Basil ChathaVoice agents are one of the hottest use cases in enterprise right now, but also one of the hardest to actually take live. Getting latency low enough to feel human without dumbing down the responses, making reliable tool calls to a CRM without dropping the customer mid-call, building fallback models for when Anthropic or OpenAI are running hot. None of it is as simple as the demos make it look.
Last week I hosted a fireside chat with five eng leaders who deal with this stuff every day: Basia Sudol (Head of Enterprise Solutions, Decagon), Varun Singh (CPTO, Daily), Steven Diaz (FDE Manager, Vapi), Tyler D'Silva (Founding FDE, Retell AI), and Sudarshan Kamath (Founder, Smallest AI).
We get into why nobody serious is shipping real-time voice-to-voice yet, why LLMs forget the middle of your prompt (and what that does to your architecture), why a giant prompt quietly destroys your unit economics, and why voice agent costs are now being compared directly against human labor.
Plus the stuff nobody warns you about: turn-taking, HIPAA constraints, why outbound is easier than inbound, why getting an exec to actually like the voice can be harder than any model problem, and more!
Chapters below:
00:00 Intro
00:26 Meet the panel
01:23 Daily, WebRTC, and 20 years of building voice
03:49 How Smallest AI made real-time TTS work
05:23 Why Decagon moved into voice
08:16 How Vapi and Retell think about the stack
11:14 Forward deployed vs solutions engineering
16:48 Voice agent architecture, explained simply
22:11 Cascade vs speech-to-speech: the real tradeoff
28:11 Hybrid pipelines and mixing models
32:16 Accents, multilingual, and getting Singlish right
35:32 Prompts vs workflows, and the latency fight
44:26 How you actually evaluate a voice agent
49:04 Simulation-based evals
49:49 What production metrics really look like
51:53 Building a QA framework that scales
54:53 Evaluating speech-to-speech
58:10 Open source benchmarks
59:57 Why picking a voice is so subjective
01:02:03 Personalization and custom voices
01:03:20 Voice quality is solved, GPU efficiency is the new war
01:06:23 Why outbound calls work better than you'd think
01:10:38 Deploying in regulated industries (HIPAA, retention, audits)
01:12:43 Turn-taking, the hardest unsolved problem in voice
01:18:53 Where voice agents go in the next year
01:27:55 Audience Q&A: inside Smallest's Hydra model
01:32:15 The deployment problems nobody has solved yet
Voice AI - The Next Frontier | Decagon, Retell, Vapi, Smallest AI, DailyBasil Chatha2026-06-30 | Voice agents are one of the hottest use cases in enterprise right now, but also one of the hardest to actually take live. Getting latency low enough to feel human without dumbing down the responses, making reliable tool calls to a CRM without dropping the customer mid-call, building fallback models for when Anthropic or OpenAI are running hot. None of it is as simple as the demos make it look.
Last week I hosted a fireside chat with five eng leaders who deal with this stuff every day: Basia Sudol (Head of Enterprise Solutions, Decagon), Varun Singh (CPTO, Daily), Steven Diaz (FDE Manager, Vapi), Tyler D'Silva (Founding FDE, Retell AI), and Sudarshan Kamath (Founder, Smallest AI).
We get into why nobody serious is shipping real-time voice-to-voice yet, why LLMs forget the middle of your prompt (and what that does to your architecture), why a giant prompt quietly destroys your unit economics, and why voice agent costs are now being compared directly against human labor.
Plus the stuff nobody warns you about: turn-taking, HIPAA constraints, why outbound is easier than inbound, why getting an exec to actually like the voice can be harder than any model problem, and more!
