For me the prerequisite for leveraging openclaw was developing function oriented repositories of markdown files tied to my roles that capture pretty much everything I know about the subject and ongoing work, and working with agents as assistants off of those as context. As a founder, product manager, for growth etc.
From there it’s pretty natural that I wanted to talk to an always on agent not tied to any particular machine which has the same context plus access to google drive etc.
One thing that I'm sure of is that the agentic future is test-driven. Tests are basically executable specs the agent can follow and verify against.
When we have solid tests, the agent output is useful and we can trust it. When tests are thin or missing, the agents still ship a lot of code, but we spend way more time debugging and fixing subtle bugs.
This is why I think they work so well with strongly typed languages like Haskell and OCaml. You say do this until it compiles and passes a set unit tests for business logic. I find I am using even more verification tools like JSON schema validators. The more guardrails and hard checks you give an agent, the better it can perform.
Great, so now I have to design the API for the AI, think of all the edge cases without actually going through the logic, and then I'm invariably going to end up with tests tightly coupled to the implementation.
Like any CLI Claude Code should follow decades old tradition of providing configurable verbosity levels, like tcpdump's -v to -vvvvv to accommodate varying usage contexts.
I refuse to believe that. The Linkedin cringe is from posts that are optimised to go viral on Linkedin (consciously or not); no-one writes in that style sincerely.
i think there's two main flavors of linkedin slop.
there's the founder/ceo trying to brand themselves as a "thought leader" slop. stupid made up inspirational stories. grind/hustle motivational stuff. etc.
then there's the slop from employees. this is usually a multi-paragraph missive where they announce that they've made the hard to decision to leave company X for company Y but they learned SOM MUCH and everybody at company Y are ABSOLUTE ROCKSTARS and on and on and you just wonder "if all that's true, why are you leaving"
LinkedIn cringe comes from people imagining situations to align with a certain narrative and writing it in a way they think how it'd look like if it came from the heart.
When’s the last time your heart told you to post “today I went for an interview. [insert bullshit here] I was rude to a passerby’s dog. [more bullshit] The dog was the interviewer.”?
LinkedIn slop has a certain smell to it like no other spam does. I’m still puzzled as to why anyone does it - *surely* everyone from the cohort you wish to attract is familiar with it and sees right through it? Even for marketing positions I don’t see how this can translate to other, actually-profitable venues since this kind of content wouldn’t work anywhere else.
Same as the rest of the corporate world. LinkedIn sloppers hire LinkedIn sloppers until the only way to get into <insert high paying company / industry> is to post about your "experiences" like - "I was late for the interview because I saw a homeless dog outside and went to get it some food and sit to ask about its day [more bullshit] Half way through the interview the dog came in - turns out they were the CEO."
From there it’s pretty natural that I wanted to talk to an always on agent not tied to any particular machine which has the same context plus access to google drive etc.
reply