AGENT HARNESSES ARE THE NEW GPT WRAPPERS What exactly is an agent harness? A harness does 4 things: 1. Runs the model in a loop so it keeps working step after step instead of answering once and stopping. 2. Gives it hands to read files, call tools, open portals, and run code. 3. Manages its memory so hour three of a job still knows what happened on hour one. 4. Enforces the rules about what it can touch and when it has to stop and ask a human. WHY IT'S INTERESTING - The market is MEGA. I think about it like a wrapper let you sell software ($800B market) but a harness lets you sell the work ($5T+ market)! - It doesn't depend on any one company's model. The knowledge about the job lives in the harness, so you can run GPT today, Claude next month, an open model like Google Gemma, Qwen, Deepseek etc on your own machine after that, and it keeps working. A wrapper was one model doing everything and a harness is a router. - It gets better the more you use it. See, every correction a human makes becomes a rule the harness keeps, so what you have after 500 jobs is a completely different product than what you had after 5. Wrappers only got better when OpenAI got better. - You can charge for finished work! The harness knows when a job is done, so you can price per claim, per filing, per review, per resolved exception, or per closed month. This helps compete with SaaS! - Most jobs are just the same handful of decisions, repeated, using the same few tools. That's true for most of the 800+ occupations out there, which is why almost all of them could have a harness built for them. Lots of space for startups to be building. -The frontier labs won't come for these. OpenAI is not going to learn how a freight claim gets denied in Rotterdam or which prior auth your specific payer rejects. Those markets are too small for them and the knowledge only exists inside the job. They'll keep making the models better, which just makes your harness better which is cool. - OH, AND really important, you can ACTUALLY build one now. OpenAI's Agents API, Claude's managed agents, Vercel's eve, LangChain harness framework etc. They all make it way easier to build agent harnesses. Agent harnesses truly are the new GPT wrappers. This is just the beginning.

I think building a crowd sourced niche dataset is one of the most UNDERRATED bootstrapped businesses in the AI AGE: (think LevelsFYI, Glassdoor, Zillow etc but for any niche) 1. Your users build it for you by adding their own data (it gets more valuable with every entry) 2. AI agents now need clean, trusted data to make decisions, and they'll pay to query it on repeat 3. Cloudflare (and others!) are building the rails for agents to pay per query, so this becomes real recurring revenue 4. One dataset sells to many buyers at once: consumers, companies, and now agents 5. Charge three ways from the same data: free for contributors, paid for pros, API access for the agents 6. The narrower the niche, the more defensible it gets (you own a corner nobody else has) 7. Frontier models are hungry for data (and are a great customer) 8. The wedge: give a teaser amount of data, then make people add theirs to unlock the rest (ask for data or email) 9. LevelsFYI was brilliant because people will hand over their own salary just to see what everyone else makes (human nature) Big fan of these types of businesses in the AI age. Low risk, high margin, and they get stronger the longer they run!