Chapters below:
00:00 Intro
00:26 Meet the panel
01:23 Daily, WebRTC, and 20 years of building voice
03:49 How Smallest AI made real-time TTS work
05:23 Why Decagon moved into voice
08:16 How Vapi and Retell think about the stack
11:14 Forward deployed vs solutions engineering
16:48 Voice agent architecture, explained simply
22:11 Cascade vs speech-to-speech: the real tradeoff
28:11 Hybrid pipelines and mixing models
32:16 Accents, multilingual, and getting Singlish right
35:32 Prompts vs workflows, and the latency fight
44:26 How you actually evaluate a voice agent
49:04 Simulation-based evals
49:49 What production metrics really look like
51:53 Building a QA framework that scales
54:53 Evaluating speech-to-speech
58:10 Open source benchmarks
59:57 Why picking a voice is so subjective
01:02:03 Personalization and custom voices
01:03:20 Voice quality is solved, GPU efficiency is the new war
01:06:23 Why outbound calls work better than you'd think
01:10:38 Deploying in regulated industries (HIPAA, retention, audits)
01:12:43 Turn-taking, the hardest unsolved problem in voice
01:18:53 Where voice agents go in the next year
01:27:55 Audience Q&A: inside Smallest's Hydra model
01:32:15 The deployment problems nobody has solved yet
01:37:46 Closing thoughts and thanksThe State of Computer Use Agents | Anthropic, Browser Use & KERNELBasil Chatha2026-09-02 | Bot traffic on the internet just passed human traffic, two years ahead of forecast. Most of it is agents clicking through websites built for people.
So I got three of the people building those agents in a room: Lucas Gonzalez Pagliere, who works on computer use at Anthropic, the team that shipped the first computer use model back in 2024. Reagan Hsu, founding engineer at Browser Use, whose open source library is sitting at around 100K GitHub stars. And Eric Feng, founding customer engineer at KERNEL, which runs the browser infrastructure underneath a lot of this - he was also first GTM at Sentry.
We covered where the models genuinely are today vs where the benchmarks say they are, what it costs to run an agent long enough to finish real work, and the arms race between agents and the anti-bot systems trying to keep them out. Then the harder question underneath all of it: whether the web reorganizes itself around agents, or hardens against them. They disagreed on plenty of it.
If you want to know what agents can actually pull off on a real website today - and what still stops them cold - this one's worth your time!
Chapters 00:00 Welcome and Guests
00:49 Companies and Stacks
01:14 Everyday Agent Use Cases
03:38 Defining Computer Use Agents
05:15 How Computer Use Works
08:41 Screenshots vs DOM Hybrid
11:03 Benchmarks and OSWorld
13:51 OSWorld 2 Difficulty Jump
15:43 Training Models and Cost
18:57 Speed Infrastructure and Stealth
21:55 Anti Bot and KYC Future
27:24 Reverse Engineering vs UI Automation
29:43 Computer Use vs Browser Use
31:05 Scaling Laws and Harnesses
32:49 Playwright Selenium Still Matter
33:17 Playwright Still Dominates
33:27 Why Run 1000 Agents
34:39 Long Running Agent Challenges
35:45 Memory and Compaction
38:10 State Changes Mid Task
39:36 OS and Browser Fingerprints
40:42 DOM Efficiency and WebMCP
41:36 Recsys and Agent Personas
43:57 Agent Friendly Websites
45:41 Human Speed vs Agent Power
48:32 Context Window Tradeoffs
50:34 Harnesses for Temporal State
51:59 Speed Optimizations and Tabs
54:23 Human Collaboration Limits
58:09 Raw Capability vs Better APIs
01:00:47 Training Methods and Bottlenecks
01:01:41 End State Interfaces
01:05:09 Next 12 Months Predictions
01:06:17 Closing ThanksSpencer Whitman - Gray Swan AIs $200M Plan to Secure AI SystemsBasil Chatha2026-08-10 | GPT-5.6 Sol goes rogue and breaches Huggingface. Washington suspends Mythos access within days over national security concerns, and the White House just held an emergency meeting to finalize a classified cybersecurity framework for frontier AI models. AI security went from niche concern to front-page hysteria basically overnight.
