Sydney Runkle's banner

Sydney Runkle

@sydneyrunkle • 14,754 subscribers

product + open source @LangChain

Shorts

instead of generating text, jev from TypeSafe AI generates structured output this makes it great for classification tasks like model routing, tool selection/search, and guardrails of many forms! it's also ridiculously fast and cheap compared to LLMs doing the same tasks

instead of generating text, jev from TypeSafe AI generates structured output this makes it great for classification tasks like model routing, tool selection/search, and guardrails of many forms! it's also ridiculously fast and cheap compared to LLMs doing the same tasks

52,876 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

here's a quick breakdown of TypeSafe AI's new jev model: what it is, and how to plug it into your agents!

here's a quick breakdown of TypeSafe AI's new jev model: what it is, and how to plug it into your agents!

69,388 Aufrufe • vor 1 Monat

if you give your agent a browser, it can do work on the web, even on sites w/ no agent native APIs! in this demo my agent books dinner reservations for me. i only had to log into the reservation site once; it saved my login and acts on my behalf for every new session!

if you give your agent a browser, it can do work on the web, even on sites w/ no agent native APIs! in this demo my agent books dinner reservations for me. i only had to log into the reservation site once; it saved my login and acts on my behalf for every new session!

11,364 Aufrufe • vor 11 Tagen

new in langgraph: interrupts with typed response schemas! when your agent pauses for a human, you define what a valid response looks like: 1. responses are validated before they're passed back to the agent 2. you can render a real response form in your UI, not just a json entry field human in the loop, but (type) safe docs:

new in langgraph: interrupts with typed response schemas! when your agent pauses for a human, you define what a valid response looks like: 1. responses are validated before they're passed back to the agent 2. you can render a real response form in your UI, not just a json entry field human in the loop, but (type) safe docs:

18,339 Aufrufe • vor 1 Monat

not every task needs a frontier model! we built a model router into our coding agent's harness and cut costs by 64% w/o reducing quality. this vid walks through how it works, and how you can build one into your own harness!

not every task needs a frontier model! we built a model router into our coding agent's harness and cut costs by 64% w/o reducing quality. this vid walks through how it works, and how you can build one into your own harness!

12,620 Aufrufe • vor 1 Monat

this blog covers 6 common workflow patterns we see with dynamic subagents (fanout and synthesize, adversarial verification, etc) if you'd prefer to learn w/ a video, check out this excellent guide from Colin Francis with examples and trace walk throughs!

this blog covers 6 common workflow patterns we see with dynamic subagents (fanout and synthesize, adversarial verification, etc) if you'd prefer to learn w/ a video, check out this excellent guide from Colin Francis with examples and trace walk throughs!

20,047 Aufrufe • vor 4 Monaten

Keine weiteren Inhalte verfügbar