←
Ayan Barua885 posts
Ayan Barua avatar

Ayan Barua

@ayanb

Co-Founder @ ampersand.ai - previously founded Siftery and led engineering at G2. Relentlessly positive sum.

◷ Joined September 2008▧ 30 Photos and videos
Ayan Barua avatar
Ayan Barua@ayanb·Oct 6

Your AI is vaporware without deep integrations with your customers’ systems of record. Introducing @WithAmpersand: integration infrastructure for enterprise agents. We power 11x, Orb, and Square's ability to take agentic action in systems of record like Salesforce, SAP, NetSuite, and Workday. Ask anyone serious about building AI and they’ll tell you: - The SaaSpocalypse didn’t happen. The world depends on CRMs, ERPs, HRISs, and ITSMs. - Your customers customized their deployments beyond recognition. - Systems of record companies are basically monopolies. They never had to make their APIs and MCPs user-friendly. - Docs don't explain half the weird edge cases you'll hit. - One bad write can blow up your pilot or renewal. - Once you finally get it working, someone changes a field and it breaks again. The world's data lives in structured databases. AI needs a translation layer to work with it. So, for your AI to truly transform the way enterprises work, you'll need deep integrations built for: - scoped permissions - bi-directional actions - real-time speed for agents - custom objects, fields, and workflows for each of your customers We built Ampersand to power the future of software. AI didn't trivialize writing integrations. It made them the critical path. I believe that deeply, so I didn't make a launch video about Ampersand. Instead, it's the best builders I know explaining just how big of a challenge this is.

5:00
Ayan Barua avatar
Ayan Barua@ayanb·Nov 10

Building, deploying, and scaling enterprise agents is a monumental task. Much less building a revenue-generating enterprise agent. 11x is one of the best to do it. Congrats Prabhav!

@11x_official voice agents are on fire 🔥. Just signed another F500 financial services company. Seven-figure annual recurring revenue. Six weeks to deploy and beat their call center benchmarks across after-hours inbound and upsell/cross-sell. Better experiences for prospects & accelerates growth for our customers. Building good voice sales agents is incredibly hard - huge kudos to the team 🚀

Post attachment
Ayan Barua avatar
Ayan Barua@ayanb·Nov 2

Every customer action with your agent will move at the speed of agents. If your MCP, agent, whatever it is, consumes from their systems-of-record, you'll be updating their systems-of-record at the speed of agents. 1000x-10000x the speed of humans. Can your infra keep up with that? Will your customers trust you? x.com/hnshah/status/21127559…

Hiten Shah @hnshah Oct 21 Harnessification of software Your customers can build what you sell. Their agents can use it without opening it. Now software can take care of the work itself. We're in the early days of the harnessification of software. A

Ayan Barua avatar
Ayan Barua@ayanb·Nov 2

System of Records like NetSuite are terrified of startups building Systems of Action.

0:46
Ayan Barua avatar
Ayan Barua@ayanb·Nov 1

This is exactly why Salesforce is still around. Its UI is so bad, but people keep using it. Agents need access to Salesforce too, and they don't care about UI. Salesforce's years of not investing in design paid off (LOL)!

"Running Salesforce agentically inside of Claudeforce, Replit or Lovable is 10x-100x better than logging into the 'native' Salesforce. I'm not sure why anyone would ever log into Salesforce again in fact once Claudeforce is GA." We demo them all to you LIVE with our real data on this week's The Agents!

4:10
Ayan Barua avatar
Ayan Barua@ayanb·Oct 31

Vertical AI and niches 📈 We see this all the time, supporting agent integrations for a long tail of CRMs in every industry. Those CRMs are getting much stronger, they're not being eaten by the models.

The big bitter lesson question in the applied AI layer is that as models get better and better, what is the best way to diffuse that intelligence into an enterprise. Ironically, I’d argue that as models are getting more capable, and can handle longer running tasks and better tool use, the ability to differentiate on a domain by domain basis goes up instead of down. When models were quite limited in what they could do, ironically all you could be literally was a “wrapper” because you were effectively delivering tokens back to the user with a custom prompt or some limited RAG. But in a world of agents using tools, tasks that run on for hours or days, workflows that kick off agents, agent swarms that need to be coordinated against a goal, data sources that are domain specific, model routing that requires domain-specific routing, implementation that requires real change management of the workflow instead of “just type into this chat box”, it’s very very possible that specialization of these systems goes up more. Obviously this doesn’t apply to everything - the closer you are to the labs core use-cases the tougher this play gets, but I’d argue we’re going to see autonomous systems for a wide range of job functions that weren’t practical to build out before. We’ll see this in security, life sciences, healthcare, finance, manufacturing, and many other fields. Either way going to be a fun and wild couple of years.

