AdaL Agent

The full-lifecycle harness for agentic engineering. Research, code, browser, review in one session

[AdaL Agent @adalagent]

Today we're announcing AdaL.

Our goal: true autonomy — agents and humans moving as one, starting with developer and coding agents.

[AdaL Agent @adalagent]

Getting an agent to execute is solved. Getting one you can trust with real work is not.

That was the conversation all day at the AI-tonomy Summit, where our founder @panda_liyin showed AdaL live to a room of builders, researchers, and founders at @PlugandPlayTC

Thanks for having us!

[Li Yin @panda_liyin]

as ai took over the code generation, it creates a new gap: understanding

@adalagent self-review is to close this gap and to help engineers

(1) keep all code changes in one tab, instead of splitting across local and the github pr
(2) cluster changes and walk though engineers to understand and improve

self-review is invented to stop the vibe coding crisis.

[Li Yin @panda_liyin]

gonna do a prelaunch party at @Soma_Capital SF on the night of 17th June.

builders will get the early access to @adalagent agent sdk, meta-agent, and adal engineer which likes humans, operates a coding agent to work.

if ur in sf, come to hang:

https://t.co/Fw3ASEgDzR

[AdaL Agent @adalagent]

Instantly switch between specialized agents for deep research, browser use, coding, self-review and sub-agent delegation with just /agent.

Along with /model, it unifies your entire workflow, so you always have the right model and toolset active without breaking your flow state to open another tab.

[AdaL Agent @adalagent]

Manual prompts are reactive. /cron makes them proactive.

With /cron, AdaL can check builds every 5 minutes, detect new failures, and return a concise triage summary automatically. Your scheduled prompt goes through the exact same pipeline as manual input, so @ file references, tool usage, and multi-step reasoning all work identically.

Set it and forget it.

[AdaL Agent @adalagent]

How does AdaL stack up against Claude Code?

We put the numbers up publicly. On coding (SWE-Pro-Curated-50), AdaL solved 50% of tasks vs Claude Code’s 46%, and in 34% less time, with 60% fewer tokens, and at $0.68 per success vs $1.87.
On browser automation, we hit 92% on BU100. That’s 2.5 points above the next best agent.

Fewer tool calls, fewer tokens, and better results is what our unified agentic workflow system gets you. Learn more here: https://t.co/CYq6CGbxWi

[AdaL Agent @adalagent]

Precisely. From our side at AdaL, we’ve seen the same thing: people debate models, but what matters is whether the work gets done well.

That’s exactly why we built /model so that you can switch across Anthropic, OpenAI, Google, Moonshot, DeepSeek, Zai, and MiniMax based on the task all while keeping context

[Li Yin @panda_liyin]

a coding agent will not be truly autonomous w/o browser use.

last night, @adalagent in browser use mode autonomously fixed a long-backlogged issue, all while i was watching a movie with my friend @AnnieLiao_2000 .

its like the great engineer i always wished i had.

[AdaL Agent @adalagent]

Yesterday, we hosted Agents After Dark with Build Club, and it was incredible getting to meet so many talented builders making things here in SF.

Thanks to everyone who came out and made it such a great evening. See you at the next one! Sign up here: https://t.co/5KRzaBsLCj

[AdaL Agent @adalagent]

try it out:

https://t.co/FXqfJvuPKt

[Li Yin @panda_liyin]

For launch week, Claude Opus 4.8 is 50% off in @adalagent.

Anthropic's newest Opus upgrade is now available in AdaL CLI and Desktop. Run /model and pick Claude Opus 4.8 from the New category for coding, research, and long-running agentic work.

https://t.co/ggkL5U4fKo

[Li Yin @panda_liyin]

For launch week, Claude Opus 4.8 is 50% off in @adalagent.

Anthropic's newest Opus upgrade is now available in AdaL CLI and Desktop. Run /model and pick Claude Opus 4.8 from the New category for coding, research, and long-running agentic work.

https://t.co/ggkL5U4fKo

[AdaL Agent @adalagent]

call for sf awesome builders

[Li Yin @panda_liyin]

I’m teaming up with @adalagent , @AnnieLiao_2000 and @buildclub_ to co-host Agents After Dark - a special co-working night for top AI researchers, builders and engineers in SF.

Only 30 spots available, highly curated.

Wednesday from 6.30-10pm.

Come meet other builders working at the frontier of AI agents - or tag someone who should be in the room.

See you there 🌙

https://t.co/7m3KlGBLNO

[AdaL Agent @adalagent]

@AnnieLiao_2000 @panda_liyin come to build w us.

[AdaL Agent @adalagent]

come to build with us!

[Annie ❤️‍🔥 @AnnieLiao_2000]

co-hosting a special "agents after dark" event for top AI Builders / Researchers in SF with @panda_liyin ✨.

this Wednesday. only 30 spots available, come meet other builders pushing the frontier!

apply / RSVP 🧵

[Annie ❤️‍🔥 @AnnieLiao_2000]

co-hosting a special "agents after dark" event for top AI Builders / Researchers in SF with @panda_liyin ✨.

this Wednesday. only 30 spots available, come meet other builders pushing the frontier!

apply / RSVP 🧵

[Li Yin @panda_liyin]

82% of developers feel the pain of the Vibe Coding Crisis. This is how AdaL, as a coding agent, stands out to best resolve it.

The “vibe coding crisis” is not that AI writes bad code. It is that teams start confusing code generation with engineering progress. The danger is shipping faster without understanding what was built, why it works, or how it will hold up as the system grows.

How does AdaL differ from other coding agents?

Engineering is 20% code and 80% everything else. AdaL operationalizes the whole process through agents. We stand out in three major ways:

(1) High-performing worker agents cover the full life cycle of engineering, from deep research to coding to browser verification.

(2) Three levels of automation: (a) You can Shift+Tab or use /permission to switch the implementation part to YOLO mode without needing humans to approve. (b) Run a recurring /cron job to run long-term experiments, which is especially great for AI researchers. (c) Another AdaL Engineer Agent can control multiple AdaL worker sessions so that you can work with AdaL as if you are working with a high-agency senior engineer.

(3) Optimized for humans to learn and understand. Our agent shows the full chat history, even in CLI, full tool input and output, and the full reasoning trace to make it easy for human engineers to follow. Plus, we are the first with AdaL review, which clusters a big PR into multiple clusters to walk through and iterate on the PR so that no PR is sent to reviewers without being fully understood.

We are grateful that developers are loving our approaches and are super excited to continuously improve so that humans can be freed to do high-value tasks.

[Li Yin @panda_liyin]

Gemini 3.5 Flash is live in @adalagent with 50% for a week.

It matches Gemini 3.1 Pro performance with flash speed. It is available to everyone in the AdaL CLI and Desktop Preview — just start a new session or resume an old one to try it out.

Already 25% cheaper than Gemini 3.1 Pro at base price — and with our 50% launch discount for the next 7 days, it's over 2.6x cheaper overall and 6.6x cheaper on cached inputs.
👇

[AdaL Agent @adalagent]

Every problem deserves the right model.
AdaL's worker agents can run on Claude, GPT, Gemini, Kimi, DeepSeek, GLM, MiniMax, and more. Each worker brings the right model and toolchain into one agentic engineering workflow. All you need is /model.

Try it out yourself. Link in bio.

[AdaL Agent @adalagent]

we promise it’s all voluntary

[Li Yin @panda_liyin]

Hey, if you travel to SF, we can get you free stay, all you have to do is this 👇

thanks @EcZachly