MD @z47_vc | Agenting agents | Building @DeVC_Global | past @DisneyPlusHS @Housing | 2X founder 3X CXO | Deep Learning Geek
Mumbai
Joined November 2009
- Tweets5K
- Following5.4K
- Followers3.2K
- Likes33.1K
aacash.eth - Aakash Kumar retweeted
it’s hard to explain the 2010s microservices fever dream to anyone who wasn’t there
every day on HN, we'd wake up to an article from a new startup about how they split their app into 300 services so they could infinitely scale (never mind that they only had 100 MAUs today)
so many companies never recovered from this
it turns out, replacing simple function calls with network calls that could randomly fail isn't great for shipping velocity
“- Martin: every bit of code doubles the ways a program can behave, which is why humans still own systems
- The real world is messier than AI's training data, self-driving took 20 years and $170B”
Engineering leaders told Grepr founder and CEO Jad Naous they spend 5 to 20% of their infrastructure budget on observability, and it's buying less and less reliability.
Jad, a former a16z partner, joins a16z's Martin Casado to discuss whether AI can run production systems as well as it writes code.
Grepr sits in a company's log stream, can scan a petabyte of logs a day, cuts observability costs by about 90%, and is building AI agents that use those signals to troubleshoot production issues.
How AI is changing engineering at Jad's 10-person company:
- A data lake feature that once took one engineer about six months took Jad 10 days
- The gap between okay and great engineers on his team "just multiplied 10X"
- He runs 3-4 agent sessions at once, with a "tech lead" agent reviewing every PR
Why running live systems is a harder problem for AI:
- Jad: AI can almost tune databases, but can't yet keep servers running on its own
- Martin: every bit of code doubles the ways a program can behave, which is why humans still own systems
- The real world is messier than AI's training data, self-driving took 20 years and $170B
0:55 From Stanford to a16z to Grepr
7:00 Why observability spend stopped paying off
11:00 From autocomplete to AI that trains engineers
13:10 Why AI widens the engineer skill gap
14:55 Syntax vs semantics
18:00 Inside Jad's AI workflow
22:55 Six months of work in 10 days
24:50 Can AI reason about how systems really run?
30:10 Why AI SRE tools start in the wrong place
32:30 Can AI run a distributed cluster yet?
37:35 Why engineers buy extra capacity over predicting
39:15 How AI could trace failures in production
43:45 Why AI for ops is harder than for code
49:55 Can AI do a VC's job?
52:05 Why self-driving took 20 years and $170B
57:05 Customers skipped the AI pitch for the 90% savings
YouTube: youtu.be/blkIGLlZePg
@jadtnaous @grepr_ai @martin_casado
I got a feeling once. Then I got it again. And feelings can’t be wrong. I agree with @TheIndianTruth_ that RBI governor should resign. I’m forming Jhingur Janta Party today! Domain registered.
First of many steps towards unleashing the harnesses=product=business maxim! Lfg 🚀@alokbishoyi97 and team @useRouterPlus
Getting your inference right shouldn't be hard.
@useRouterPlus (YC F26) is live: the right model and provider for your workload, at the best price.
check out : routerplus.com/capacity
aacash.eth - Aakash Kumar retweeted
AI agents are changing how we work and collaborate, but documents are still stuck in the pre-AI era.
Agents can now create beautiful, interactive decks, dashboards, and reports in HTML. But the moment you want to collaborate on them, everything breaks down.
Google Docs wasn’t built for rich, interactive HTML or AI agents. Feedback gets scattered across Slack and email. Every edit means going back to the agent, generating a new file, and sharing another link. No real-time collaboration. No single source of truth.
We built SlashDocs to fix this.
Think Google Docs, but built for AI agents and the documents they create. Host HTML and Markdown in one central hub. Share documents, manage permissions, and comment directly on the content, just like Google Docs.
Agents can read feedback and update the same document in real time. No duplicate files, no endless back-and-forth, and everyone stays in sync.
What started as a small internal experiment in one team has now scaled across @Razorpay. 28,000+ documents created. Over 50% of all documents generated at Razorpay now live on
SlashDocs.
And today, we’re opening it up to everyone. Self-hosted. Agent-agnostic. Fully open source.