Ayan Barua avatar
Ayan Barua@ayanb·Oct 31

"Finally, the harnesses and surrounding infra — sandboxes, file systems, data pipelines, etc. — allows for longer running agents, agents to be able to work on arbitrarily complex or long tasks, process data at enormous scale, and more." One of the areas where you need to use infra made after AI. Pre-AI infra for syncing data is built on a massive assumption that humans are doing a lot of the work, and are the primary users/consumers. Agent speed breaks these assumptions, and if you want to take advantage of this emerging form factor, pre-AI won't cut it. x.com/levie/status/211276968…

Pretty cool that we clearly have an emerging form factor for what AI might look like for the foreseeable future as autonomous systems dedicated to specific tasks or domains. This is a huge leap past the LLM wrapper days because the new expectation is that you can finally farm out more sophisticated work to the agent to tackle for you. And you can reliably trust that work can get accomplished properly (still with a human in the loop) because of far better tool and computer use, and the general intelligence of the models improving. 1) The tool and computer use capability increases in the models mean that you can provide the agent with far more granular access to external data systems and other software to operate. This means, in effect, the agent begins to execute workflows similar to how a person would have in that same function. And where there isn’t existing software, the agent just builds it itself. This is a huge unlock. 2) Next, the actual capability of the models are improving in just about every vertical domain. The models can make far better judgment calls in legal, do deeper bio research, scan for security issues in code, understand supply chain processes, and more. Obviously in many of these spaces then models still have worse intuition than people, but that will only get better. 3) Finally, the harnesses and surrounding infra — sandboxes, file systems, data pipelines, etc. — allows for longer running agents, agents to be able to work on arbitrarily complex or long tasks, process data at enormous scale, and more. Few of these components worked well for AI even a year ago, but we now have many of the core primitives necessary for more autonomous systems. When combined with the right UX, implementation, and change management for the human oversight and coordination, it’s clear that these autonomous systems will become quite powerful in a wide variety of enterprise workflows. We’re starting to see them in IT automation, cyber operations, drug discovery, manufacturing, AI research, and more spaces. You can almost imagine one or more of these systems for every role in the economy. Quite a bit of opportunity ahead.

Ayan Barua avatar
Ayan Barua@ayanb·Oct 30

This is what kills enterprise deals. You can't ask to connect to a F500 customer's SFDC data without a guarantee this won't happen. You need guardrails beyond a prompt that says "Please don't delete anything you shouldn't"

A third party agent deleted all our Salesforce records literally minutes after we deployed it Luckily, Replit had stored backups Agents are still ... unpredictable

Ayan Barua avatar
Ayan Barua@ayanb·Oct 30

I'd go further, none of this will be possible without the right infrastructure to support 1000x reads / writes to the systems of record agents interact with. It doesn't matter how quickly agent swarms work if their method of talking to SFDC is hobbled by rate limiting. x.com/levie/status/211062298…

Moving from chatting back and forth with agents, to having agents that you spin up in the background to do useful work for you is probably on the order of 100X or 1000X more token consumption than what we’re seeing today. Most work right now is essentially rate limited by our ability to process and work with information. Moving data between systems. Reviewing a document. Looking through code for security issues. Processing log data to look for even patterns. Looking up information about a prospective client. Almost all of knowledge work is constrained by these steps, and AI has become a huge unlock to that. So our first step was to use AI to do these individual tasks much faster for us. That was the chatbot phenomenon that we have been experiencing for the past 3+ years. But we can still then only augment the work that we remain in the loop for, and we’re highly limited by our ability to parallelize this work by our own bandwidth and context. But where we’re going is quite different. As AI models continue to improve at incredible rates, we can hand off more and more work to the agent. First it’s letting the agent run with a harder problem. Then it’s giving a few agents multiple parts of a task at once. But we’re not far off from being able to throw an arbitrary number of agents at a problem and just say “come back when you’ve accomplished this goal”. Now imagine that agent swarm for any problem we can think of. Protecting our codebases, data, and systems. QAing every change we make and make sure all our infrastructure is robust and does what it should. Looking through every document for potential risks. Auditing this company with vastly more data reviewed. And on and on. Most of this isn’t even replacing existing work we do, it’s all net new. These agents will get deployed as swarms by people, by workflows, by triggers, and by other agents. And none of this would be possible if the models weren’t getting better, and if the cost of AI didn’t make it affordable. Both of those trends though are playing out. Now the next frontier is just having enough compute. But this is where it’s heading.

Ayan Barua avatar
Ayan Barua@ayanb·Oct 29

UX, Identity, Memory, Sandboxes, Schedules...and identity is probably the toughest piece for the enterprise. Most agents use some fixed service account! You really need per-user, field-level read/write into the CRM/ERP so the agent isn’t God-mode.

