More agents ≠ engineering transformation. Meet Cosmos, the OS for agentic software development.
- Tweets 1,716
- Following 45
- Followers 21,740
- Likes 2,462
Pinned Tweet
Introducing Cosmos: the Unified Agents Platform for software teams.
Orchestrate a fleet of agents across your entire software development lifecycle, as a single organizational system instead of disconnected workers.
It's changed how our own engineering team works, with throughput up 3x.
9
12
38
4,465
Sonnet 5 is now available in the model picker in Cosmos.
New model, same story: better performance for less money. Sonnet 5 begins to close the gap to frontier-level intelligence, bringing near-Opus performance at Sonnet pricing. This means that quality and cost become less of a trade-off, and we recommend trying Sonnet 5 for work where cost and throughput matter most.
Until August 31, experience this new level of Sonnet intelligence at a discount ($2/M input tokens, $10/M output). After this period, Sonnet 5 will be priced the same as previous Sonnet models.
Introducing Claude Sonnet 5, our most agentic Sonnet yet.
It makes plans, uses tools like browsers and terminals, and runs autonomously at a level that just a few months ago required larger and more expensive models.
1
9
2,133
Augment Code retweeted
This is internal feedback on our version (Cosmos). Cloud agents + integrations + Slack.
1
2
630
How do you keep up with AI? @gregorojstersek has advice for any engineering leader:
2
4
14
1,655
The next wave of AI adoption is a measurement problem.
AI tooling is now a line item in every engineering budget. But, assessing its value still remains ambiguous. Most engineering leaders went into AI expecting 2-3x productivity gains, but are landing closer to 30%.
We are building a benchmark on AI engineering productivity and ROI. If you help lead, measure, or operate engineering work, your input helps set the baseline.
Take the survey here: augmentcode.com/lp/ai-engine…
2
2
5
1,694
A few we shipped to production like this, all on systems with thousands of active users, none of which caused an incident.
1
2
937
The human reviews the design before any code exists. Our Code Review experts then read the full diff in minutes and check it against that approved design. Implementation size stopped being a constraint the moment a person was no longer the one reading every line.
The unit of work is no longer the PR. It's the project, and one agent can now carry a project from approved design to merged code on its own.
Full write-up: augmentcode.com/blog/acceler…
1
2
909
Most teams point agents at small, well-scoped work. A ticket goes in, a tidy PR comes out, a human reviews it, it merges.
Our largest projects don't work that way.
On Cosmos, once a human has reviewed and approved the design doc, we hand the entire design to a single worker agent and let it build the whole thing as one PR. It implements the design, fixes its own CI failures, and works through review comments until the change is ready to merge. No ticket-splitting, no relay between agents.
The PRs are large, often thousands of lines, and we prefer them that way. One agent holding the full approved design writes a more coherent change than several agents each working from a slice of the context. The seams you get from splitting, the mismatched assumptions between unit three and unit seven, don't show up when one agent carries the whole picture.
4
4
34
2,514
Claude Fable 5 has been suspended following a US government directive. Details here: nitter.app/AnthropicAI/status/206….
We've removed Fable 5 from our model picker for now. Any new and existing agent sessions in Cosmos that were pre-configured to use Fable 5 will now fallback to Opus 4.8 (at Opus 4.8 pricing). No action is needed unless you choose to switch to another model. All other models remain fully accessible.
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
5
1
13
2,887
"There's never been a better time to be a software engineer", @JustinReock with the hot takes 🔥
Watch the full episode here: piped.video/n-VGqrRK2vk?si=m-gR…
3
7
967
With models like Fable 5, model routing is more important than ever. We’ll be adding Fable 5 to our model router, Prism, soon.
Prism routes each turn to the best-fit model and is cache-aware, so teams can keep frontier-level quality while cutting cost. In our internal benchmarks, Prism delivered up to 30% lower cost per task at no difference in quality.
3
2
554
Fable 5 is built for long-horizon work: investigations, multi-step changes, and end-to-end tasks that normally take hours. You’ll see the biggest lift when you point it at your hardest, most ambiguous engineering work.
If you try Fable 5, let us know: we’re eager to hear how you use it and where you find the most value with this new model family.
2
531
Fable 5 is now available to Augment Code users. At ~2x the cost of Opus 4.7, Fable 5 is a premium option for long, multi-step engineering work.
Try Fable 5 today in Cosmos, our unified agent platform, to fully experience the power of the most advanced model on the market.
5
6
34
3,356
The bigger unlock is Fable 5 running in our unified agent platform, Cosmos. Pull context from your tools and run across the SDLC (triage → spec → implement → review → test → deploy).
Instead of “one prompt, one answer,” you get background workflows with triggers + durable memory: and engineers step in only when judgment is needed.
1
1
501
TL;DR: Fable 5 isn’t the right-sized model for every task, but when quality and depth matter (review, architecture, long-running changes), the lift is impressive.
Here’s how it stacks up vs Opus 4.8 + GPT‑5.5
2
2
3
1,029
Fable 5 brings a new level of capability to complex software engineering work.
We've found it performs best for:
- Code review where catching subtle issues matters
- PR authoring and implementation support
- Large-project planning and architecture reasoning
- Long-running, multi-step technical tasks
- High-stakes engineering work where quality matters more than cost
2
1
2
957
We're all experiencing the moving bar of "being AI native". How do we navgiate it?
Watch the full episode with @CircleCI's @z00b here: piped.video/2cGdwowJiSw?si=WRTk…
2
6
644