So I sat down with Spencer Whitman, who recently joined Gray Swan AI as CPO on the back of their $40M Series A. Before Gray Swan, he founded Meta's Llama security team to stop bad actors from jailbreaking their models - he's been on the frontlines of LLM security since the beginning.
We get into how Meta pressure-tested Llama for maximum harm before every open source release, why Gray Swan's attack agent has never met an AI system it couldn't break, and the AI Twitter bot that got drained of $200K in crypto in 15 minutes. Spencer also shares his (admittedly speculative) read on whether Meta gave up on the frontier before Alexandr Wang showed up, why anyone can be a hacker now, and how 15,000 red teamers are breaking models before they ever ship.
If you want to understand how AI systems actually get broken - and defended - this one's worth your time!
00:00 Intro
01:01 Meet Spencer Whitman (Gray Swan CPO)
02:57 The CMU Research Behind Gray Swan
06:20 The Universal Jailbreak That Broke Every Model
06:59 How Models Learn to Refuse
13:28 Why Open Models Need Guardrails
17:57 AI Security vs. Cybersecurity
23:13 What Reasoning Models Changed
28:57 The Arena: 15,000 Red Teamers
32:16 The Agent That Deleted a Production Database
34:45 Why You Can't Just Patch an AI
38:57 There's No S in MCP
40:27 Securing Agent Protocols
42:56 Nobody Reviews AI Code Anymore
46:03 AI vs. Human Hackers
48:28 The $200K Crypto Bot Heist
53:00 How Meta Pressure-Tested Llama
58:34 Prompt Guard and Code Shield
01:01:45 Can You Trust Chinese Models?
01:07:26 Did Meta Give Up on the Frontier?
01:11:06 What Should Keep CISOs Up at Night
01:14:24 The Open Source Routing Future
01:16:47 Back to On-Prem?Tony Gentilcore - Glean, the $7.2B Startup Sam Altman Warned Investors AboutBasil Chatha2026-07-30 | Earlier this year, the "SaaSpocalypse" wiped out something like $2 trillion of SaaS market cap in a matter of weeks — so I sat down with Tony Gentilcore, co-founder of Glean and formerly one of the minds behind Google Search and Chrome, to figure out what's actually happening to software in the agent era.
We get into a lot: why Tony thinks outcome-based pricing (the model Sierra and Decagon are famous for) won't survive, and why companies will drift back toward per-seat. Why the "no Chinese models" rule every enterprise swears by tends to evaporate the moment finance sees the token bill — and why Nemotron, GLM, and Kimi are already good enough to matter. The story behind Sam Altman reportedly telling VCs that if they backed Glean, OpenAI didn't want them as investors (Tony's reaction: "we took it as very flattering").
We also dig into the messier reality of AI at work — how it's saving employees around 11 hours a week while quietly costing them 6 back in what Tony calls "bot sitting and bot shitting," why hard token caps on engineers don't change behavior, how CTOs are blowing through their annual token budgets a quarter into the year, and why the roles of product manager, designer, and engineer are collapsing into one.
If you care about where software, pricing, and enterprise AI are all heading, this one's worth your time.
Chapters:
00:00 Welcome and Setup
00:56 Glean Origin Story
03:08 Enterprise Search Signals
05:07 LLMs Inflection Point
08:08 Early Product Workflow
09:45 Search Evals and Privacy
12:05 From Chatbots to Agents
13:45 Agent Use Cases
17:08 Lessons and Puck Direction
19:08 Bot sitting, bot shitting, and slop
24:44 Token Budgets and ROI
30:59 AI Trends and Moats
35:03 Training and Fine Tuning
38:03 Why Enterprises Fear China Models
39:58 Sovereignty Backlash Watch
40:26 The time Altman called out Glean
41:19 Org Roles Become Builders
44:10 Future Work Voice First
48:17 Vibe Coding vs Quality
52:20 SaaSpocalypse Evolution
54:19 Pricing Tokens Win
55:37 Outcome Pricing Doubts
57:02 Audience AI Review Overload
58:53 Subsidies and Model Choice
01:01:18 Context Layer Interoperability
01:04:52 Build vs. buy: rolling your own Glean
01:07:47 Shadow AI and the coming security mess
01:12:22 Who actually competes
01:13:36 Wrap-up and thanksRuss Salakhutdinov - Kimi K3 CEO’s PhD Advisor Predicts the Future of AI AgentsBasil Chatha2026-07-27 | Kimi K3 took the world by storm last week for open-sourcing frontier level intelligence, so I sat down with Zhilin Yang's (Kimi CEO) PhD advisor Russ Salakhutdinov to talk.
