Web Search Agents are expert web crawling and research agents for your specific domain (company enrichment, regulations research, etc.). They self-learn your use case to go deeper into the sources that matter most to you, giving your AI deeper and more relevant web context. To get started, give your AI this link: https://docs.nimbleway.com/agent-onboarding.md
@sansa_grey If you mean saving a configuration and reusing it for similar projects, that already works: an agent is basically a saved preset (sources, output schema, goals), so you can rerun it or clone it as a starting point for the next similar task, and there's a gallery of ready-made ones for common use cases.
if you meant something else, like presets for the CLI or SDK, tell me a bit more about the workflow you have in mind?
Love that each agent keeps memory of past runs and deprioritizes sources that burned it before, so reliability compounds over time instead of resetting on every query.
Dune
CONGRATS ON THE LAUNCH!!
Mastra
@dhanrajchoudhary THANK YOU!!1 😸
the future is now
Web Search Agents by Nimble
@michael_levinger damn right!
Floqer
Web Search Agents by Nimble
@shivam_mahajan1 thank you!!! what have you used web search agents for?
Buffup.AI
are there any plans to add customizable presets so we can quickly apply saved terminal configurations for different project types?
Web Search Agents by Nimble
@sansa_grey
If you mean saving a configuration and reusing it for similar projects, that already works: an agent is basically a saved preset (sources, output schema, goals), so you can rerun it or clone it as a starting point for the next similar task, and there's a gallery of ready-made ones for common use cases.
if you meant something else, like presets for the CLI or SDK, tell me a bit more about the workflow you have in mind?
Web Search Agents by Nimble
@sansa_grey @ella_sheer_engineer You can learn more about reusing web search agents here: https://docs.nimbleway.com/nimble-sdk/web-search-agents/quickstart
Love that each agent keeps memory of past runs and deprioritizes sources that burned it before, so reliability compounds over time instead of resetting on every query.
Web Search Agents by Nimble
@ilko_kacharov Exactly right! Learn how the self-learning mechanism works (at a high-level) in the diagram below!