How do you actually build an effective harness with Claude? We had Thariq (@trq212) from Anthropic at Navigate 2026 to talk about "Unhobbling Claude", the difficulties and processes on how to build agents and harnesses.

Stagehand can use Stripe's new WebMCP tools in checkout pages. Run page.tools() to see what WebMCP connectors a page exposes. With Stripe, you can use Stagehand to add items to cart and complete the checkout with native tools.

Browserbase (@browserbase) is now available in Merge Agent Handler. Agents can fetch a page, search the web, or hand a plain-English task to a browser agent that runs on its own. Check it out: docs.merge.dev/merge-agent-h…

Your Agent needs its own Identity. Join the Coinbase Space today at 12PT (3pm ET) to hear about how agentic payments are driving a need for agents to have delegated identity models.

Your agent can trade. Your agent can pay. But who is your agent? Join us tomorrow, Sept 18 at 3pm ET for a Space on AiFi: Agentic Identity. w/ @World_ID, @browserbase, @marco_derossi, @programmer & @Coinbase Set a reminder ↓ nitter.net/i/spaces/1XxygwOZELdGM

we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand executes it.

Jev is incredibly fast at making split-second decisions, so i raced it against Luna on a Wikipedia sprint. To go from Lionel Messi --> Sam Altman Jev just took 9.7 seconds, while Luna took 20.4 seconds -- at one-third the cost! Super fast browsers running on @browserbase, video at actual speed.

you can build a price-monitoring tool on @browserbase in <5 minutes using fetch w proxies running this for 3 products costs roughly $1.50 a day if i price-check every 15 minutes.

LangChain's CEO says they built their gateway a year too late, and it's still costing them. I sat down with Harrison Chase, Co-Founder & CEO of LangChain, to talk about what's changed since LangChain started as a side project in 2022, why sub-agents rarely work the way people expect, and why LangChain now runs its own hiring, content, and coding work through internal agents in Slack. 00:00 Why "I use agents for everything" is a red flag in an interview 01:21 How LangChain started as a fall 2022 side project 05:18 From LangSmith to LangGraph: rebuilding as the ground kept shifting 09:06 The gateway LangChain built a year too late 13:23 Code mode: why agents writing code beats human-style tools 19:04 Should the agent run inside the sandbox, or call it as a tool? 28:31 The agent identity problem: whose credentials does it use? 45:43 Running LangChain's own GTM, content, and coding agents in Slack 48:34 The AI slop problem, and why they built a Slack emoji for it The full pod is also available on YouTube, Apple Podcasts, or Spotify.

Muse Spark 1.3 from @Meta tops the charts in our Browser Agent benchmarks using the @mastra agent harness. In this harness, Muse outperforms Opus 5 in cost, speed, and accuracy.