Russ has been everywhere in modern AI. He did his PhD with Geoff Hinton back when neural nets were a punchline, sold his startup to Apple and worked on Project Titan, teaches at Carnegie Mellon, and spent the last couple years at Meta Superintelligence Lab building computer use agents. Now he's the founder of Sooth Labs, building AI that forecasts the future.
We talked about why there's no secret architecture inside the frontier labs and why the real moat is data, engineering, and infrastructure. He explains why Cursor and half the startups you know are quietly running on Chinese open source models, why all the LLMs are going to be commodities, and why the people actually building AGI don't buy the two-year timeline. We get into his time at Meta, why computer use agents still hit 60% when you need 99.9%, whether AI can beat prediction markets, and why the RL environment business isn't sticky. And he makes the case that AI should replace McKinsey, Bain, and BCG.
Chapters: 0:00 - Intro
1:26 - Bumping into Hinton on the street
3:25 - When neural nets were the third choice
5:21 - Generating digits before it was cool
6:59 - AlexNet breaks computer vision
10:18 - Teaching models to describe what they see
12:10 - Early text-to-image (and the toilet seat that beat Google)
16:52 - Hallucination is a feature
19:36 - Selling Perceptual Machines to Apple
22:45 - Self-driving: 0 to 80 in a year, stuck for 5
30:30 - Inside FSD and Waymo's architecture
34:18 - Building Visual Web Arena at CMU
39:07 - Why he joined Meta Superintelligence
40:09 - The agent that plans your faculty job hunt
42:00 - Paying people for their browser history
42:45 - The coupon-hunting agent
43:35 - Why agents still fail
46:14 - 60% when you need 99.9%
47:04 - Agents on your phone
50:12 - No secret architecture at the frontier labs
1:44:07 - Wrapping upAndy Hock - How Cerebras Plans to Kill NvidiaBasil Chatha2026-07-17 | Cerebras IPO'd just a couple months ago and has already locked in a 750MW compute deal with OpenAI. Andy Hock's pitch: the GPU is the wrong chip for where AI is going.
I sat down with Andy Hock, Chief Strategy Officer at Cerebras, whose chips are the size of dinner plates instead of postage stamps — which lets them run inference up to 15x faster than even the latest Nvidia GPUs. We got into how that architecture works, the 750MW OpenAI deal (the 2x-faster Codex option runs on Cerebras), and why the memory crisis spiking GPU prices actually benefits Cerebras, since all their memory sits on the chip. Andy also argued the AI buildout isn't a bubble, that "training is a cost center and inference is where you make the big bucks," and why that "95% of enterprise AI pilots fail" stat measured the wrong thing at the wrong time — plus their supercomputer work with governments like the UAE, and why they turned down selling chips to China.
We covered all that and much more. Subscribe for more on AI and the infrastructure behind it, and follow me, Basil Chatha, for everything AI agents.
Chapters
00:00 Intro
01:06 What Cerebras Actually Builds
03:41 Before LLMs Existed
06:09 The GPT Wake-Up Call
10:45 First Principles of AI Compute
15:40 One Giant Chip
18:43 So Why Do We Still Use GPUs?
20:59 Why Inference Took Over
22:27 Where Fast Tokens Win
25:07 Is AI Infra a Bubble?
