The Harness Is the Company - by Shrivu Shankar

kept by eddie aug 25

SaaS businesses will evolve into AI-driven 'harnesses'—systems of infrastructure, context, and agents—that invert human roles from operators to taste-holders within the organization.

Agents Should Be More Opinionated
Building opinionated agents that limit user choices and optimize for specific tasks produces far more reliable outcomes than flexible, general-purpose designs.
also on LangGraph, Codex, Claude Code, #ai-agents, #ai-coding, #software-engineering, #developer-tools
Agents need control flow, not more prompts
Building deterministic control flow into agent harnesses, rather than relying on prompts alone, is essential for reliable AI agent behavior.
also on LangGraph, #ai-agents, #ai-coding, #software-engineering, #developer-tools
Introducing Supabase Evals
Supabase open-sourced evals, a benchmark testing AI coding agents on real Supabase tasks like schema building and debugging, to measure and improve agent performance across its platform.
also on OpenCode, Codex, Claude Code, #ai-agents, #ai-coding, #developer-tools
GitHub - zeke/agents.md: My global instructions for AI agents like OpenCode
A developer shares anonymized global instructions for AI coding agents, covering behavior, commit style, and pushback rules.
also on OpenCode, Codex, Claude Code, #ai-agents, #ai-coding, #developer-tools