemap regression after my Hugo-to-Astro migration degraded indexing for three months.

Introducing synthesis writing — the discipline of keeping the creative act of writing wholly human while letting AI help with the scaffolding.

When one end of a software contract is an LLM, Postel's Law isn't a courtesy — it's load-bearing.

Synthesis project management now works across Claude Code and OpenAI Codex by keeping durable project memory in CONTEXT.md, REFERENCE.md, and sessions.

Fitz and I went to Broadway to watch his second cousin Emmet Smith perform as Albus Potter in Harry Potter and the Cursed Child.

How I used Claude Code, the Wayback Machine, and AI vision to restore 16 broken images from a decommissioned Smugmug photo hosting service across 10 blog posts.

Ship every software product with built-in demo mode.

An open-source local tool that renders project management markdown and YAML as browsable, searchable pages.

You understand your AI-generated code.

Why a green test suite after a schema change should trigger suspicion, not confidence.

A practitioner guide to eliminating Claude Code approval prompt fatigue.

Every command an AI assistant proposes has a blast radius: the worst it can do if wrong.