> Disclaimer: this proves integrity, not completeness (as a self-held chain proves nothing was edited but does NOT prove that nothing was omitted).
Or as the page puts it in more detail:
> A self-held chain proves integrity: nothing was edited or reordered after the fact. It cannot prove completeness: the operator of a recorder can delete the bad day and re-seal the chain, or never write a record at all, and the chain stays internally consistent.
I don't get this. If I "hold" the "chain" (I hate the jargon agents invent), why can't I edit or reorder and then "re-seal" it?
brian_kuan 5 hours ago [-]
[dead]
brian_kuan 7 hours ago [-]
PS: please try to break it - if you find that the report does not catch a deleted line, changed number, or modified record, I'd love to know!
And to start a discussion: if you sell or buy AI agent products, what do security reviews ask about them?
mdellison 3 hours ago [-]
I've been working in the same lane. The vendor uses the same technique that academic preregistration uses in experiments. No audit firm/institution/organization needed. The customer just compares what was delivered against what was pre-committed. This way if something is off, it doesn't just show up as nothing... it shows up as a gap.
brian_kuan 2 hours ago [-]
Very cool! Heard on all of that - IMO you didn’t remove the witness, but instead distributed it so that every customer becomes their own witness. The catch is pre-committing catches declared-but-missing, but not the thing nobody put on the list, which is the case security teams fear most.
Would love to hear more about what you’re building!
all2 7 hours ago [-]
I'm currently working on an agent framework that has auditability as one of its core promises. I'm glad to see others are working in this domain!
I've seen other products/apps in this space farther up the stack at the API boundary.
What frameworks does your package work with? How does it handle intercept?
brian_kuan 6 hours ago [-]
There's no interception - it runs in-process, so it works with any Python code (with or without a framework). There's a TS version too if your stack is in JS.
Would love to hear more about your agent framework!
all2 6 hours ago [-]
I don't want to hijack your thread. My email is in my profile, I'd be glad to shoot you an in depth description of what I have so far.
brian_kuan 5 hours ago [-]
Sending you an email now!
ambicapter 6 hours ago [-]
> may have built observability dashboards and audit logs, but those are editable and partisan
Why would these be editable?
brian_kuan 6 hours ago [-]
Because they live in infrastructure the vendor itself controls - there's some conflict of interest there. Things like retention, rotation, deletion, what gets included/excluded, etc are all decisions the vendor makes. Same reason why compliance requires audits!
The hash chain doesn't make the log unwritable, it makes any edit detectable.
rmonvfer 5 hours ago [-]
Could I monitor something like Claude Code or Codex with this?
Why a Python library instead of a completions API proxy?
brian_kuan 5 hours ago [-]
Proxies are blind to sensitive things enterprises might worry about (eg. the agent read a database, wrote a file, sent an email, etc) as those happen in the agent's own code. That said, if you already run a gateway, its logs can be ingested into the same chain.
nf-x 7 hours ago [-]
Looks very slop, but it’s a good idea. The main difficulty is that no big name is hosting a witness.
brian_kuan 6 hours ago [-]
Fair point - I am a marketer by training and built this with some help from Claude! But appreciate the love.
If you find something/have feedback, please let me know and I'll gladly fix it.
Separately - 100% agree on the witness - only someone/thing outside the vendor can prove nothing was omitted. Who do you think fills that gap - is it an audit firm (my world), a standards body, or something else?
3 hours ago [-]
Rendered at 02:50:39 GMT+0000 (UTC) with Wasmer Edge.
Or as the page puts it in more detail:
> A self-held chain proves integrity: nothing was edited or reordered after the fact. It cannot prove completeness: the operator of a recorder can delete the bad day and re-seal the chain, or never write a record at all, and the chain stays internally consistent.
I don't get this. If I "hold" the "chain" (I hate the jargon agents invent), why can't I edit or reorder and then "re-seal" it?
And to start a discussion: if you sell or buy AI agent products, what do security reviews ask about them?
Would love to hear more about what you’re building!
I've seen other products/apps in this space farther up the stack at the API boundary.
What frameworks does your package work with? How does it handle intercept?
Would love to hear more about your agent framework!
Why would these be editable?
The hash chain doesn't make the log unwritable, it makes any edit detectable.
If you find something/have feedback, please let me know and I'll gladly fix it.
Separately - 100% agree on the witness - only someone/thing outside the vendor can prove nothing was omitted. Who do you think fills that gap - is it an audit firm (my world), a standards body, or something else?