Interesting!
In my experience using custom harnesses has worked better eg: Stripe etc all did it custom largely because of the sensitive integrations. How would you handle that?
We track the failure modes in production directly instead of relying on simulation. So if suddenly we are seeing a failure mode pop up too often, we can alert timely. In the approach of going from simulation to monitoring, I am worried the feedback might be delayed.
Doing it in production also helps to go run simulations by replaying those production conversations ensuring you are handling regression.
This comes from our architecture. Since we are aware of the agent's context our test agents know the incomplete flows and the assertions are per session.
If we miss some cases, there's always a feedback loop to help improve your test suite
Yes, we already support knowledge base integrations for BigQuery and plan to expand the set of connectors. You can always drop knowledge files currently.
Moreover, we even generate scenarios from the knowledge base
Training is an overkill at this point imo. I have seen agents work quite well with a feedback loop, some tools and prompt optimisation. Are you doing fine-tuning on the models when you say training?
To clarify you are using the "fast brain, slow brain" pattern? Maybe an example would help.
Broadly speaking, we see people experiment with this architecture a lot often with a great deal of success. A few other approaches would be an agent orchestrator architecture with an intent recognition agent which routes to different sub-agents.
Obviously there are endless cases possible in production and best approach is to build your evals using that data.