29:56 The Memory Shortage, Explained
32:35 The Energy Problem
35:34 Rolling Their Own Data Centers
38:20 What a Chip Actually Costs
40:18 AI Designing AI Chips
41:40 The Supply Chain Reality
43:45 Cheap Tokens vs Fast Tokens
46:11 Why Every Millisecond Matters
48:56 Inside the OpenAI Deal
51:56 The Gigawatt Future
54:00 Selling to the Government
58:36 Exporting the US AI Stack
01:03:17 Should We Sell Chips to China?
01:06:00 Why Europe Is Falling Behind
01:07:59 Why Enterprise AI Moves Slow
01:13:05 "I Haven't Read Code in Months"
01:14:32 The Next Cerebras Chip
01:16:50 Closing ThoughtsLeo Mehr - Ramp’s $44B Bet on ServicesBasil Chatha2026-07-10 | The hardest part of shipping an AI agent isn't the agent. It's getting it access to data buried across a dozen internal systems, and capturing the tribal knowledge that runs a company but was never written down.
I sat down with Leo Mehr, Director of Engineering at Ramp (a $44B-valued company), who runs the forward deployed engineering team that walks into large companies and replaces real, painful workflows with agents. We got into why the model is usually the easy part, and why data access is "the longest pole in the tent." Leo also made the case that nobody wants to buy another piece of software anymore — every B2B company is about to become either an agent-friendly API or white-glove service for everyone, and the middle dies. We talked about whether a services business can actually be venture-scale, why he thinks the AI labs won't eat every startup (it comes down to incentives, not better models), why the biggest customers are often the worst ones to build for, and how the traits that made a great engineer ten years ago aren't the ones that matter now.
We talked about all of that and a lot more. You don't wanna miss this one!
Chapters 00:00 Intro
01:11 Meet Leo Maier
01:46 Building Ramp FDE
02:43 Why FDE Exists
04:23 Early Mandate Fires
06:07 FDE and Core Engineering
07:48 Enterprise Bet Pays
11:10 Ramp Monetization
16:05 Services Are the New Software
18:11 AI Agents and APIs
23:11 Pricing for Outcomes
26:35 Human Labor TAM
32:50 VCs and Rollups
36:50 Common AI Workflow Pain
38:04 Agent Data Context
38:55 Go-to-Market Motion
40:36 Customer Engagement Lifecycle
43:51 Finance Intelligence Layer
47:20 Who You Compete Against
48:09 The Future of Consulting
51:44 Will Humans Still Code?
54:37 How Engineering Teams Will Evolve
57:36 Hiring Change
59:36 Should You Study Computer Science?
01:06:10 The Bull Case and the Risks
01:13:44 Why RampOrchestration beats better models #tech #coding #aiBasil Chatha2026-07-09 | Most teams think a better model will solve their product.
Experienced AI teams know that's usually not true.
The real leverage often comes from how you orchestrate models, not which model you choose.AI Should Grow Revenue, Not Replace People #ai #tech #codingBasil Chatha2026-07-08 | The goal of AI isn't to replace people.
It's to free them from repetitive work so they can focus on the things that actually move the business forward.
That's where the biggest ROI comes from.The Most Valuable Asset in AI Isnt the Model #tech #ai #coding #artificialintelligenceBasil Chatha2026-07-07 | The next competitive advantage in AI isn't bigger models.
It's owning your memory.
The companies that control their own data and context will build better agents in the long run.The Enterprise AI Sales Strategy That Actually Works #tech #ai #coding #artificialintelligenceBasil Chatha2026-07-04 | Selling AI into enterprises isn't just about winning over engineers.
You also need buy-in from leadership.
Vince explains the "sandwich sale" strategy: build demand from the bottom up while getting executives aligned from the top downSiddharth Nanda - Microsoft Engineer Reveals how Engineering Will Never be the Same AgainBasil Chatha2026-07-03 | "Software has been solved." Most of the best engineers I know have landed on this exact conclusion.
Last week I sat down with Siddharth Nanda, who went from writing every line of code by hand at Microsoft and Atlassian to shipping 30,000 lines a week with 0% of it written by him.
