How Hightouch built their long-running agent harness

Re:How Hightouch built their long-running agent harness by jasendo on Tuesday January 20, 2026 @03:57PM (#46697657)

We've been working on a similar problem, but went the route of pushing this into the model and runtime layer instead of the orchestration layer. Less scaffolding, more baked into how the model reasons. Happy to share more if useful

[ Parent | on HN ]

Re:How Hightouch built their long-running agent harness by thecr0w on Tuesday January 20, 2026 @04:03PM (#46697720)

yeah actually would love to hear more. what problems have you been working on, what did you try, and tell me more about the solution. Super curious.

[ Parent | on HN ]