> - Rubric based grading to guarantee you (for instance) don’t leak PII accidentally That does not sound like a "guarantee", at all.
once your team comes to a consensus on what PII is, you can roughly guarantee it... especially as models improve.
Show HN: Gambit, an open-source agent harness for building reliable AI agents
31–33 of 33 posts
Re: Show HN: Gambit, an open-source agent harness for building reliable AI agents
#32Earlier quoted context omitted.
So two things. 1/ crypto signing is totally the right way to think about this. 2/ I'm limiting prompt injection by using chain of command: https://model-spec.openai.com/2025-12-18.html#chain_of_comma... we have a "gambit_init" tool call that is synthetically injected into every call which has the context. Because it's the result of a tool call, it gets injected into layer 6 of the chain of command, so it's less likel…
Injecting context via tool outputs to hit Layer 6 is a clever way to leverage the model spec. The gap I keep coming back to is that even at Layer 6, enforcement is probabilistic. You are still negotiating with the model's weights. "Less likely to fail" is great for reliability, but hard to sell on a security questionnaire. Tenuo operates at the execution boundary. It checks after the model decides and before the tool…
yaaaaa exactly. You're totally on the same wavelength as me. Let's be friends lol
Re: Show HN: Gambit, an open-source agent harness for building reliable AI agents
#33also, it seems like this works with openrouter, and perhaps OpenAI -- what about Gemini API?
thanks for the PR! :)