Harrison Chase @hwchase17 Oct 24 Article The five components of building a "company harness" How do you build a company harness? We've built internal agents at LangChain across marketing, sales, and engineering, and they have completely changed how those teams work. They weren't easy to get

Ayan Barua avatar
Ayan Barua@ayanb·Oct 29

This is what enterprises are grappling with internally. If you're trying to sell your external agent to them, you'd better have permissions, security, and governance for data access figured out. Otherwise, why would they add another attack vector for agents? x.com/levie/status/211439126…

Good assessment of the on the ground reality for security in most large enterprises right now. The fragmented landscape of the risk surface is only going to get more gnarly, making it even more complex for enterprises to solve. There’s a never ending set of libraries to keep up with, tools to leverage, and sprawling infrastructure, data, and code to secure. Most large enterprises can barely keep up with this, let alone smaller startups or most companies outside of tech. In many cases enterprises need to work to modernize their tech stacks. Data, in most organizations, is highly fragmented which means you don’t really know the state of risk at any given time. Some systems are open up privileges too broadly, and others are operating primarily via security through obscurity. Lots of upgrading here to do. Once you can get your data and infra into a better spot, at least you have a chance for agents to help you secure the environment. Agent swarms can fan out, leverage any security tool, test various perpetuations of attacks, read through logs, process enterprise data for risk level, and more. This capability only emerged in the past few months, and none of it would be possible before we had long running agents and computer use good enough. This is a huge area of opportunity right now for every layer of the security stack across identity, firewall, network, code scanning, data protection, and more. And it’s at least one reason to be optimistic about the balance of offensive and defensive capability. But everyone does need to do the hard work of getting the basics right at the start.

Ayan Barua avatar
Ayan Barua@ayanb·Oct 28

The enterprise will not ask you what your moat is, but they will ask you why your agent burned through their entire SFDC quota in 30 minutes

Why Hand Wringing about Defensibility Is Probably Pointless: - analyzing how product value grows as a company scales is really hard -- this generally involves reasoning about conversion properties of an adaptive feedback system - analyzing how product value is impacted by competitors' scale is really hard -- also adaptive feedback system - analyzing competitive equilibrium is really hard -- autonomous differential equation - stochastic nature of serendipity and setbacks are really hard to bound - all this shit is dynamic based on macro factors, team, cyber threat environment etc. - market growth trumps all this stuff anyway, as fast growing markets create new white space which totally changes the value functions I've now read a lot of the key papers on this stuff, and most of it is either post hoc, or makes mature market assumptions which I just don't think are all that relevant with early stage tech startups. The tl;dr is invest in fast growing markets.

Ayan Barua avatar
Ayan Barua@ayanb·Oct 28

This is a real test for Salesforce's enterprise customers. We've been in the $2 Uber era of AI access and token cost...when you have to pay API pricing for agent calls, how much do things change?

Will customers pay Salesforce when they’re using their own AI agents? Salesforce plans to require customers to register external AI agents and monitor their calls into its systems. The Information’s Applied AI reporter Laura Bratton explains why customers are waiting for pricing details—and what’s at stake for software companies. “If software companies can't monetize when customers use their own AI, rather than paying for the software company's AI, how are they going to survive as AI agents become increasingly popular?”

1:45
Ayan Barua avatar
Ayan Barua@ayanb·Oct 16

The counterpoint is that agent-to-agent coordination — which is inevitable, since swarms will be either a tree or a graph data structure — seems like a super interesting and hard problem to solve. How do you evaluate agent-to-agent back-and-forth a very large number of times (so it isn't a law of diminishing returns)? You cannot likely throw a protocol at this since the semantics of this communication are very context-dependent

Moving from chatting back and forth with agents, to having agents that you spin up in the background to do useful work for you is probably on the order of 100X or 1000X more token consumption than what we’re seeing today. Most work right now is essentially rate limited by our ability to process and work with information. Moving data between systems. Reviewing a document. Looking through code for security issues. Processing log data to look for even patterns. Looking up information about a prospective client. Almost all of knowledge work is constrained by these steps, and AI has become a huge unlock to that. So our first step was to use AI to do these individual tasks much faster for us. That was the chatbot phenomenon that we have been experiencing for the past 3+ years. But we can still then only augment the work that we remain in the loop for, and we’re highly limited by our ability to parallelize this work by our own bandwidth and context. But where we’re going is quite different. As AI models continue to improve at incredible rates, we can hand off more and more work to the agent. First it’s letting the agent run with a harder problem. Then it’s giving a few agents multiple parts of a task at once. But we’re not far off from being able to throw an arbitrary number of agents at a problem and just say “come back when you’ve accomplished this goal”. Now imagine that agent swarm for any problem we can think of. Protecting our codebases, data, and systems. QAing every change we make and make sure all our infrastructure is robust and does what it should. Looking through every document for potential risks. Auditing this company with vastly more data reviewed. And on and on. Most of this isn’t even replacing existing work we do, it’s all net new. These agents will get deployed as swarms by people, by workflows, by triggers, and by other agents. And none of this would be possible if the models weren’t getting better, and if the cost of AI didn’t make it affordable. Both of those trends though are playing out. Now the next frontier is just having enough compute. But this is where it’s heading.