Steverse

Build, test, monitor Agentic AI and be done.
LangChain, LangGraph, LangSmith.

[Steverse @Steverse7]

@hwchase17 async agents imitates humans really well.

[Steverse @Steverse7]

@sydneyrunkle I think people in different locations have different mindsets. In some locations people think in a binary way, in others people think with more results to the issue. Will agents influence how people decide?

[Sydney Runkle @sydneyrunkle]

https://t.co/ET7YEMT4Bz

[Steverse @Steverse7]

Why does every org need their own agent? @hwchase17 explains.

Could an agent framework become the IP of an org?

[LangChain @LangChain]

.@hwchase17 kicked off Interrupt London with a keynote on where agents are headed, and why every org should own their intelligence.

🔴 Full talk: https://t.co/4K7KoeiHlb

⏯️ Every session, on demand: https://t.co/hL8WUWHbjG

[Steverse @Steverse7]

@rosslazer IMO You can build Grok @bot or @Muse for less cost and faster time with @LangChain, if you have a solid team and infra.

[Steverse @Steverse7]

@hwchase17 I think every professional website will have ready-to-use MCP with skills. That way every business will increase their chance of agent conversation and eventually make the sales. The question is if LangChain building it?

[Steverse @Steverse7]

@harikesh_devops I would use the word an agent instead of LLM as it pertains to raw outside model.

[LangChain @LangChain]

LangSmith now tracks cache hit rates for your agents 🦜

Cached LLM calls are cheaper and faster, so it's worth knowing how often your agent actually gets a hit.

📊 View your agent's overall hit rate as a single stat
🧵 Break it down thread by thread
📈 Chart it over time with our dashboard templates

Try it out today ➡️ https://t.co/NZbDhzp8xX

[Steverse @Steverse7]

@LangChain @hwchase17 Will providing an RSI context to the running agent directly from evals about its previous actions and confusion matrix help the agent improvise itself recursively?

[Steverse @Steverse7]

@leoleotoobad Why not store in agent.MD ? It is time consuming, however structuring the MD file(s) will help.

[Steverse @Steverse7]

@LangChain @divyasan0 Trust is built when people do act and reflect outside the scope of their work. We can observe and discuss their motives.
However, we don’t come across LLMs like people. So, no trusting LLM judges… we should monitor, verify, score for degradation.

[Steverse @Steverse7]

@LangChain LangChain+LangGraph+LangSmith=99% of agent issues solved!

[Steverse @Steverse7]

Jev 🚀

[TypeSafe AI @typesafeai]

@OpenRouter 🤝 @typesafeai

[Steverse @Steverse7]

Your personal assistant and business chief of staff 24/7. This is the least boiler plate AI system ready to go in minutes.

[Grok Bot @bot]

Three SpaceXAI employees are building a company in 3 days with Grok Bot. This is Day 1.

Matt Palmer (@mattyp), Lauren Tan (@poteto), and Roshan Sadanani (@roshan_s) start with research, a plan, and a product.

Live now, plus sessions for engineering, product, and founders.

https://t.co/eV3Tfd5Bf2

[CL Art Studio @cl_art_studio]

Hey @grok in 24 hours pick someone random who liked and RT this post to win a Tier II STONE.

STONES ARE FOREVER
➜https://t.co/5xKQ4j5jlX

[Leonidas 🧡 $DOG @LeonidasNFT]

Runes will be the most hated rally of all time

[Steverse @Steverse7]

@Yagobiverse Great perspective!
Question:
Why are runes different than other tokens?

[Steverse @Steverse7]

@degens @clairesilver MLow is your art project on its way to fruition?
I remember purchasing a rune.
👍

[Steverse @Steverse7]

@leocaillard @MEonBTC Leo, how do we check the VIP listed , want to make sure everything is good to go

[Steverse @Steverse7]

@rarefinds Agree! But why the people did not get convinced still that Ordinals are real forever art that nobody can turn off.