Prad Biswas

Partnerships at @merge_api

[Merge @merge_api]

Every company manages two layers of AI. One helps employees do their work and the other runs inside the products customers use. Both need to be secure and connected to the right data.

This fall, Merge launched a product for each: Merge for Workforce and Merge for Products. In this recap @aj2w and @sarahraemazur, who lead product and engineering, demo each one end to end.

Merge for Workforce securely brings approved skills and company context into the coding agents employees already use. IT sets model budgets and plain-English guardrails once, like blocking confidential customer details from an agent’s Slack message.

Merge for Products gives teams building AI features Gateway for models, Agent Handler for tools, and Unified for customer data, with one setup every new customer reuses.

What have we been cooking: https://t.co/m8IXwULxtP

[Shensi Ding @shensi]

Introducing Merge’s Universal Context Layer.

It substantially decreases token cost while increasing accuracy.

Every company uses AI wrong:

Say your designer makes a deck using Claude. They teach Claude your design systems and typography.

Now a Marketing hire makes a deck. None of the information your designer taught Claude gets passed over… why?

Merge fixes this:

All knowledge and memory across your entire company gets stored inside our context layer.

When someone on the org teaches Al, that skill lives across the entire organization instead of staying locked in their session.

Your AI runs faster, cheaper, and with more accuracy. You don’t have to switch systems, incur more costs, or retrain anyone on your team, Merge runs invisibly in the background.

Book a demo here: https://t.co/aj3ecxk7zP

[Parallel Web Systems @p0]

We’re proud to partner with @merge_api on the launch of Universal Context Layer in Merge for Workforce, a new solution unifying ground truth from within a company’s internal tools with broad context from the open web, powered by Parallel.

[Prad Biswas @pradbiswas3]

@GilFeig @merge_api that's a lot of digits 🥶💯

[Gil Feig @GilFeig]

We're seeing the same thing. @merge_api Agent Handler calls are up 1220x this year and growing faster than ever.

[Prad Biswas @pradbiswas3]

@nishkachotai @merge_api @aidan_timmerman partnership gang 💪

[Prad Biswas @pradbiswas3]

@shensi Merge connectors are the best I've tried so far, have often seen more available tools beyond the public MCPs, and usually they have better and faster performance than the public ones for my agents

[Shensi Ding @shensi]

What’s becoming clear from every new agent company is that connectors are king.

Every user expects connectivity to everything, and the better the connectors, the more magical the experience.

We know - we’ve been building the best connectors for years.

https://t.co/uWkc1sVOr9

[Prad Biswas @pradbiswas3]

@merge_api these open source models are getting truly nuts

[Khairallah AL-Awady @eng_khairallah1]

this is f**king insane

you're paying premium prices for AI and using it to rename files.

renaming files. formatting a doc. cleaning up a transcript. writing a slack message.

every one of those runs on whatever model you picked last. which is (of course) the most expensive one available.

a cheap model does them identically. you just lit money on fire for no reason.

doesn't matter if you're one person on a subscription or 40 people on a company plan. same leak.

the fix is a routing agent:

→ small tasks go to a cheap model automatically
→ the expensive models stay for work that actually needs thinking
→ if you have a team, each group gets its own model list and its own limit
→ nobody picks anything. nobody changes how they work.

using AI doesn't save you money.

using AI efficiently does.

most people won't check their usage until something forces them to.

save this before your next bill.

[Prad Biswas @pradbiswas3]

@systemdesignone in my eyes token optimization infrastructure for the middle tier of models is as valuable as creating smarter frontier models

[Prad Biswas @pradbiswas3]

@aashatwt exactly, this benefits the smallest highly specialized agencies the most, who have the intellect & talent to take advantage of intelligent routing, model fusion, etc this is how those agencies are able to finally optimize spend and do a lot more for a lot less overhead on the P&L

[aasha @aashatwt]

do you actually understand what's happening right now
you can start a content agency this month with 2 VAs and a laptop.

b2b companies pay $4,000-$6,000/month to agencies with 5-6 people on payroll for content ops. it's not glamorous work, it's just volume, and every company needs it.

you don't need 5-6 people anymore. you need 2 VAs who can each run 3x their output with AI, and a control over what those VAs' models cost and what they can see.

here's how people fail at this: VA #1 runs the most expensive model on earth to reformat a blog post. VA #2 has an agent that can read every client folder you own.

Here’s how you can set it up properly from day one:
> VAs go in a group
> the group decides which models they can reach
> the group decides what those models can see, so client A's docs are invisible to client B's work
> tasks route themselves, cheap work gets a cheap model, no one chooses

3 clients at $5,000 = $15,000/month. two VAs, small tool bill, and you kept the margin instead of donating it to a model provider.

an agency this size used to take a year and a hire list. it takes a weekend now.

there is genuinely no excuse anymore.

[Prad Biswas @pradbiswas3]

@MaxDEagle we just made the only realistic way for companies to enforce AI spend budgets, spend control will be one of the most important pieces of infrastructure for companies as the AI adoption wave continues

[Kyle @spacegluder]

“Mom how did we get so rich?”

“Your father implemented Merge for Workforce”

[Prad Biswas @pradbiswas3]

@spacegluder kids can afford the nice christmas gifts because dad didn't blow it all on tokens

[Turner Novak 🍌🧢 @TurnerNovak]

Uber could have saved $750M with this