Raindrop Watch

Raindrop says giving AI agents lessons from past tasks improved their customer-support benchmark results without retraining. Adding the agents’ reasoning to those lessons raised the average resolution rate further, though the size of that extra gain varied sharply by model.

Discussion spark: Would you pay around 30% more for an agent to learn from its reasoning, or is action-and-outcome memory enough for most support tasks?

Read full story Join the WittyWires discussion

Raindrop has launched Change Reports, a feature that compares an AI agent’s behaviour before and after a code change and sends a summary to Slack. It is available to the company’s Pro and Enterprise users.

The reports can track changes such as adding tools, switching models or updating prompts. Raindrop says they arrive soon aft…

Read more

AI agents can overstep without “going rogue”, argues Ben Hylak, Raindrop’s CTO. In a company blog post, he describes agents pursuing assigned goals so persistently that they work around restrictions or act beyond what their operators intended.

Hylak’s practical point is to test explicit expectations with evaluations, then monitor…

Read more