AI agents have changed how we create documents. It’s time we changed how we collaborate on them.
Try it: razorpay.com/slash-docs/
aacash.eth - Aakash Kumar retweeted
Be profitable and run your company with maximal agentic loops
You don’t need to sell more of your co anymore
$10M profit per year reinvested is like an annual Series A no dilution
The best startups do this now. No whinging about the Series A/B crunch.
You don’t need saving.
Series A and Series B are the hardest rounds for founders today.
Founders launch a vertical AI SaaS company. They reach $1M-$3M ARR in 2 years or $5M-$10M in 3-4 years.
They go out to market with their 1x-3x growth. Almost no interest from investors.
If it's not the right category or a deep, long-term conviction bet, most investors stay away.
Founders are stuck with large pref stacks and a market that doesn't value this growth. They are neither sustainable (at their current burn) nor venture-fundable (without growth).
The exit options (if available) don't leave much for the team. In most cases, founders are required to join the acquiring company (but they aren't interested).
I talk to many founders who have been misadvised, and they keep grinding without making progress.
The Series A or B that didn't happen won't magically happen in 1 year with a little more progress. If the market moves much faster than your company progresses, you will always be behind. If you are told today to hit some metrics and come back, the market will have already moved by the time you return.
aacash.eth - Aakash Kumar retweeted
If you're going to survive in the AI world five years from now you have to:
1. Build for people that will never build for themselves (even if its incredibly simple to do so)
2. Make your product as close to free as possible so it doesn't even make sense to prompt and build. Then monetize in other ways (Payments, Capital, Ads, Insurance, etc.)
3. Leverage the only moats there are left: Proprietary data, network effects/marketplace dynamics, owned audience, hardware, physical stuff (supplies, etc.), offering services, regulatory, group purchasing and digital franchises.
Agreed
One of my more controversial bets: the AI feed will be the form factor of 2027!
Most people don’t know what to prompt, and they won’t prompt their way into complicated agentic workflows. With chat, we ask users for digital labor: figure out what AI can do, explain the task, provide the context, repeat. That’s a lot to ask if we want billions of people using agents every day.
Meanwhile, people already spend hours in feeds. Twitter, Instagram, LinkedIn. They know how to scroll, discover something useful, and act on it.
An intelligent system that knows you should bring you the next useful action. Here’s the email you need to answer, already drafted. Here are the latest sales numbers, with an update ready to send to your team. You approve, edit, dismiss, or jump into chat to go deeper. That’s how people will discover what agents can do, without having to invent a prompt first.
And you can put ads in a feed, one of the biggest business models on the internet. A system that understands your plans can recommend a relevant restaurant, product, or service, clearly labeled as sponsored. You get a reason to come back every day, useful work ready to approve, and a business model to fund the agents doing it.
aacash.eth - Aakash Kumar retweeted
imo in the context of this tweet, @deedydas makes a perfect argument. if you look at the size of outcomes, there's really no logical reason to build in india.
but in the larger context, it may not hold to be true. US is the largest economy in the world and one of the most entrepreneurial nations in the world. but it doesnt make sense for all 8bn people on the planet to take the below logic and relocate to US.
there will always be people all over the world migrating to other places and making a better life for themselves and that is a noble cause. there will also be people who will chose to stay back, and improve the country they are born in which is also a noble cause.
there will be some, who will be in between, begrudgingly moved to a new country in the chase of a better life but would like to be in their home country. atleast for that lot, India of today provides a lot more opportunities than india of a decade ago and that is undeniable.
the call of "build in india" is never about being better than the US. maybe someday we get there, but today our fight is to make india worth building in and I think every day we make progress there and we justify india as a good place to build for another day.
The smartest Indians continue to come to build in the US for the simple reason that the economic incentives are far far better.
Perplexity ($20B), Skild ($14B+), Baseten ($13B), Together ($8B), Glean ($8B), Modal ($5B), Rubrik ($25B), Harness ($5B), Blacksmith, Parallel, Greptile, CodeRabbit, Composio, Distyl ($2B), Resolve, Luma, Cartesia, Wispr, dMatrix, Arize and many more - all started by at least one Indian-born founder.
