
🤌 I Build Agentic AI experiences for Fortune 500s @AccentureSong. Father of 3, 1 unimpressed dog, 5 Mac Studios running frontier AI in my wife's closet.
Milan - Italy
Joined March 2009
- Tweets4.3K
- Following1.4K
- Followers1.6K
- Likes1.1K
Tommaso Nervegna retweeted
Replying to @cursor_ai
@Cursor_AI is getting renamed to Grok @Build
Cursor is now Grok Build.
A new name, and a faster app.
Grok Build CLI 2.0 is already in alpha-unified channel, which seems it will be tied to the unified sub.
The cube stays. The Cursor name doesn't.
Write the exam before the code.
New paper: a 4B model proposes 8 harness edits, only the best on held-out questions survives. Your job shrinks to the scoring set.
via @hanakoxbt
teapawt.org/hanakoxbt/status/21235…
#AgenticDesign #SortedPixels #Evals
ok this paper is f*cking insane
Chinese researchers just dropped a paper with a title that should make every agent framework nervous: "The End of Harness Engineering"
the argument fits in one line: hand-writing the program around the model is finished as a skill
a harness written by a person is one guess about one task on one afternoon
it ships, then runs for months unread and unscored
a harness written by the loop is a file that grades itself
a small 4B model reads what failed and proposes 8 edits
only the edit that scores best on held-out questions survives
the big model stays frozen the whole time
put Claude Fable 5.2 in that seat and every round rewrites the harness around it
so the human job shrinks to one artifact: the scoring set, the questions the harness gets graded on
frameworks become disposable, and the exam becomes the job
the whole paper in one line: write the exam before the code
then read the article below ↓
28
An agent that quizzes you about the fries, then burns the steak.
Theo on GPT-6.2 Astra: sharpest agent UX critique this week. Clarifying questions are a design surface, not a toll booth.
via @theo
teapawt.org/theo/status/2123536846…
#AgenticDesign #SortedPixels #AIUX
Read this to the end, I promise it’s worth it.
Imagine that you’re ordering food at a restaurant.
You: “I’ll have the steak medium rare with fries”
Waiter: “What about the fries?”
You: “…huh?”
Waiter: “do you want the fries medium rare too?”
You: “idk what that means just cook them normal”
Waiter: “okay got it, coming right up!”
15 minutes pass, waiter comes back out
Waiter (panic’d): “hey man, we REALLY need to know if you want your fries cooked at 413 degrees or 471 degrees. Whole kitchen is held up until you decide!”
You: “wtf just do whatever the chef wants”
Waiter: “okay got it!”
30 minutes pass.
The waiter comes out with mostly passable fries, and an entirely burnt steak
You: “wtf happened this steak is burnt!”
Waiter: “so sorry, the chef got distracted when waiting for your answer about the fries. We can put the steak in the fridge to cool it off if you’d like?”
This is how it feels to use GPT-6.2 Astra.
2
1
39
Hermes Agent just walked into Microsoft Teams.
The bit I like: nail a recurring task, it becomes a skill your team shares after review. Governance in the system.
via @NousResearch
teapawt.org/NousResearch/status/21…
#AgenticDesign #SortedPixels #EnterpriseAI
We've partnered with @Microsoft to bring Hermes Agent to the enterprise.
Hermes Enterprise now works inside Microsoft Teams, the Microsoft Store and Azure. In Teams, employees hand Hermes work like financial analysis, document drafts or inbox triage, and review the result in the same chat. Agent workloads run in isolated Azure Container Apps sandboxes.
When someone finds a good way to do a recurring task, Hermes saves it as a skill. With Collective Wisdom, they can share that skill with their team after review, so the next person starts out with the best approach anyone has found to accomplish that task. The skills then grow along with the company.
Companies with strict data residency or procurement rules can run Hermes Enterprise in their own Azure tenant. Our CTO Jeffrey Quesnelle presents how Hermes uses these sandboxes at Microsoft Ignite today, in session BRK448.
Thanks to @M12vc and the @Azure Container Apps team.
nousresearch.com/hermes-ente…
70
1 in 4 AI agent skills had security holes.
NVIDIA scanned 31,132: 26.1% vulnerable, 5.2% looked malicious. The scanner is open source. Installing skills from random repos? Scan first. I will.
via @RoundtableSpace
teapawt.org/RoundtableSpace/status…
#AgenticDesign #SortedPixels #AgentSkills
NVIDIA scanned 31,132 AI agent skills. 1 in 4 had security holes.
→ 26.1% had vulnerabilities
→ 5.2% looked deliberately malicious
→ These skills run inside Claude Code, Codex and Gemini CLI with almost no checks
NVIDIA open-sourced the scanner it used. Run it before you install any skill.
github.com/NVIDIA/SkillSpect…
41
Tommaso Nervegna retweeted
Chloe Ayton, SpaceXAI Western Europe Marketing Manager, at Grok Bot Galaxy London. The event gathered more than 140 senior executives for conversations and demonstrations of real use cases in engineering and knowledge work.
