ZeNorm
Blog

Notes on building software with AI agents

What actually breaks when you hand implementation to a coding agent — context loss, the last 30%, specs that drift, tests that verify nothing — and what to do about it.

0110 min read

Context engineering for coding agents

What to put in an agent's context window and what to keep out: project instructions, retrieved code, the task spec, and history you barely control.

AI Coding AgentsContext EngineeringSpecsEngineering Practice
028 min read

Planning mode vs. just prompting

When making an agent plan before it writes code pays for itself, when it is pure ceremony, and what separates a useful plan from a restated prompt.

AI Coding AgentsPlanningSpecsEngineering Practice
038 min read

Acceptance criteria that actually work

Treat acceptance criteria as executable contracts, not prose wishes. What makes a criterion verifiable, plus a rewrite table of common bad ones.

SpecsAcceptance CriteriaAgent Workflow
049 min read

Drift between the spec and the code

The doc says one thing, the code does another, and nobody notices until an incident. Why agents make it worse, and what you can actually detect.

SpecsDocumentationAI Coding Agents
0511 min read

How to write specs for coding agents

A practical guide to specs an LLM can execute — non-goals, verifiable criteria, named interfaces, and decisions with rationale that survive review.

SpecsAI Coding AgentsAgent Workflow
069 min read

AI-generated tests that verify nothing

A taxonomy of tests that pass without checking anything, why agents produce them, and the one heuristic that catches all five kinds in review.

TestingAI Coding AgentsCode Review
078 min read

ZeNorm vs. AWS Kiro

Kiro closes the loop inside its own IDE with click-through approvals. ZeNorm gates on a score and hands off to your agent. A mechanism comparison, honestly.

Tool ComparisonAI Coding AgentsSpecsAgent Workflow
089 min read

ZeNorm vs. GitHub Spec Kit

Spec Kit is free MIT-licensed prompt templates run by your own agent. ZeNorm runs a server that refuses. A mechanism comparison, and when Spec Kit wins.

Tool ComparisonAI Coding AgentsSpecsAgent Workflow
097 min read

ZeNorm vs. Traycer

Traycer plans and reviews inside your editor. ZeNorm refuses to emit tasks until the spec scores. A mechanism-level comparison, with when to pick Traycer.

Tool ComparisonAI Coding AgentsSpecsAgent Workflow
109 min read

The 70% problem in AI-assisted coding

Why agents get a feature 70% done in minutes and the last 30% takes longer than writing it yourself — and what to do about it.

AI Coding AgentsAgent WorkflowSpecs
1110 min read

Code review when an AI wrote the code

Reviewing agent-generated code is a different job from reviewing human code. Most teams run the human process against it and get burned.

Code ReviewAI Coding AgentsEngineering Practice
1210 min read

Why AI coding agents lose context

The mechanics of context loss in long agent sessions — what gets evicted, why compaction is lossy, and what actually survives a session boundary.

AI Coding AgentsContextAgent Workflow
139 min read

Scoping work for AI agents

How to size a task so a coding agent can finish it coherently: decision count over line count, vertical slices over layers, and dependency order.

AI Coding AgentsTask DecompositionSpecsEngineering Practice

Browse by topic

Product updates

All updates