The US is a far easier to raise capital in with far less dilution. Most Indian companies are switching where they're domiciled to get access to the US capital markets. Every single Indian venture firm is trying very hard to invest in the US or risk not participating in the AI race (ironically, the management fees of venture firms are so high in India relatively that this is the one group that net of carry actually has incentive to be in India because they take home well north of a living wage whether or not funds perform do)
While Zomato ($35B now, $8B at IPO) might be the biggest outcome in Indian venture, Cursor ($60B), Reflection (potentially $20B+), World Labs ($8B), OpenRouter ($8B), HuggingFace ($12B) and of course the $1T+ big labs quickly make those outcomes seem small and happen on a much smaller time scale, with much higher IRR.
Engineers at these startups regularly get paid $1M/yr, and make $10M+ on exit. Even in BigTech, it is trivial to pull up levels fyi and see that if you're L6/L7+ with ~10 years of experience, you're making $1M/yr there too. And of course, we all know the slew of Indian CEOs of companies here, not to mention a huge bench of lesser known executives across the board in public and private companies.
I say all this because every time there is a slight immigration hiccup in the US, I hear the online pleas to "build in India", I struggle to understand why most engineers, academics or founders would do that net of desire to be close to family, failure to obtain visa and devout patriotism.
This is not a superiority thing or a US v India thing. The economic incentives at least for technologists to being in the US outweigh India by at least an order of magnitude.
aacash.eth - Aakash Kumar retweeted
It is so easy to gather views by picking up a few outlier examples and drawing up a conclusion for all.
I have spent plenty of time in SFBA as well as India over the past 25+ years of building/operating/investing and have come across talent in both places closely. I also know a fairly large number of folks working in tech both in the US (Silicon Valley) and India.
(1) Plenty of "smartest Indians" are staying back and choosing to build in India in spite of the constraints of lower capital. That "plenty" number is consistently growing year after year. And this has been true for a fairly long time now. So a blanket statement that "the smartest Indians continue to come to build in the US" is plain wrong. And it will be more wrong every year going forward.
(2) Most Indian companies are NOT moving their domicile to the US - ONLY THOSE who are building for the US market are doing so and that is the right thing to do to be closer to the customer, in their geo, aligned with that geo's setup/compliance/laws etc. This has nothing to do with India and everything to do with being setup correctly for the target market.
The call for "build in India" is a few people who say it again and again and need not be generalised. Today, talented Indian founders are independently deciding what they want to do with their lives, what is more important to them.
There are plenty of world class folks who are choosing to stay in India. Plenty of world class researchers who are choosing to move back to India after decades in the US.
And there are plenty of founders who are choosing to move to the US to build their by being closer to their customers and capital for their businesses.
We don't need to paint only one side of the story because it is literally one side. The other side is equally full and real.
So, if you really want to know what "the smartest Indians" are doing in 2026 look at the real data - it is not so hard to see.
The smartest Indians continue to come to build in the US for the simple reason that the economic incentives are far far better.
Perplexity ($20B), Skild ($14B+), Baseten ($13B), Together ($8B), Glean ($8B), Modal ($5B), Rubrik ($25B), Harness ($5B), Blacksmith, Parallel, Greptile, CodeRabbit, Composio, Distyl ($2B), Resolve, Luma, Cartesia, Wispr, dMatrix, Arize and many more - all started by at least one Indian-born founder.
The US is a far easier to raise capital in with far less dilution. Most Indian companies are switching where they're domiciled to get access to the US capital markets. Every single Indian venture firm is trying very hard to invest in the US or risk not participating in the AI race (ironically, the management fees of venture firms are so high in India relatively that this is the one group that net of carry actually has incentive to be in India because they take home well north of a living wage whether or not funds perform do)
While Zomato ($35B now, $8B at IPO) might be the biggest outcome in Indian venture, Cursor ($60B), Reflection (potentially $20B+), World Labs ($8B), OpenRouter ($8B), HuggingFace ($12B) and of course the $1T+ big labs quickly make those outcomes seem small and happen on a much smaller time scale, with much higher IRR.
Engineers at these startups regularly get paid $1M/yr, and make $10M+ on exit. Even in BigTech, it is trivial to pull up levels fyi and see that if you're L6/L7+ with ~10 years of experience, you're making $1M/yr there too. And of course, we all know the slew of Indian CEOs of companies here, not to mention a huge bench of lesser known executives across the board in public and private companies.