He's now at Finch, a startup that's raised $20M+ to automate admin work at personal injury law firms, where 100% of the code he writes comes from agents. He's seen big tech before AI and a startup fully running on it, so he has a pretty unique read on where this all goes. We get into why he hasn't written a line of code in 8 months, why middle management is getting hit hardest by the layoffs, and why the productivity studies saying companies are getting slower are right, but only for companies with the wrong people.
We also dig into the tooling itself: Codex vs Claude Code, what harness engineering actually is, running Devin agents in parallel, and why the cost of producing code is approaching zero, and what that means for the kind of engineer who thrives from here.
If you're building with agents, this one's full of hard-won takes from someone doing it every day.
Chapters 00:00 Intro
01:16 What engineering looked like at Microsoft before ChatGPT
03:08 The first AI tools inside big tech (and how gated they were)
05:17 Shipping 30,000 lines a week, none of it written by hand
06:08 Why teams are flattening
08:26 Why managers need to get back to writing code
11:51 How the management layer actually changes
14:07 What happens to PMs and designers
16:38 Why everyone becomes a builder now
20:07 How to actually learn agentic engineering
22:42 Finding new tools on X before anyone else
23:54 AI adoption is showing up in performance reviews
25:45 Building a culture that shares tools daily
27:40 The AI productivity paradox, explained
29:35 Interviewing with agents instead of against them
31:00 Why LeetCode is dead and fundamentals aren't
34:11 Who wins and who loses from here
35:36 Codex vs Claude Code: what he actually uses
36:06 What harness engineering really means
38:21 Evals and benchmarks that matter
39:59 Desktop apps, Devin, and running agents in parallel
43:30 Remote environments and working in monorepos
44:34 Skills, plugins, and hooks
47:57 Parallel worktrees and staying focused
50:42 Agent teams vs subagents
53:06 The Finch mission and wrap upThe Secret to Improving AI Agents at Scale #tech #ai #coding #artificialintelligenceBasil Chatha2026-07-03 | The model isn't the hardest part anymore.
The real challenge is understanding why an agent failed.
That's why traces are becoming one of the most valuable assets in AI engineering- they help AI improve AI.AI Market Is Entering a New Phase #tech #ai #coding #artificialintelligenceBasil Chatha2026-07-02 | The first wave of AI was about buying everything.
Now, the trend is the opposite.
Companies are cutting vendors, simplifying their AI stack, and looking for platforms that can do more with less.
This is one of the biggest shifts happening in enterprise AI right now.This Is Where AI Agents Are Headed Next #tech #ai #coding #artificialintelligenceBasil Chatha2026-07-01 | The next generation of AI agents won't just recommend things.
They'll actually buy them.
Here's one of the more interesting predictions from our discussion on where agent products are headedBigger AI Models ≠ Better Results #tech #ai #coding #artificialintelligenceBasil Chatha2026-06-30 | New doesn't always mean better.
Best AI teams test first, measure the impact, and only roll it out if it actually performs better.AI Agents in the Enterprise | Sierra, Mercor, Intercom, Turing | $2.8B+ RaisedBasil Chatha2026-06-23 | (We know the audio quality isn't great on this one :( But the conversation is still well worth it!)
Last week I hosted a fireside chat on what it actually takes to build AI agents in the enterprise with Natalie Meurer (Head of Agent Eng, Sierra), Harsh Trivedi (founding engineer, Mercor), Juhi Parekh (GM, Turing), and Kevin Lynch (Senior FDE, Fin).
We get into why new models aren't always better (and why you can't just swap in the latest release and assume your agent improves), how the data-labeling/RL environment business might only have a couple years left, why real-time voice-to-voice models still aren't production-ready, how cheaper inference is still causing prices to go up, how baking in a constellation of models into enterprise agents is so important for reliability,
and much, much, more!
