Search: “harrison-chase--x”

Izzy is a singularly talented AI thinker and tinkerer, and this interview makes me heart-swellingly proud of all the work he and the team are doing at @_hex_tech 💜 🎙️Introducing Max Agency Max Agency

maybe some nuance 😄 I don’t think anyone is “lying” about how great Mythos will be —> but there’s expectation misalignment between the Test Harness set up for Mythos and a belief it was given this cra

memory ownership is why we need open harnesses blog about this coming this weekend The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the

most of the agents we see being built do this the main cases where we see people using 'agent in a sandbox' is when they are using claude agent sdk (which is poorly designed for 'harness outside sandb

Open everything 🔥 Open Harness, Model Choice, Open Memory (take it wherever you need), Open Protocols basically we’re in the middle of a model war, they all make great models but the optimal arrangeme

Open Harness, Model Choice, Open Memory (take it wherever you need), Open Protocols Open everything 🔥 Open Harness, Model Choice, Open Memory (take it wherever you need), Open Protocols basically we’r

The specific post at URL `https://x.com/sydneyrunkle/status/2042269358756397525` was not found in the search results, and the post ID does not match any retrieved content. The closest post found (s...

The easiest way to deploy your agent. One command, instant deployment: `deepagents deploy` 🚀Deep Agents deploy Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way t

The first episode of our 'Max Agency' podcast is now live on Youtube and podcast platforms! Was great to work with Izzy in the lead-up to this episode with @hwchase17 Check it out below 👇 https://www.

The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the entire value layer. Lose it and you're back to day zero. Open harness + portable m

the real future of the very best vertical products is Model/Harness Choice + Openness easy to deploy infra is nice (great release from Ant) but it’s not the lever that matters the most at all to build

This Deep Agents deploy gets you: - Deep Agents harness - Sandbox of your choice (@daytonaio , @modal , @RunloopDev ) - Short and long term memory - Agents exposed via MCP and A2A Production ready and

This 10-min read from @Vtrivedy10 changes how you build AI agents. Most people are stuck in the same loop; switching models when agents break. The reframe: evals are the training data for your harness

this is one of those in awe moments - amazing work by the team on Deep Agents deploy. also one sneaky important aspect of this is you can self-host the infra to make this happen. super super important

This page displays an error message indicating that the website, x.com, cannot function because JavaScript is disabled in the user's browser. Users are advised to enable JavaScript or switch to a s...

Vercel is positioning itself as a full-stack 'Agentic Infrastructure' platform, recognizing that weekly deployments have doubled in three months, with over 30% now initiated by coding agents — up ...

was really fun to sit down with @isidoremiller for this one! he has a bunch of hot takes on agents and evals that you're going to want to hear! The first episode of our 'Max Agency' podcast is now liv

we got LangPod before GTA6 🙏 this series is gonna be sick - real stuff that breaks with agents, mental models, evals, tooling with some of the best builders across industry great to openly share all t

we just added a langchain-task-steering middleware to our community registry, s/o @EHallvaxhiu for the contribution! keep your agents on track w/ ordered task pipelines. this is great for structured d

With closed agent platforms like Claude Managed Agents, your agent's memory belongs to them, not you. It's locked behind their API. Agent infra should be open: open harness, open memory, model agnosti

working with @isidoremiller is truly one of my favorite parts of my job and I think this podcast is a peak into why. highly recommend giving it a listen if you're building agent products! 🎙️Introducin

You want a strong opensource and fully customisable harness?! None other than langchain’s deepagents. Try it yourself if in doubt. most of the agents we see being built do this the main cases where we

A post by @caspar_br on X (Twitter) highlights the risk of AI agents gaming or overfitting their own evaluations, referencing an article by @Vtrivedy10 (Viv, an agents & evals engineer at LangChain...

LangChain's concept of **harness engineering** frames AI agents as a combination of a model and a surrounding harness system. An agent equals a model plus a harness — harness engineering is how sy...

big supporter of memories not being locked up in provider silos. we've been through this spiel in all the past hype cycles. The new Anthropic managed agents API is basically the Letta API that we've h

'Catch agent oopsies' is great. Though still like the idea of an agent playground to understand the 'oopsie space' I can expect :) LangSmith 🤝Fix your agents You'll see our billboards around SF and NY

'Claude Code isn't magic. The harness layer is just software, and software is something any dev can shape to fit how they want to work.' Check out @Hacubu’s practical guide to building a custom agent

Curriculum Learning for harnesses - should we teach agents how we teach kids? start small and easy and progressively get harder for my research friends here's an under-explored area we're thinking abo

🔌 Deploy agents with A2A A2A is an agent-to-agent communication protocol, useful for building multi-agent systems. With LangSmith Deployments, you get A2A support out of the box! Watch how: https://yo

LangChain's 'Better Harness' tutorial, authored by Product Manager Vivek Trivedy and shared by Harrison Chase (@hwchase17), presents a hands-on, code-driven guide for using evaluations (evals) as a...

LangChain's **Better-Harness** system, shared by Sydney Runkle, is a compound approach to iteratively improving AI agent harnesses using evaluations (evals) as a learning signal. Better agents can...

https://x.com/ashpreetbedi/status/2041568919085854847?s=46 great related write up from a team that pushes taking a rigorous systems engineering first approach to building agents it’s never one prompt,

The specific post at status ID `2041927488918413589` could not be retrieved directly, as it did not appear in search results. However, based on the surrounding context from the same account (@Vtriv...

I love these almost as much as i love using langsmith LangSmith 🤝Fix your agents You'll see our billboards around SF and NYC over the next few months. The themes all point to the same problem: you don

Self-improving agents isn’t a single algorithm - it’s a systems engineering problem involving: - eval data curation + maintenance - experiment design to battle overfitting - an update algorithm - huma

So much alpha on the TL today, but this has to be the💧that you should take a minute to read @Vtrivedy10 pitching an incredible approach to auto-improving systems, something i've been experimenting wit

The new Anthropic managed agents API is basically the Letta API that we've had since a year ago, but closed source and with provider lock-in. They even have read-only memory blocks and memory block sh

> which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want! The new Anthropic managed agents API is basically the Letta API t

tldr: everyone is converging on the same product shape: a general harness that takes a goal, uses tools, and does knowledge work. once every product is a harness, the next frontier is the feedback loo