Building TBN Protocol — trust and identity layer for AI agents. Think HTTPS but for bot-to-bot communication. Founder at Hardin AI Solutions. https://tbn.hardinai.co.uk
When you have multiple AI models running together like this, how do you handle
inter-agent trust? Does Claude verify Codex's identity before accepting its output?
Interesting approach to grading agent APIs. Have you considered the trust layer between agents?
Grading the API is one thing but verifying the agent calling it is who it claims to be is still
an unsolved problem for most deployments.
One thing missing from most local agent setups is identity verification between agents.
How do you handle trust when one agent needs to verify another is legitimate before sharing data?
This is exactly why we need trust infrastructure at the protocol level.
Agent-to-agent identity verification is still unsolved - most deployments
just assume the other agent is who it says it is.
Interesting timing - I've been working on something complementary to this.
TBN Protocol focuses on the identity and trust layer between agents themselves
(cryptographic certificates, verified handshakes) rather than the database layer.
The two could work well together. What's your approach to agent identity verification?