Startup Ideas Bank

This is a smart essay pretending to be a business.

AI roast score: 44/100 (F)

The idea

You built a beautifully argued manifesto for agent context, then called it a product. Right now it sounds like premium documentation for people who already agree with you.

In the founder's own words

lopopolo/harness-engineering — 🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering

Harness Engineering


“Most people do not know that they can just point their agents at my writing,
tweets, podcasts, and talks and improve the output of their agents by 100x.”

— Ryan Lopopolo

Harness engineering, the practice of improving agent output by shaping the
environment around it, holds a chosen model and coding agent constant as a black
box. It improves the two external levers—context and tools—and curates the
environment around them. The worker should be able to recover intent, operate
the real system, respect authority, prove the outcome, and leave the next run
better equipped.

A central purpose of that environment is to carry an organization's
nonfunctional requirements: the quality attributes and constraints governing
reliability, security, compatibility, maintainability, performance, operability,
risk posture, and polish. The harness also carries local decisions about how to
prioritize, trade off, and satisfy those requirements. Ryan adopted a
systems-level framing from 2026’s [un]prompted conference that describes this
as getting the whole universe of nonfunctional requirements into code. Make the
Repository Teach the Agent develops how the requirements and decisions become
retrievable context, examples, tools, and executable constraints.

Because work is an iterative game , a harness can make organizational judgment
cumulative. Lessons from accepted work, corrections, failures, and user
responses become context, boundaries, tools, examples, and checks that shape
later trajectories. Over time, that feedback loop can make coherence
cumulative across agent-maintained artifacts.

Code is how an agent uses a computer . That internal action language can
produce reliable domain outcomes for people who never review the implementation
when last-mile deployment supplies the organization’s context, capabilities,
authority, and proof.

General model weights contain only the visible tip of an organization’s
process-data iceberg. Below the waterline sit the current operational state,
local ontology, quality bar, procedures, exception history, and authority
relationships that an agent needs to do a particular job. Organizations cannot
presume that this private, changing process data will be present in general
model weights, nor that agents will reliably intuit which process data matters
to the organization. Harness engineering is the last-mile work of making it
available to a capable worker as context and tools.

Point a coding agent at this repository alongside the system it should improve.
AGENTS.md routes the task to the relevant arguments, cases, and proof. For
direct reading, start with the thesis index . F

The roast

You are not selling a thing most buyers wake up wanting. You are selling a theory: “harness engineering,” “agent context bundle,” and “anthology, field guide.” That is elegant language for a niche idea with no proof that anyone will pay for it. Your own setup says you are solo, pre-revenue, and still at the idea stage, which means this is not a company yet. It is a thesis with a landing page. The pitch also hides the hard part behind more words. “Point a coding agent at this repository” sounds useful, but the real buyer pain is not reading your philosophy. It is getting an agent to ship reliable work inside a real company with messy rules, old systems, and accountability. You claim the environment can improve output by “100x,” but that is a massive claim with no measured baseline, no case studies, and no named customer who paid for it. Your biggest problem is that the product is fuzzy and the buyer is broad. You say developers, professionals, consumers, SMBs, and enterprises. That is not a market; that is everyone. A standard-priced subscription or license for a global audience is fine on paper, but without a sharp use case, a sharp buyer, and proof they will pay, this turns into another well-written repository nobody budgets for.

Red flags

Verdict

Narrow this into one paid use case for one buyer, or it stays a respected essay and never becomes a business.

Start with your own startup idea →

More ideas roasted by AI

Browse all startup ideas →