Agent Reliability LabRequest a scope
Materials

Written as operators, not as a feed.

Short notes from the same practice that audits production agents. Filter by cluster without scripts: each cluster is its own page.

AllVerificationReliabilityLocal modelsAutomationWeb
Verification

2026-09-05 · 4 min · Verification

Why AI agents game their own tests, and how to isolate verificationAn agent that writes the test will pass it. Isolate the falsifier, allow BLOCKED, and stop treating a green self-report as a release signal.Read →
Automation

2026-09-05 · 5 min · Automation

A macro dashboard built by a multi-agent ensemble on DuckDBBeat rate is a first derivative. A DuckDB panel plus a three-family ensemble reads acceleration — with a falsifier on every scenario.Read →
Automation

2026-09-05 · 5 min · Automation

Multi-dimensional portfolio stress-testing against liquidity shocksVaR is calm-weather maths. A 12-by-6 shock matrix and a 60 percent margin ceiling show where a book dies in a liquidity event.Read →
Automation

2026-09-05 · 4 min · Automation

PWA and Telegram Mini Apps: mobile without the app storesA catalog, a booking flow, or a request form rarely needs an app-store cycle. One codebase can live as a PWA and a Telegram Mini App.Read →
Verification

2026-09-05 · 5 min · Verification

Silent no-ops and fail-plausible: when the system reports success and does nothingGreen dashboards and exit 0 are claims. Silent no-ops freeze data; fail-plausible agents invent a success report. How operators catch both.Read →
Verification

2026-09-04 · 5 min · Verification

How to verify an LLM answer: a verification layer that catches hallucinationsFluent is not true. Grounding, citations, an isolated judge, code for numbers, and a human on the high-stakes path — before a fabricated fact ships.Read →
Reliability

2026-09-04 · 4 min · Reliability

Why leads from your website never arriveAds are live, analytics looks healthy, the CRM is empty. The leak is usually the delivery chain from the form to the desk — not the traffic.Read →
Reliability

2026-08-31 · 5 min · Reliability

The chatbot went silent: debugging failures that produce no errorProcess up, logs clean, bot silent. Messenger bots fail without an exception. An external ping notices before a customer has to.Read →
Local models

2026-08-23 · 4 min · Local models

The price of privacy: local models vs API, in numbersA 24 GB card, a rental GPU, or an API: the invoice is not the decision. Data that cannot leave the room is.Read →
Local models

2026-08-23 · 5 min · Local models

What a local model can actually do: 75 business tasks, measuredTwo open-weight models on an office GPU, 75 office tasks, a code grader. Where a local assistant holds, where it invents, and what one rule changes.Read →
Automation

2026-08-21 · 4 min · Automation

An appointment bot that talks to the CRM in real timeA lead form collects a phone. An appointment bot reads live slots, locks one, and writes the CRM before anyone calls back.Read →
Web

2026-08-21 · 6 min · Web

What actually moves rankingsThere is no official table of 200 weighted factors. Google ranks a mix of relevance, honesty, and technical fitness — and punishes bought visibility.Read →
Web

2026-08-20 · 6 min · Web

Usability audit: what it finds and what it's worthA usability audit is a job-completion check, not a taste note. Formats are slice, funnel, or fixes — not a public price list.Read →
Reliability

2026-07-01 · 8 min · Reliability

AI Agent Drift: The Five Failure Layers, DiagnosedAI agent drift isn't one bug — it's five distinct failures in five harness layers. We run 10+ agents in production. Find the layer first, then fix it.Read →
Reliability

2026-07-01 · 6 min · Reliability

AI Agent Forgets Context Between Sessions — Why & the FixYour AI agent forgets everything between sessions because working memory dies at the session boundary. The three-case test for what to write down — and what not to.Read →
Reliability

2026-07-01 · 6 min · Reliability

AI Agent Infinite Loop: Fix the Death Spiral — Diagnose ItCursor or Claude Code agent stuck in a retry loop, editing the same file, burning tokens going in circles? Three signs, the math behind it, and a 4-rule fix.Read →
Verification

2026-07-01 · 6 min · Verification

AI Agent Says "Done" But Nothing Changed — Why & How to VerifyYour AI agent claims the task is done, but the file is unchanged and the test is red. Here's why agents over-claim — and how to measure the gap in 10 minutes.Read →
Reliability

2026-07-01 · 6 min · Reliability

How Big Should a .cursorrules / CLAUDE.md File Be?How big should .cursorrules, CLAUDE.md, or AGENTS.md be? Two numbers to measure today, the lost-in-the-middle myth tested, and a refactor that lifted task success 45%→72%.Read →
Verification

2026-07-01 · 5 min · Verification

The Verification Gate Your AI Agent Is SkippingStop your AI agent claiming 'done' on a broken build. A 30-line local check.py — lint, types, tests, smoke — that exits non-zero so 'done' has to be true.Read →
Reliability

2026-06-30 · 4 min · Reliability

Why an AI agent works one day and not the next: drift at the harness levelAn agent that worked yesterday can quietly do the wrong thing today. That is harness-level drift: the world moved, the instruction did not.Read →
Web

2026-06-26 · 4 min · Web

Website chatbot: template or customA widget covers FAQ and first-touch capture. A custom bot is the move when the catalog, the stock, or the slot grid has to be true.Read →
Reliability

2026-05-31 · 5 min · Reliability

AI, agentic system, autonomous agent: three levels of automation for an ownerAn owner who asks for AI may mean a chatbot, a scripted fleet, or a digital employee. Three levels, and which one to start with.Read →
Agent Reliability Lab
● Online