Blog

AdaL Blog

Let's have a journey on agents and models.

Featured
Sep 19, 20265 min read

AdaL 1.8.4: Write Like a Human

A capability that takes the model tells out of anything AdaL writes for a person to read. Plus BYOAK against your own gateway, and weekly usage you can see before you hit the limit.

Read Article
Recommended

Start Here

Curated reads from the SylphAI team on agents, product releases, and the community building around production AI.

Latest Articles

Browse by Category

1 / 4
#SEP 14, 2026
4m

AdaL 1.8.0: Capabilities Replace Modes

Browser use, deep research, and video generation are no longer modes you switch into. They're capabilities AdaL loads on its own when your task calls for them.

Read Article
#SEP 3, 2026
7m

How We Built a Browser Agent with a 92% Task Success Rate

AdaL scored 92% on BU100. The result is a systems score, not a model score: closed-loop control, CDP transport, liveness vs readiness, and the remaining 8%.

Read Article
#SEP 2, 2026
5m

@skills vs skills.sh: Two Bets on How Agents Should Find Capabilities

skills.sh, backed by Vercel, ships an install command and a leaderboard. @skills ships a reference and skips the install step entirely. Same protocol underneath — SKILL.md — two different bets on how an agent should reach a capability.

Read Article
#AUG 7, 2026
13m

Autonomy Is the Bottleneck of the Agents of Today

Today's coding agents are excellent tools for humans in the loop, but real autonomy may require a layer above the agent, not more capability inside it.

Read Article
#JUL 31, 2026
8m

Stop Repeating Your Workflow by Using Skills

In 5 minutes, you'll understand Skills, how they differ from MCPs and AGENTS.md, and discover how Skills let your AI automatically reuse workflows instead of starting from scratch every chat.

Read Article
#JUL 8, 2026
10m

Loop Engineering For Everyone

Loop engineering is clearly where we're heading. The missing piece is making it simple enough and affordable enough that every engineer can actually use it.

Read Article

Join the Evolution

Get notified about new agent behaviors, benchmark breakthroughs, and core AdaL framework updates.