Shrimithran

GTM @scalekitinc | 📍Chennai / SF | GGMU

[Shrimithran @shrimithranr]

@0xPaulius I ranted about this a couple of days ago. It’s not just indie hackers. This playbook feels foreign to anyone who still believes authenticity wins.

https://t.co/zIOWvhO6va

[Shrimithran @shrimithranr]

Watched enough launches this past year to see there's one playbook now: pay a network of big accounts to boost you on cue.

It works. No shade to anyone running it.

But the "why" got lost.

Noise became the currency, and conviction is getting priced out.

[Ravi Madabhushi @ravibits]

Looks like our Hermes plugin has taken off a bit, and the chatter under it is mostly "why Scalekit over the others?"

Thought I'd take a moment to share how we think about this.

Getting an agent to call thousands of tools is table stakes now. Every platform in this space does it, us included.

The hard part starts after that. Your agent is acting for a real person, inside systems your customer owns.

→ Your customers' systems don't all use OAuth. Some use key pairs, service accounts, admin-level access. We handle those out of the box.

→ Every customer has that one internal API or MCP server nobody has a connector for. You can plug it in, and it gets the same auth and logging as a native connector.

→ An agent with 500 tools in context is slow and hard to trust. You give each agent a bundle of exactly the tools it needs, behind its own URL.

→ Every call is streamed and audited. And if your customer needs it to run in their own cloud, it can.

We're building for depth: the stuff that decides whether an agent makes it to production.

Happy to go deeper on any of this.

[Shrimithran @shrimithranr]

@yenkel You should meet @ravibits - our worlds at Scalekit and Auth0 overlap a little bit, will make the conversation more useful I guess.

[Shrimithran @shrimithranr]

@rajivayyangar @pipecat_ai @Vapi_AI @DeepgramAI @ElevenLabs Would add the likes of @scalekitinc @merge_api and @NangoHQ to the agent infra mix - to solve the integrations and mcp tooling at scale, securely.

[Tamilselvi Ramasamy @Tamil_2399]

back in may when we did our first edition of agents & bagels, i ate the leftovers alone. fast forward to october our 16th edition, we ran out of bagels 😄

SF @Techweek_ edition of @scalekitinc's signature agents & bagels with @nebiusai @tavilyai @tenki 🥯

[Shrimithran @shrimithranr]

Watched enough launches this past year to see there's one playbook now: pay a network of big accounts to boost you on cue.

It works. No shade to anyone running it.

But the "why" got lost.

Noise became the currency, and conviction is getting priced out.

[Tamilselvi Ramasamy @Tamil_2399]

this was @scalekitinc's 5th hackathon for the year, and i think we're getting better at figuring out how much people can actually build in less than 4 hours!

a little late, but here's a recap from our SF @Techweek_ hackathon with @cognee_ and @RespanAI!

the challenge: build a company brain that could pull context from different tools, remember things, and actually take action with the right access.

we had 8 solid submissions by the end of the evening, and some really fun demos. thanks to everyone who showed up and built with us. and to @tricalt and @HendrixLiu29208 for putting this together with us!

[Shrimithran @shrimithranr]

The easiest advice to agree with and the hardest to follow: show up every day.

[Shrimithran @shrimithranr]

Every conversation lately is about which agent to build next.

Over coffee with Adam Frankl, the OG dev marketer, we went back to first principles instead: how buyers make decisions. Agents haven’t changed that.

A few things that stuck 🧵

[Shrimithran @shrimithranr]

Those beliefs should decide everything:
– what you write about
– which news you react to, and which you skip
– what you’ll argue about in public
Engineers love smart people disagreeing in good faith. Give them something to disagree with.

[Shrimithran @shrimithranr]

The easiest advice to agree with and the hardest to follow: show up every day.

Working on it.

[Ravi Madabhushi @ravibits]

A customer-facing agent can work perfectly in a demo and still be nowhere near ready for production. We had a good conversation about this at our SF Tech Week session on building and deploying customer-facing agents, with @simonrohrbach, @hey_amandam, and @Homer_Wang.

A few things stuck with me.

1. Calling your agent once and seeing it work isn't testing: Amanda made this point well. You need evals around specific decisions, simulated conversations with different customer personas, and monitoring once agents are live. You can't manually call every agent every time something changes.

2. Your agent is only as good as the context it has: Simon Plain shared something interesting about knowledge freshness. Human support teams can give inconsistent answers. Documentation can go stale. The codebase often gets you closer to how the product actually behaves. And even if your knowledge is accurate today, your agent can drift as the product, models and human behaviour change. Getting the right answer is more than just retrieval. It's about knowing when your source of truth has changed.

3. Making the web accessible to agents shouldn’t come at the expense of the web itself: The web needs to be accessible to agents, but access can't come at the cost of overwhelming websites or ignoring their boundaries. There's a balance to get right.

A few good conversations with people building this stuff for real. Thanks to everyone who joined us!

[Shrimithran @shrimithranr]

@Dipanjan_Dey Our design team will be delighted to see this! GPT 6 leading the way is not a surprise at all. Great report @Dipanjan_Dey

[Shrimithran @shrimithranr]

@tricalt 🤯

[Shrimithran @shrimithranr]

@ishaansehgal @Tamil_2399 @scalekitinc Demo nights - 30-35%. Higher turn out if there is a marquee high value speaker on the panel. Typically offers greater engagement though pre and post event.

Breakfasts - 25%. We run these as no agenda, networking meet-ups at 8am. So 25% is already pushing the bar I think.

[Shrimithran @shrimithranr]

@ishaansehgal @Tamil_2399 can go into the details. Here is what we see for all the events we do at @scalekitinc

Curated dinners - 90-100%. Mostly for the peer network and pre event touch points.

Hackathons - 30-40%. Higher turn out if there are no competing hackathons on the same date. 1/2