Harness Engineering vs Spec-Driven Development
What harness engineering means for AI coding agents, how it differs from spec-driven development, and how to run both.
Topic: AI Coding
A focused archive of AI Coding articles for spec-first teams.
Spec-First Workflow for AI Agent Teams
A five-stage spec-first workflow for teams running AI coding agents: spec packets, bounded tasks, write scopes, evidence gates, and PR review that scales.
MCP Server API Contracts for AI Agents
Write API spec contracts for MCP servers: input schemas, output shapes, error taxonomies, idempotency flags, and versioning that AI agent clients can rely on.
OpenSpec vs Superpowers vs Spec Kit: Compare and Combine
OpenSpec vs Superpowers vs Spec Kit, checked Sep 2026: what each one owns, how to combine them, and which to start with.
AI Coding Spec Packet Before Code Generation
A copy-ready packet for giving AI coding tools a bounded task, acceptance criteria, file ownership, tests, and review evidence before code generation starts.
Spec Skills Case Study: From Ticket to Spec
Follow a vague support ticket as it becomes a shippable technical spec using Spec Skills, guided questions, and review-ready output.
Spec Skills and Spec-First Delivery
See how Spec Skills fits spec-first delivery through constrained prompts, spec injection, boundary enforcement, and reviewable AI output.
Superpowers for Spec-First AI Coding
Superpowers enforces spec-first discipline for AI coding agents through brainstorming, specs, plans, TDD, verification, and repeatable review evidence.
AI Coding Prompts That Follow Specs
AI coding tools drift without constraints, adding fields, renaming functions, expanding scope, and inventing tests. Spec-first prompts keep changes reviewable.
AI Coding Governance with Spec-Driven Prompts
Govern AI-assisted coding with spec-driven prompts: define scope, boundaries, evidence, and audit trails before generated code reaches review.
AI Coding PR Review with Acceptance Criteria
Review AI-generated pull requests against acceptance criteria: inspect the diff, run evidence checks, and catch failures a quick skim misses.
AI Coding Risk Register Before Merge
Use a pre-merge risk register for AI-generated code: flag auth, data, contract, migration, rollback, and observability risks.
AI Coding with Test-Evidence Gates
Use test-evidence gates for AI-generated code: require meaningful tests before merge and catch hallucinated implementations before release.
Designing API Specs for Agentic Clients
Design API specs for LLM-powered agentic clients with discoverable fields, idempotency, dry-runs, semantic descriptions, and safe destructive actions.
Quality Gates for AI-Assisted Development Specs
Quality gates for AI-assisted code: pre-prompt spec checks, diff review, test evidence, and human sign-off before generated code ships.