I say all this because every time there is a slight immigration hiccup in the US, I hear the online pleas to "build in India", I struggle to understand why most engineers, academics or founders would do that net of desire to be close to family, failure to obtain visa and devout patriotism.
This is not a superiority thing or a US v India thing. The economic incentives at least for technologists to being in the US outweigh India by at least an order of magnitude.
aacash.eth - Aakash Kumar retweeted
The three startup types
1. Model companies
2. Deployment companies
3. Data companies
You might start as one, but chances are you’ll end up being multiple
aacash.eth - Aakash Kumar retweeted
Rationality is sometimes wildly overrated.
The biggest decisions in life are not made on spreadsheets. Who you marry, what you choose to build and where you choose to belong.
If I get goosebumps when I hear A.R. Rahman sing Vande Mataram - not sure if I can put a price to that feeling.
15 years ago, I had the choice to move to the US. I chose India. Not because I had calculated that it would maximise my financial returns. But because I wanted to be here. Because I belong here. Because I am deeply optimistic about what we can change.
And even if that turns out to be a financially suboptimal decision - perfectly okay with it.
It makes me happy. It gives me purpose. It gives me the energy to show up every morning and build something that matters.
Not every decision needs to maximise wealth. Some decisions maximise meaning of who you are.
India first. India first. India first.
The smartest Indians continue to come to build in the US for the simple reason that the economic incentives are far far better.
Perplexity ($20B), Skild ($14B+), Baseten ($13B), Together ($8B), Glean ($8B), Modal ($5B), Rubrik ($25B), Harness ($5B), Blacksmith, Parallel, Greptile, CodeRabbit, Composio, Distyl ($2B), Resolve, Luma, Cartesia, Wispr, dMatrix, Arize and many more - all started by at least one Indian-born founder.
The US is a far easier to raise capital in with far less dilution. Most Indian companies are switching where they're domiciled to get access to the US capital markets. Every single Indian venture firm is trying very hard to invest in the US or risk not participating in the AI race (ironically, the management fees of venture firms are so high in India relatively that this is the one group that net of carry actually has incentive to be in India because they take home well north of a living wage whether or not funds perform do)
While Zomato ($35B now, $8B at IPO) might be the biggest outcome in Indian venture, Cursor ($60B), Reflection (potentially $20B+), World Labs ($8B), OpenRouter ($8B), HuggingFace ($12B) and of course the $1T+ big labs quickly make those outcomes seem small and happen on a much smaller time scale, with much higher IRR.
Engineers at these startups regularly get paid $1M/yr, and make $10M+ on exit. Even in BigTech, it is trivial to pull up levels fyi and see that if you're L6/L7+ with ~10 years of experience, you're making $1M/yr there too. And of course, we all know the slew of Indian CEOs of companies here, not to mention a huge bench of lesser known executives across the board in public and private companies.
I say all this because every time there is a slight immigration hiccup in the US, I hear the online pleas to "build in India", I struggle to understand why most engineers, academics or founders would do that net of desire to be close to family, failure to obtain visa and devout patriotism.
This is not a superiority thing or a US v India thing. The economic incentives at least for technologists to being in the US outweigh India by at least an order of magnitude.
aacash.eth - Aakash Kumar retweeted
Assorted things I've been mulling over regarding agents in the economy:
• Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive surplus to advance their interests against those of certain consumers: relative to the optimization capacity of companies, consumers can be inattentive, underinformed, irrational, etc. (Think, say, of some of the classic insurance upsells at the end of a booking process, which is typically priced substantially above what a regular policy would cost.) Herbert Simon introduced the idea of bounded rationality, and firms often end up benefiting from it. Thanks to personal agents, we will probably get somewhat more rational in how we engage with companies.
• How exactly will outcomes change? Well, certain kinds of price discrimination will work less well (how do coupons work if every agent hunts fastidiously for them?), and certain kinds of customer cross-subsidy will change (today, people who forget to cancel subscriptions subsidize those who don't). Taken across the economy as a whole, I'm not sure what the incidence of all of this will be.