A notable part of the program involved setting up an AI teammate live on stage and then leaving it to run on its own, illustrating the move from querying AI or directing every step to assigning a goal and letting the bot complete the work independently.
Customers and Grok Bot superusers who shared adoption experiences on stage included Krešo Žmak (Chief Innovation Officer at Infobip), Matthew McGuire, and Tommaso Nervegna (@Nervo, who builds agentic AI experiences for Fortune 500 companies at Accenture Song).
Design hiring is down 20% YoY. PM demand is up.
Juicebox recruiter data via Lenny: SWE demand falling, AI engineering growing fastest. My read: designers who ship with agents still get the call.
via @lennysan
teapawt.org/lennysan/status/212321…
#AgenticDesign #SortedPixels #ProductDesign
The folks at @juicebox_work looked at recruiter trends (outbound searches from recruiters) and are seeing exactly the same thing I saw:
1. Demand for software engineers is dropping
2. Demand for PMs is growing
3. AI engineering growing even faster
4. Design hiring down 20% YoY
3
62
Gemini 4 Neon just moved the cost-performance bar in Cursor.
63.7% on CursorBench 4.1, up from 57.3% for Hydrogen, at $3/M input. I'm putting it on real UI work today before I believe the hype.
via @cursor_ai
teapawt.org/cursor_ai/status/21231…
#AgenticDesign #SortedPixels #Gemini
Gemini 4 Neon is now available in Cursor!
At its default effort, it sets a new cost-performance frontier on CursorBench 4.1, scoring 63.7%, up from 57.3% for Gemini 4 Hydrogen.
Priced at $3/M input and $15/M output tokens.
50
Your agent can QA its own UI in a real browser.
New agent-browser skill applies Chrome's guidance on layout shift, reduced motion, dark mode and focus, then checks it.
via @ctatedev
teapawt.org/ctatedev/status/212281…
#AgenticDesign #SortedPixels #Accessibility
New skill: modern-web-guidance
Your agent looks up Chrome's Modern Web Guidance, applies it to your code, then checks the result in a real browser
Layout shift, reduced motion, dark mode, dialog focus, more
Start here:
npx skills add vercel-labs/agent-browser
34
"I hired Fable 5.2 as my full time designer."
Bold claim, with a video to back it. Designers: watch it and tell me which calls still need you.
via @tobiadonadon_
teapawt.org/tobiadonadon_/status/2…
#AgenticDesign #SortedPixels #ProductDesign
1
33
Claude's smallest model beat Opus with one text file.
84 real tasks: Haiku + skills 27.7%, Opus without 22.0%. The edge: writing the work down once.
via @distortgeekin
teapawt.org/distortgeekin/status/2…
#AgenticDesign #SortedPixels #AgentSkills
Claude's smallest model just beat Claude Opus with one text file
84 real tasks: Haiku with skills 27.7%, Opus without them 22.0%
The difference wasn't the model, it was writing the work down once
6 parts, 6 broken skills and a SKILL.md you can copy ↓
24
Open sourcing your SaaS is the new SaaS playbook.
Turn your best workflows into skills, put them on GitHub, make them run in Claude Code, Codex and Cursor on day one.
via @gregisenberg
teapawt.org/gregisenberg/status/21…
#AgenticDesign #SortedPixels #Startups
I’ve noticed open sourcing your saas is the new saas playbook
1. pick the job your customers hire you for
2. turn your best workflows for that job into skills
3. open source them on github
4. make them work in claude code, codex, cursor and openclaw on day one
5. ship an MCP so agents can use your product directly
6. post the repo with a list of every skill inside (like this one)
7. every install puts your brand inside someone's agent, and it gets used every day
8. the free skills do the work once. the paid product does it every week, with your data, hosting and support
9. upsell to done for you, team plans and the hosted version
10. keep shipping new skills. every one is a new launch
Your free skills are the new free trial.
saas has gone open source for real
42
User interviews are out. Evals are in.
When your users are agents, you stop mocking journeys and run evals that feed the build loop.
Who writes the evals on your team?
via @rauchg
teapawt.org/rauchg/status/21224155…
#AgenticDesign #SortedPixels #UXResearch
The old way: users are human, you run user interviews, get inspired, mock up user journeys.
The new way: users are agents, you run evals, evals inform the software engineering loop.
Good read on how we do evals at Vercel.
1
1
37
A rough sketch to a working font in minutes.
Gemini 4 Hydrogen builds the typeface and the design tool around it. Type designers: try it on your own glyphs.
via @GeminiApp
teapawt.org/GeminiApp/status/21223…
#AgenticDesign #SortedPixels #Typography
Turn a rough sketch into a working custom font in minutes with Gemini 4 Hydrogen.
Using Google @Antigravity in the Gemini app for Mac, Hydrogen handles the technical heavy lifting so you can build custom typefaces and interactive design tools from scratch.
