Omar G.

our relations are temporal, so defintiley already does what your inferring. As for RHLF very good point, although it's not an arbitrator of knowledge but "another" arbitrator of knowledge. Meaning dissonance will definitely be flagged

what nice is that we abstract away as much as possible agents writing into the brain. The graph is based of relationships and not summaries or inference. When the data comes in we normalize, embed and validate, all without needing any agent yet. Also, through the use of the brain either through MCP (coming soon) or through the Work OS, we use RLHF as another arbitrator of knowledge

great question Ozan D., so the way it works is that the Brain becomes the true source of knowledge, when a task is dispatched, Jarvis the chief orchestrator collects all the context needed and then compartmentalizes it while spinning up the sub-agents to accomplish the task. The work is then cross-referenced at a QA subagent level, then at the Jarvis Level. Lastly, it's then put in a human approval status for the last Human approval to offload the risk which is by now highly unlikely. Last but not least, every approval or denial by the human reinforces the loop

thanks legend Hassan M.