laul_pogan

5 karma · joined June 7, 2022

laul_pogan··on DeepSeek Harness developer preview

Trying it now, seems a little sloppy...

laul_pogan··on Show HN: Ingot, evidence-gated optimization and version control for agent skills

Hi, I'm Paul- James and I built Ingot because skill changes felt like copy-paste, and are difficult to track across large orgs. Ingot versions them and requires human review. It can also optimize them using real agent traces. We'd love to know how others are solving the skill control & versioning problem

laul_pogan··on Agent-talk: Enabling coding agents to work together

My tool has a public-good relay and the ability to chat between environments, so it's important to resolve ID to operator or company

laul_pogan··on 1Password for Claude: Give Claude access without giving up your credentials

Oh wow! I had no idea. Even with a service worker? I'll switch over to this- it works just as well for insertion and .env replacements in claude code?

laul_pogan··on 1Password for Claude: Give Claude access without giving up your credentials

How is this different than OP CLI with a service account?

laul_pogan··on Launch HN: Traceforce (YC S26) – Company-wide security monitoring for AI apps

Hey Xia! Super excited for this- good talking to you a few weeks ago and best luck with the launch :)

laul_pogan··on Agent-talk: Enabling coding agents to work together

I find that the real problem tends to be identity and trust across sessions- ideally there are ways to enable zero-knowledge trust between two agents in different environments.

I develop a similar tool open source tool called wire (wireup.net) https://github.com/SlanchaAi/wire