Not saying this is AI-gen but it's very dense and doesn't read like something I could glean info from easily
ai-literacy-superpowers is a set of plugins for agents, this text is not even meant for human consumption.
Harness Engineering
31–40 of 47 posts
Re: Harness Engineering
#32Earlier quoted context omitted.
Here's a better summary: https://github.com/rush86999/atom/blob/main/docs/architectur... I also have a self-evolving architecture on it, but you have to be careful, especially if you're using multiple models (still WIP).
That looks like a “Deep Research” report generated by an LLM, not a summary.
Yeah, it is. Bad wording on my part, but the list is a summary of what's going on so far in agent harnesses.
Re: Harness Engineering
#33Is Harness Engineering the new Prompt Engineering?
Re: Harness Engineering
#34What’s the best current practice if we want to enable agent code review and approval of GitHub PRs but only for specific users?
Maybe code owners? I'm not sure if it'll do exactly what you want; but you can say that "such and such" files must be edited, or reviewed, by specific users.
Then, if someone opens a PR who isn't one of those people listed, it requires them to be a reviewer.
We use it for .editorconfig; specifically, we don't want a newcomer to come in, not like a style rule, and slip in a change.
Re: Harness Engineering
#35Earlier quoted context omitted.
The Agent/harness has no meaningful distinction. The backing model(s) can only read through a harness. Call it an agent, call it a tool, call it a library. They are all harnesses if they are backed by a model. Broadly speaking, - Copilot only reads AGENTS.md - Codex reads AGENTS and CONTEXT - Claude reads CLAUDE This ai-literacy is noise, muddling the definitions and suggesting yet-another-md-file.
I put everything in CONTRIBUTING.md, and then put "See: CONTRIBUTING.md" in those vendor-specific files.
I just symlink each file to one master
Re: Harness Engineering
#36It’s fascinating to live through a the emergence of a new technology and to see people trying to make sense of it as they go. I personally think that a lot of the words used around AI, harness, SKILLS, agents, RAG.. are make up words or close to it, words that do not have profound semantics, even though people are trying to, often after the fact, make sense of them. It’s just popular words that are different enough t…
Hear hear! We techies are bad at naming things. "NoSQL" is probably a top contender there.
I give you "serverless" which is on someone else's... server.
Re: Harness Engineering
#37definitely a little bit of shameless self promotion but I write about a lot of common harness concepts in the docs of Wingman (https://wingman.actor) - a client agnostic agent harness I've been working on for a while:
https://docs.wingman.actor/concepts/sessions/
I think there is still plenty of innovation to be had in the space. Right now everything is still pretty bundled to the file system where getting skills and things to work inside of like a virtual worker requires simulating a virtual file system (usually). I believe even in the latest opencode v2 versions it still requires that a session be bundled to a working directory, I try to avoid (some of) that in Wingman.
Re: Harness Engineering
#38The term harness engineering does not come from Birgitta Boeckeler's article in martinfowler.com. It was first used by Mitchel Hashimoto months earlier in his 'My AI adoption journey' blog post [1], and immediately picked up by OpenAI [2] a week later. Also worth noting that this text is not only entirely AI generated, but meant for other agents to read , not us humans. [1] https://mitchellh.com/writing/my-ai-adoptio…
The site looks like aislop after skimming through 10 of his docs on the site, and the mistake you pointed out.
Something feels off, and claims on the site do not seem credible. Def not manually verified. If it was verified, the author did not go deep enough to give credits where it's due.
The only thing I got out of the site was to see terms I never heard of.
Re: Harness Engineering
#39The term harness engineering does not come from Birgitta Boeckeler's article in martinfowler.com. It was first used by Mitchel Hashimoto months earlier in his 'My AI adoption journey' blog post [1], and immediately picked up by OpenAI [2] a week later. Also worth noting that this text is not only entirely AI generated, but meant for other agents to read , not us humans. [1] https://mitchellh.com/writing/my-ai-adoptio…
Honestly it would be helpful for someone to collect a list of these articles and concepts in a single location for engineers to get up to speed on these concepts. I think that is the only advantage of this AI generated website at the moment.
Re: Harness Engineering
#40The term harness engineering does not come from Birgitta Boeckeler's article in martinfowler.com. It was first used by Mitchel Hashimoto months earlier in his 'My AI adoption journey' blog post [1], and immediately picked up by OpenAI [2] a week later. Also worth noting that this text is not only entirely AI generated, but meant for other agents to read , not us humans. [1] https://mitchellh.com/writing/my-ai-adoptio…
the one by https://earendil.com/posts/what-is-a-harness/ is also a good read
and if you want to see what a simple harness implementation looks like you can just dive into the code and ask your favorite agent about it