What is effort really? When do you change it it and why not just use max effort for everything? I dove deep into this problem, looking into evals and doing my own tests and I was quite surprised by the results.

Claude Code will now try to find a graceful stopping point when you hit your 5-hour limit mid-task, instead of cutting off mid-edit. It gets a small, fixed allowance pulled from your weekly limit to wrap up what it can.

Tag writes >50% of my PRs every day. It also does ~100% of my data analysis, and fixes most of our product feedback + bugs. It's not like a regular Slack bot. It is proactive, programmable, it has memory, it has access to your connectors. With Opus 5.5 and Fable 5.1, it has strong judgement. Example prompts I use: - "@Claude react to threads in this channel with ✅ when resolved" - "@Claude from now on, attempt to repro every bug in this channel end to end, running the full app. once you reproduce the bug, put up a pr to fix it and tag the right team for code review" - "@Claude brainstorm ~100 hypotheses for what could explain this weird data, use a workflow to in/validate. spend 10m tokens or so digging very deep. draw a chart with the result." - "@Claude make me an interactive game explaining how this part of the code works, then make a slide deck explaining it for others on the team"

At Box, we've been testing Opus 5.5 on a variety of complex enterprise knowledge work tasks dealing with unstructured data with the Box Agent. Overall, we saw frontier capability levels, with major performance improvements over Opus 5. 63% fewer tokens used, 42% less verbosity, and 30% faster vs. Opus 5. And the model itself is cheaper, so this is a major win for any agentic computer use, coding, analytics, or data work that enterprises will be doing. Here are some examples of the task wins and performance gains across a variety of industry tests that we performed: • Financial services - due diligence (+39% task accuracy): A year of transaction records, with the job of finding every miscalculation in an acquisition target's pricing tool. Opus 5.5 scored a perfect result on every attempt in half the words Opus 5 used, consuming 82% fewer tokens overall. • Technology - cloud cost analysis (+65% task accuracy): Work out what a company should actually change about its cloud spend. Opus 5.5 picked the right basis for the retention calculation and kept the source data's unit conventions straight all the way through, so the number at the end actually holds up. It took half the time Opus 5 took, with 70% fewer tokens. • Consumer products - client account analysis (+17% task accuracy): Set the onboarding targets for a client account, reading across the signed contract, a satisfaction tracker and a team metrics sheet. The contract never states a senior/junior split, so Opus 5.5 derived it from the 18-person roster and showed the rule it used; several clients had a perfect 10 on individual survey questions, so it averaged each client's responses instead of crowning the single 10. It finished this one in half the time, on 78% fewer tokens. • Clinical diagnostics - data analysis (+15% task accuracy): Malaria rapid-test performance across a dry and a wet season: build the patient records out of two clinical PDFs, compute positive test rates by season and gender, and test whether parasite counts really differ between test-positive and test-negative patients. Opus 5.5 caught that the two groups' standard deviations differed more than 100-fold, re-ran it the right way, and found the dry-season difference didn't hold up after all. This accuracy gain came with a final answer that was half the length of Opus 5's, and also needed 78% fewer tokens end to end. Customers will be able to build AI Agents with Opus 5.5 shortly in the Box AI Studio.

Cloud sessions are officially available and out of research preview! They let you keep Claude Code working, even when your laptop is closed. Existing subscribers get a one-time credit to try them: $100 on Pro, $250 on Max.

Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR. We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use. Read more:

If you've noticed how fast and the Desktop app have become in the last few weeks, here's how we did it. Lots of juicy learnings & techniques in the blog post for engineers working on speeding up your own apps.

I rarely post about our model launches, but I truly enjoy Claude 5.5 and I am really glad it is finally available to everyone. It communicates more clearly, is much more concise and is a very capable model, all of it while being much cheaper. I found myself using it quite a lot.

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt. I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted. Is formal verification the future of coding (or at least, bug finding)?

Opus 5.5 is the result of your feedback. It communicates clearly, it's cheaper per token than Opus 5.0 with the intelligence of Fable 5.1, it’s very token efficient and works across every effort level. We're also increasing 5h rate limits & giving you a banked reset.

Opus 5.5 is a really good model. It's been my daily driver the last few weeks. We had Opus 5.5 and Fable 5.1 each port HAProxy from C to Rust. Both passed nearly all of HAProxy's tests, but Opus 5.5 finished in 9.5 hours compared to Fable 5.1's 12 hours, and for 51% less cost.

We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.

What makes Claude Projects so interesting is that it handles teams of agents really well, you talk to a main orchestrator agent and it spins up specialists. Basically it creates an organization to solve your issue, mixing expensive and cheap agents depending on your preferences. For example, I asked Fable in Claude Projects to select famous historical mysteries that it could try to resolve. It initiated research agents, selected the mysteries based on data it could access, and spun up eighteen separate threads, each with an agent each focused on one mystery. Then each thread launched additional agents (simulating avalanches, breaking codes) before summarizing those and passing them to still more agents for write up and another set of skeptical agents to fact check. It did this over a day of work, with the central orchestrator agent organizing it all. The results were interesting if you like historical mysteries. They are also for fun and certainly not definitive or guaranteed error-free (but they are also mostly reasonable & grounded in the literature).

Projects have changed not only how I interact with Claude but how I code. I stopped managing sessions. I just send thoughts as they come, Claude splits them into threads, and the project remembers how I work. It's where I do a ton of my coding now. [screenshot: my actual prompts for claude code cli yesterday]

Today, we're combining Cowork and Chat into one Claude. You can fire off questions and then turn to serious work in the same conversation. When your computer is open, Claude can use your local files and apps - and if you close it, Claude will keep working with its own computer in the cloud.