1
62
A paywall skill that bans fake timers, fake reviews and hidden close buttons.
It studies rival paywalls, then drafts 3 screens a critic scores until they pass.
via @tobiadonadon_
teapawt.org/tobiadonadon_/status/2…
#AgenticDesign #SortedPixels #UXDesign
the onboarding sequence is the most important thing to optimize in an app
i built a skill that designs your onboarding and the paywall
it researches all the main app paywalls/onboardings in the niche
→ your onboarding, redesigned so every screen has one job
→ your price, set against what your competitors charge
→ the doubts in their head when the paywall appears, and what happens if they say no
→ three directions, as real screens, scored by a fresh critic until they pass
→ the code: SwiftUI with Apple's purchase system, or Stripe for the web. no fake timers, no invented reviews, no hidden close button
giving it away for free
comment "PAYWALL" and i'll send it over
(need to follow for dm)
28
Your coding agent can now learn Disney's 12 principles of animation.
LottieFiles' motion-design-skill: timing and easing before code. 1 of 20 repos for agent motion work.
via @0xMovez
teapawt.org/0xMovez/status/2121312…
#AgenticDesign #SortedPixels #MotionDesign
These 20 GitHub repos will turn your Fable 5.2 into a premier motion studio.
this is f*cking gold for Fable 5.2
skills. 3D. FX. Motion. Sound. Export.
01 /motion-design-skill → Timing, easing and Disney's 12 principles.
github.com/LottieFiles/motio…
02 ai-kit → CSS springs and motion audits for agents.
github.com/motiondivision/ai…
03 Remotion Skills → Official video skills for coding agents.
github.com/remotion-dev/skil…
04 /hairline → Interactive line figures from an idea or an SVG.
hairline.lucasmarkes.com/ski…
05 /anatomy → Machines and systems as isometric figures.
skills.wheresryan.sh/anatomy
06 /anatomy-reveal → Exploded product views and a reveal MP4.
typingmind.com/skills/annngu…
07 /blender-agents → A full AI 3D team inside Blender via MCP.
github.com/scenario-labs/ble…
08 Three.js → 3D scenes and camera moves.
github.com/mrdoob/three.js
09 react-three-rapier → Real physics for React Three Fiber scenes.
github.com/pmndrs/react-thre…
10 react-postprocessing → Bloom, depth of field and film effects.
github.com/pmndrs/react-post…
11 three.quarks → Particle trails and VFX.
github.com/Alchemist0823/thr…
12 Tweakpane → Live controls for your scene parameters.
github.com/cocopon/tweakpane
13 GSAP → Animation timelines. Now fully free.
github.com/greensock/GSAP
14 Remotion → React video engine.
github.com/remotion-dev/remo…
15 Manim → Animated diagrams, equations and explainers.
github.com/ManimCommunity/ma…
16 Lottie → Lightweight vector animation playback.
github.com/airbnb/lottie-web
17 Openverse API → 5.2M+ free sound effects, ambience and music.
api.openverse.org/v1/
18 librosa → Beat detection for music-synced animation.
github.com/librosa/librosa
19 WhisperX → Word-level timing for captions.
github.com/m-bain/whisperX
20 FFmpeg → Encoding and delivery.
github.com/FFmpeg/FFmpeg
Skill → scene → motion → sound → final cut.
Bookmark this then go build something worth watching with guide below ↓
2
3
131
A tool "wildly impractical" for a human engineer just shipped.
xeet renders an X post to PNG in ~1ms. An oracle checks it against Chrome on 10k+ layout rules; agents get the PRs.
via @rauchg
teapawt.org/rauchg/status/21221847…
#AgenticDesign #SortedPixels #WebDev
Introducing 𝚡𝚎𝚎𝚝: xeet-rs.vercel.app.
A hermetic, pixel-perfect X post renderer in safe Rust / wasm. Zero browser, network, filesystem, system fonts. Renders a post to PNG in ~1ms (and 0.4 ms for @jack's "setting up my twttr" 😁).
X is the global town square, and the medium is the message. Being able to preview what things will look like before posting is great for both humans and agents.
Rendering with xeet is is 100x-1000x faster than booting up a browser and taking a screenshot, yet it's just as accurate.
It reproduces Blink & HarfBuzz text shaping, 1/64px line breaking, RTL bidi, 28 Chirp font subsets, CJK/Math/Emoji fallbacks, "Show more" rules, etc. It's the kind of thing that would be wildly impractical, if not impossible, for a human engineer to pull off.
Except 𝚡𝚎𝚎𝚝 is structured as an "autorepo." An oracle boots up Chrome, and verifies tens of thousands of text layout rules. A CI canary then watches the evolution of the original, and files signed PRs for agents to act on. It was conceived from the ground up around 'verification engineering', and the result speaks for itself.
Enjoy!
1
1
55

































