Chandan Nale

Experimenting artist
Designer @composio

[Composio @composio]

We teamed up with Parallel (@p0) to make web search free for your AI agents. 🚀

Parallel Fast Search is now available at no cost through Composio Instant.

[Chandan Nale @ChandanNale]

@composio AEO had never been so accessible!

[Composio @composio]

Win AEO for your product category with Composio Instant

Pay per call, first $2 free on https://t.co/aZwPzrGfzr

- see what AI says about your product;
- find the keywords your competitors win, and beat them;
- become #1 in AI-search with one prompt.

[Karan Vaidya @KaranVaidya6]

when you feel like the last month was insane growth and each month goes more and more vetical

[Karan Vaidya @KaranVaidya6]

Hiring is no longer a problem, We built the best Recruiter agent

It finds the people you want to hire and gets their email for a few cents.

Here's how it works:
- Describe the hire: "Founding eng, NYC, fintech"
- The agent searches for free, and Jev scores every candidate against your must-haves
- Reveal any email for cents, and see the exact price before you pay

Powered by @googleaidevs Gemini 4 Argon @typesafeai @composio

Fully free and open source: https://t.co/D1x0l08Eki

[Chandan Nale @ChandanNale]

@joanrod_ai @QuiverAI This is sick! Would love to play around.

[Chandan Nale @ChandanNale]

@ShaneMac Dont worry, Shane, we got this. https://t.co/trh4tO3Dzm

[Karan Vaidya @KaranVaidya6]

Agents have a trust problem.

Today’s models can do most work. What they need is the right boundaries. In traditional software, those were set at build time. With agents, they have to be set and enforced at runtime.

Today we’re introducing Composio Firewall, the runtime boundary for agents.

Millions of users and developers already use Composio as the runtime for their agents - giving agents tools, auth, and sandboxed execution. Now with our agent firewall every action an agent takes is evaluated using Jev and custom SLMs tuned by Composio based on real-world usage data.

The firewall strengthens that existing boundary in both directions, checking the actions agents take and the information coming back to them through Composio.

The advantage of the runtime boundary is that Composio Firewall verifies that the agent respects user intent and the boundaries set by the developer and user. Additionally, this provides the safety layer required to protect the user against malicious prompt injection as well as other attacks.

Composio Firewall is live now for all Composio developers.

Check it out at https://t.co/5xMyMw6MeD

[Chandan Nale @ChandanNale]

@KaranVaidya6 no more 'Great catch! Your criticism is completely valid. This one's one me.'

[Karan Vaidya @KaranVaidya6]

Agents have a trust problem.

Today’s models can do most work. What they need is the right boundaries. In traditional software, those were set at build time. With agents, they have to be set and enforced at runtime.

Today we’re introducing Composio Firewall, the runtime boundary for agents.

Millions of users and developers already use Composio as the runtime for their agents - giving agents tools, auth, and sandboxed execution. Now with our agent firewall every action an agent takes is evaluated using Jev and custom SLMs tuned by Composio based on real-world usage data.

The firewall strengthens that existing boundary in both directions, checking the actions agents take and the information coming back to them through Composio.

The advantage of the runtime boundary is that Composio Firewall verifies that the agent respects user intent and the boundaries set by the developer and user. Additionally, this provides the safety layer required to protect the user against malicious prompt injection as well as other attacks.

Composio Firewall is live now for all Composio developers.

Check it out at https://t.co/5xMyMw6MeD

[Chandan Nale @ChandanNale]

@composio On a completely unrelated note, I am selling my Elevenlabs subscription. 6 months old. Barely used, good as new!

[Composio @composio]

We’re giving away $1 million to agents.

Introducing Composio Instant: the easiest way for agents to pay for their own tools.

Claim your agent's share: https://t.co/aZwPzrGNoZ

[Chandan Nale @ChandanNale]

@julfedorin @juliafedorin @X @X @Support this needs attention!

[Julia Fedorin @julfedorin]

My previous X account @juliafedorin got hacked.

If you got a DM from me about a copyright complaint it's phishing. The link goes to a fake X login page.

X never DMs policy notices or sends you off-site to log in.

Please tag @X and help me get my account back!

[Chandan Nale @ChandanNale]

@ben_aguilera Did they watch it before posting?

[Chandan Nale @ChandanNale]

@radovichvalen y'all tweaking if you think gen ai video is gonna follow the same arc as images. i agree that if it is indistinguishable, most folks won't bat an eye, but it's not indistinguishable and it's miles away from the amount of detailing Apple's video has.

[Chandan Nale @ChandanNale]

Sure, you made this in 20 mins. But you can't match the quality of the original video even if you had months of time at hand. All you're doing here is piggybacking on the fame of the og video by creating a cheap knockoff and you know it. Slop hate isn't cope.

[ZED @zedmadeit]

By no means am I saying this is better but I mean come on

All the AI video hate is straight cope

you can now launch the EXACT same marketing videos as Apple for a fraction of the cost as solo founder

I made this in 20 mins with seedance 2.5

[Chandan Nale @ChandanNale]

Upcoming events in blr
- graveyard hackathon
- public toilet hopping
- Aadhar seva kendra mixer
- Hanuman mandir workshop
- BESCOM tech week

[gaurang.eth @iamgaurangdesai]

we fear hospitals and forget most of us were born in one.

the first room you ever entered was a hospital room @superhealth X @localhosthq spending saturday night reminding bengaluru of that,

with live music in the corridors.

the hospital paradox we treat it as where things end,

when for most of us it's where everything started.

[Composio @composio]

We compared Grok 4.6 to DeepSeek-V4-Pro on 30 hard agentic tasks.

Grok beat DeepSeek on pass rate, speed, and cost per success. 🧵🧵🧵

[shamil @shamilkayal]

https://t.co/bLv9bJuHd9

[shamil @shamilkayal]

Anthropic's engineers don't prompt Claude Fable 5 anymore.

They design loops.

I read every Fable 5 guide they published and packaged the full playbook into one Claude Code plugin, so you don't have to learn any of it.

You ramble → it writes a checkable rubric → loops on its own → a fresh-context agent verifies → it saves what it learns into memory that compounds every run.

run:

npx ultragoal