"Interloom's core product is what it calls a Context Graph: a continuously evolving model of how operational decisions actually get made inside a given organisation, constructed by ingesting millions of real cases, support emails, service tickets, call transcripts, work orders, and extracting the patterns of how expert workers resolve problems."
"The agent might be technically capable. It can read documentation, follow instructions, and execute steps. What it cannot do is replicate the judgment of the person who has been doing the job for fifteen years and knows, from experience, exactly why the standard playbook does not work on Tuesdays in the logistics department."
"Jakobi estimates that around 70% of operational decisions are never formally documented, highlighting the challenge of capturing tacit knowledge that is crucial for effective decision-making."
Interloom is a Munich startup creating a Context Graph, a dynamic model that maps operational decision-making based on real cases rather than undocumented knowledge. Many AI deployments struggle to replicate the nuanced judgment of experienced employees, as much of their expertise remains unwritten. Interloom's product ingests various data sources to identify patterns in how expert workers solve problems. The company recently raised $16.5 million in a seed round, significantly increasing its funding from an earlier $3 million seed round.
Read at TNW | Startups-Technology
Unable to calculate read time
Collection
[
|
...
]