• In corporate strategy, people have long debated the relative importance of distribution and product quality. Perhaps you've made something better, but does anyone know about it? Won't people just continue to buy the ACME Corp Mousetraps? Personal agents will, I think, act as a kind of structural subsidy for product quality. How would markets look different if individuals always spent at least 10 hours researching their purchases? On the margin, focusing on making a product better is, I think, going to become a more effective strategy for companies. This is good!
• It true, a corollary is that information about product quality will become more important and impactful. Today, most people have very limited ability to aggregate and integrate such data, but agents will have insatiable thirst for such signals. (It's often said that data is becoming more valuable because it helps in the training of models. That's obviously true, but I think there's a secondary way in which it's more valuable simply as a complement to cheaper intelligence.)
• A big question is whether agents will increase superstar effects (rational agents all settle on the same product) or increase dispersion (because everyone has slightly different tastes and preferences, which agents are good at eliciting, finally overcoming the artificial clustering we've been subjected to).
• Many internet companies have monetized demand routing, which is in turn often predicated on short attention spans. "I'll click on the first thing I see." This has led to some amount of inefficiency, as companies try to propitiate capricious ranking algorithms and incur various placement fees. It's not all deadweight loss (willingness to pay is itself a kind of signal, which is valuable to buyers), but it's not great. How will the nature and value of this routing change in a world of personal agents? I don't know the answer, but I think that the effects might be pretty big.
• Much of what I'm writing hinges on the assumption that personal agents will be on the consumer's side. I suspect that that will be the winning strategy, but whether it's true, and what it means to be true, involves a lot of other questions.
Taken as a whole, the market is a massively parallelized, decentralized, and highly imperfect value attribution machine, and, taking stock of all of the effects, it seems to me that the quality point may well be the biggest: that agents will change the nature of the backpropagation such that the rewards for better products increase. Maybe this is too optimistic, but I suspect (and hope) that companies that make things that they're proud of will feel that the universe is a little more partisan in their favor.
Just heard the clown roach-dip-kick use the phrase “30 saal ke bachche” (translation: 30 year old kids) to refer to himself and other dim wit puppet colleagues of his.
All these ‘kids’ should be put on a national open registry,one that the remainder of the civilised world can refer to and ensure that the kids get the right protection and safety net from real world.
They shouldn’t be burdened with employment and work and any worldly things. They truly deserve it. We have to protect the kids!
Real work should be the burden of only 18+ men and women
“The second major blocker is that world models are often autoregressive and diffusion-based. For those who know, this mix is a perfect storm for exponential drift”
This one’s going to be a hard pill to swallow for the physical ai community: world models are genuinely bad at rudimentary physics and it’s a bigger problem than you think.
Believe it or not, there was once a time when world modeling and robotics were two completely unrelated studies… today, it’s hard to even tell the difference between the two.
From mbrl to mpc and wams, the frontier seems to agree that world models are a critical component of physical intelligence; as a simulator for training, or even as part of the model architecture itself.
Often times, the point of a world model in this context is to serve as a gt that policies can train, or sample actions against. In simple terms, robotic policies look to world models to be the expert on how the world will react to its actions.
With this context, it’s easy to assume that world models have grown to simulate increasingly complex scenarios… so imagine our surprise when it struggled with tabletop demos you’d see in a middle school science class.
It’s simple to understand why it’s important for world models to have a good grasp of basic physics, but it’s much harder to understand why it currently doesn’t.
The biggest issue is that the vast majority of world models in the space are purely pixel-based. When you supervise on pixels alone, you don’t optimize for physical accuracy, you optimize for something that *looks* physically accurate.
The second major blocker is that world models are often autoregressive and diffusion-based. For those who know, this mix is a perfect storm for exponential drift. Every model output becomes the input for the next frame, so errors compound extremely quickly. This means that physical accuracy not only starts off poorly, but degrades considerably with repeated inference.
There are other challenges as well, but the point is that it’s hard to do accurate physics in world models right now. We put this research out to keep the community regulated and grounded when it comes to our current progress in the world model space. It’s absolutely critical that we understand where our models are failing, and why they’re failing so we can better contribute as a community.
aacash.eth - Aakash Kumar retweeted
Today we're reintroducing @quivlyai, backed by @ycombinator.
