Joined August 2024
191 Photos and videos
Pinned Tweet
.@nibzard built a deep research agent on Steel. Then the evals taught him it was good at the wrong thing: beautiful overviews, weak exact answers. The fix was not another tool. It was routing, durability, and reading the failures. ↓
2
3
7
961
Steel retweeted
What's new @ Steel - Changelog #029 ✦ Projects project-scoped API keys and sessions ✦ Sessions can now trust custom CAs with caCertificates ✦ v1/scrape markdown overhaul: better extraction, richer metadata, full-page fallback ✦ Plus live viewer upgrades, browser pooling & more Link below ↓
1
1
6
269
Steel retweeted
Projects are live in Steel. ✦ Isolated namespaces inside one org ✦ Sessions, credentials, profiles, and API keys scoped per project ✦ One-way promotion from Development to Production Dev stops sharing a bucket with prod.
1
1
5
252
internally, we have been automating browsing agent recordings as a fun way of observing agents here you can enjoy a simple demo of claude code actions overlayed in sync with a browser session
1
5
447
Steel retweeted
.@nibzard built a deep research agent on Steel. Then the evals taught him it was good at the wrong thing: beautiful overviews, weak exact answers. The fix was not another tool. It was routing, durability, and reading the failures. ↓
2
3
7
961
What's new @ Steel - Changelog #029 ✦ Projects project-scoped API keys and sessions ✦ Sessions can now trust custom CAs with caCertificates ✦ v1/scrape markdown overhaul: better extraction, richer metadata, full-page fallback ✦ Plus live viewer upgrades, browser pooling & more Link below ↓
1
1
6
269
Projects are live in Steel. ✦ Isolated namespaces inside one org ✦ Sessions, credentials, profiles, and API keys scoped per project ✦ One-way promotion from Development to Production Dev stops sharing a bucket with prod.
1
1
5
252
We held off on this longer than most platforms. Our honest opinion was simplicity trumps complexity: one org, one bucket, nothing to configure. Then one agent became a fleet, and simple scripts became workflows carrying their own credentials and profiles. One bucket doesn't scale with agents.
1
1
131
Nothing to migrate. Every org now has a Default project with your resources and keys already in it. Your code keeps working. Full write-up. steel.dev/blog/introducing-p…
1
61
.@nibzard built a deep research agent on Steel. Then the evals taught him it was good at the wrong thing: beautiful overviews, weak exact answers. The fix was not another tool. It was routing, durability, and reading the failures. ↓
2
3
7
961
Pi from @badlogicgames for the agent loop, Absurd by @mitsuhiko for durable execution, Steel for browser sessions, Postgres for checkpoints. The real unlock was making failure resumable. Every model message checkpoints. Notes, URLs, claims, and source ledgers rebuild from the transcript. Crashes became annoying instead of existential.
1
2
199
Steel mattered because the research needed browsers, not fetches. The useful web renders late, redirects, blocks scrapers, or hides content behind behavior. Plain fetch sees a thinner world. Deep research agents improve when every failed run leaves enough evidence to inspect, resume, and turn into the next change. steel.dev/blog/durable-resea…
1
106
Steel retweeted
The "deep research" workflow bundled in Claude Code isn't deep. It's wide. Niko pulled Claude Code's dynamic workflow to find exactly that shape. ↓
claude code /deep-research isn't deep. it's wide. your question gets sprayed across 5 parallel searches, the pile gets summarized, done. no agent ever reads a result and forms a sharper question from it. i pulled the workflow out of its binary to inspect it. ↓
1
1
5
259
The "deep research" workflow bundled in Claude Code isn't deep. It's wide. Niko pulled Claude Code's dynamic workflow to find exactly that shape. ↓
claude code /deep-research isn't deep. it's wide. your question gets sprayed across 5 parallel searches, the pile gets summarized, done. no agent ever reads a result and forms a sharper question from it. i pulled the workflow out of its binary to inspect it. ↓
1
1
5
259
What's new @ Steel — Changelog #028 ✦ Inactivity timeouts: session can release itself when your agent goes quiet ✦ CLI now manages sessions installs agent skills ✦ Wider anti-bot coverage: DataDome, Imperva, Amazon WAF & FunCaptcha ✦ Plus: raw-markdown docs access, cleaner API errors, billing fixes Link below ↓
1
3
411
great thoughts on building our skills library from our co-founder/cto papa @0xbosta
1
1
10
3,180
Today we are launching Steel Skills. Five agent skills for the web. Install one or the whole set. Runs in Claude Code, Cursor, Codex, opencode, Pi, or any compatible agent.
7
2
24
3,324
List the catalog with @vercel skills or use Steel CLI skills command. `npx skills add steel-dev/skills --list`
1
2
98