Quivly is the AI workforce for everything after the sale, built especially for companies with usage-based pricing.
Teams using Quivly take customers live in 7 days instead of 30, then expand them 4.3x on average.
Our agents turn kickoff calls into launch plans, chase blockers, catch risk and expansion signals, and have the full account story ready at renewal.
Closing the deal is just the beginning. Quivly handles everything after that.
I ask the same: Send the deck!
I write checks from $500k-$5m at @saastrfund
I ask one favor:
- don't send a lauch video
- don't send a Loom
- don't send an AI generated pitch that you wouldn't fund yourself
- don't ask for feedback
- don't send a brief teaser
Just ... Send The Deck
It still works
aacash.eth - Aakash Kumar retweeted
yes, you can now build an agentic workspace for your post-sales teams in an afternoon.
congratulations, you are now responsible for:
- connecting your CRM
- your data warehouse
- your support tool
- your call recorder
- slack
- billing
- re-authenticating all of them when a token expires.
-rate limits you discover while backfilling 2 years of tickets.
- mapping every customer's custom CRM fields.
- "Health_Score_v2_FINAL_use_this."
- one customer showing up as 4 accounts across CRM, support, and slack.
- 4 customers sharing one parent account.
- merging them.
- undoing the merge.
- mapping usage events to the right account.
- defining "active user."
- redefining "active user" for the next customer.
- teaching the AI what your columns actually mean.
- building one timeline per account out of 6 tools.
- keeping it fresh.
- turning a kickoff call into a launch plan.
- turning "we'll circle back on that" into a task with an owner.
- figuring out who the owner is.
- a customer portal the customer actually opens.
- making sure internal notes stay internal.
- spotting what's blocking launch.
- chasing the right person for it.
- chasing without being the 9th reminder this week.
- noticing usage dropped 15%.
- knowing whether it's a real problem or just seasonality.
- connecting it to the ticket sitting in another tool.
- booking the walkthrough before the customer asks.
- catching that your customer acquired another company.
- tying it to the right account.
- not tying it to another company with the same name.
- noticing your champion left before linkedin tells you.
- telling an expansion signal from a churn signal that is actually a feature request.
- pulling a year of what shipped, what changed, and value delivered for a renewal meeting.
- agents that draft the follow-up.
- agents that know which follow-ups to send without asking.
- agents that know which ones need a human to approve.
- writing back to the CRM without overwriting the AE's notes.
- showing the work: why the agent flagged this account.
- showing it in the app.
- in slack.
- through MCP.
- context windows.
- an account with 4,000 messages in 1 alack channel.
- evaluating whether any of this works.
- evaluating it again after a model update.
- a sync job that stopped sometime last week.
- monitoring all of this.
- monitoring the monitoring.
or you could let @quivlyai handle this one 🤷♀️
Yes, you can now build an inbox in an afternoon.
Congratulations, you are now responsible for:
- Deliverability.
- Bounce management.
- SPF, DKIM, DMARC.
- A domain that slowly drifts into spam.
- Finding out it why the hell it's drifting into spam?!
- Parsing emails from a mail server last updated in 2007
- HTML, plain text, and emails somehow containing neither.
- Outlook’s interpretation of HTML.
- Outlook’s other interpretation of HTML.
- Threading that breaks when someone changes the subject.
- Someone starting a new conversation by replying to an email from 2022.
- Forwards inside forwards inside forwards.
- CC, BCC, reply-all, and someone who really shouldn’t have clicked reply-all.
- Attachments.
- Attachments with malware..
- Inline images that become attachments.
- Attachments that were supposed to be inline images.
- A company logo attached to every reply, forever.
- Quoted replies.
- Distinguishing a quoted reply from the actual reply.
- Someone answering your five questions inside the quoted reply.
- Signatures longer than the conversation.
- The out-of-office that answers your out-of-office.
- Two autoresponders having a productive weekend together.
- Notifications that fire twice.
- Notifications that never fire.
- A reply sent from the notification itself.
- A reply to a notification about an internal note.
- Making absolutely sure that notes stays internal.
- Permissions.
- Two teammates writing the same reply.
- Drafts that sync across devices.
- Drafts that overwrite other drafts across devices.
- A confidently displayed “Saved” that was optimistic.
- Snoozed conversations.
- Time zones (!)
- Daylight saving time (!!)
- A conversation snoozed until a time that technically doesn’t exist.
- One customer showing up as three people across email, chat, and Slack.
- Three different people sharing one email address.
- Merging them.
- Undoing the merge.
- Search.
- Search that finds the thing you can literally see on screen.
- Webhooks arriving twice.
- Webhooks arriving out of order.
- Webhooks not arriving.
- Retrying a failed send without sending the customer six apologies.
- Rate limits you discover during your first traffic spike.
- Training your AI on your product.
- Scraping your website.
- Scraping the pages that need JavaScript.
- Not scraping your entire website footer into every answer.
- PDFs.
- PDFs that are actually pictures of PDFs.
- Keeping the content fresh.
- Knowing when content changed.
- Knowing when content disappeared.
- Making the AI forget the pricing page from last year.
- Conflicting answers across your docs, website, and past replies.
- Deciding which one wins.
- Chunking.
- Embeddings.
- Reindexing everything when you change embedding models.
- Retrieval that finds the answer, not just something with similar words.
- Web search tooling.
- Knowing when to search.
- Prompt injection hiding in a page you just scraped.
- An agent confidently promising a feature you don’t have.
- An agent confidently issuing a refund it shouldn’t.
- Tool permissions.
- Tool timeouts.
- Tool retries that issue the refund twice.
- Knowing when to hand off to a human.
- Actually handing off to a human.
- Not continuing to argue after handing off to a human.
- Evaluating whether any of this works.
- Evaluating it again after a model update.
- Token budgets.
- Context windows.
- A customer pasting an entire novel into the chat.
- WebSockets.
- WebSocket authentication.
- Reconnecting WebSockets.
- Reconnecting 10,000 WebSockets at once after a restart.
- A connection that looks alive but isn’t.
- A phone switching from Wi-Fi to mobile data mid-message.
- Messages that arrive once.
- Messages that arrive in order.
- Messages that arrive.
- Syncing read states.
- Unread badges.
- Typing indicators that stop typing eventually.
- A customer opening your widget in six tabs.
- Anonymous users becoming logged-in users.
- Logged-in users logging out on a shared computer.
- The iPhone keyboard covering the message composer.
- Safari.
- Keyboard navigation.
- A widget that must not slow down the actual product.
- Explaining that “sent” and “delivered” are different things.
- A help center.
- An editor.
- An editor that survives pasting from Google Docs.
- Images.
- Image resizing.
- Broken images.
- Article drafts.
- Autosave.
- Version history.
- Restoring the version before someone deleted half the article.
- Reordering nested categories without losing an afternoon.
- Slugs.
- 301 Redirects when slugs change.
- Internal links that now point nowhere.
- Working out which translations need updating after an edit.
- Search that understands what customers mean.
- Custom domains.
- DNS verification.
- SSL certificates.
- Renewing SSL certificates.
- Someone putting Cloudflare in front of your Cloudflare.
- Mobile layouts.
- Dark mode.
- Code blocks.
- Tables on small screens.
- Sitemaps.
- Canonical URLs.
- Accidentally indexing draft content.
- Accidentally deindexing published content.
- Cache invalidation.
- “I published it. Why does it still show the old version?”
- Making sure your AI sees the new version too.
- Spam.
- Phishing.
- Someone uploading malware as “a screenshot of the issue.”
- Someone pasting their CC details into chat.
- Someone asking you to delete every trace of that CC.
- Logs that also contain the CC.
- Backups that also contain the CC.
- Backups.
- Restoring backups.
- Discovering those are two separate features.
- An expired token.
- A background job that quietly stopped on Thursday.
- “Disk is full.” Sunday. 3 a.m.
- Monitoring all of this.
- Monitoring the monitoring.
Now you have two jobs 🤷♂️
aacash.eth - Aakash Kumar retweeted
What if,
for any scientific claim,
you can search 100M+ papers to find the strongest evidence for and against it
⚡️in 1 second?
That’s now possible with Evidence API! 🚀
paperclip.gxl.ai/evidence-ap…
For example, does drinking coffee reduce diabetes risk?