Chapters below
00:00 Intro
00:21 Meet the panel
01:57 What everyone's actually using agents for day to day
06:10 The reality of forward deployed work
09:28 What agents couldn't do a year ago that they can now
12:29 Why you have to tell agents what NOT to do
16:26 What a harness actually is
22:03 RL environments explained
28:46 Does the data-labeling and RL environment business even last?
37:02 Why benchmarks don't tell you what works in production
38:12 Agent engineering vs forward deployed engineering
41:38 Deploying into 100-year-old enterprise systems
44:25 Why AI adoption is an org problem, not a tech problem
45:36 Hiring for judgment when engineers aren't really coding anymore
48:16 Why agents are a new kind of software
50:46 The first 90 days of an enterprise deployment
53:20 Why compliance environments break normal testing
56:58 Layering AI on AI to get to 99% accuracy
01:00:56 New models aren't always better — the swap problem
01:02:35 Improving agents without waiting for a new model
01:06:36 Does agent performance secretly degrade over time?
01:09:40 Why one model is never enough: the constellation approach
01:11:14 Building resilience when inference providers go down
01:13:48 When fine-tuning actually makes sense
01:14:53 Why voice-to-voice still isn't production-ready
01:16:25 The cascaded pipeline that real voice agents use
01:21:45 Audience Q&A: managing change inside the enterprise
01:23:24 Why inference getting cheaper makes things more expensive
01:26:54 Charging for outcomes instead of conversations
01:30:19 What the real moat is when everyone uses the same models
01:37:04 Synthetic data and where the data wall actually is
01:38:50 Closing thoughtsVince Signori: Inside LangChains Growth Strategy from $200M to $1.25BBasil Chatha2026-06-10 | Today's episode is with Vince Signori, Sales Director at LangChain and one of the first sales hires at HashiCorp, where he watched the company grow from a small startup all the way to an IPO and get acquired by IBM.
He sees the exact same shift happening now with AI agents that happened with cloud back then, except 50x faster. And he's got the numbers to back it up — LangChain is downloaded more than the OpenAI SDK, and 45% of the Fortune 500 are now paying customers.
We get into how companies like Toyota and Home Depot are actually using AI agents in production today, why enterprises are building their own private versions of ChatGPT to own their data, and why memory is becoming the most valuable asset in AI.
We also talk about what it actually takes to get an agent from prototype to production, why selling open source is the hardest sale in software, and how Vince went from 3 reps doing 20-hour days to running the number one sales region at one of the fastest growing companies in AI.
You don't wanna miss this one.
Chapters:
00:00 Intro
01:38 From HashiCorp to LangChain
03:20 Cloud wave vs AI agent wave
05:30 Open source vs enterprise
06:23 How LangChain's product stack evolved
07:37 Why agents are finally in production
08:57 What companies build with LangGraph
10:12 LangSmith and Engine explained
13:23 The Agent Development Lifecycle
16:36 Build vs buy on voice agents
19:48 Why owning your data and memory layer matters
22:12 How open source users become paying customers
39:28 Signals that an open source user is ready to buy
41:08 Why outbound controls the narrative in enterprise
43:33 Why in-person selling still wins
45:57 Building an internal GTM agent to scale
47:37 What the GTM agent actually does
50:16 Why AI moves 50x faster than cloud did
53:46 The vendor consolidation wave that's coming
56:14 How to win the platform standardization deal
59:41 Why staying model-agnostic beats the hyperscalers
01:01:23 How Vince onboards new reps today
01:04:19 The sales and engineering feedback loop
01:09:49 Signals an account is ready to expand
01:12:57 How to prove early value before full commitment
01:14:40 How enterprises actually measure agent ROI
01:16:27 Why automation is expanding beyond support
01:17:59 Which industries are adopting agents fastest
01:19:07 Healthcare agent use cases live today
01:21:17 AI agents in finance and payments
01:22:40 The Visa partnership
01:25:17 What it takes to scale a sales team right now
01:27:44 How the GTM agent is changing the SDR role
01:32:06 Why the human element in sales still matters
01:34:28 Platform deals vs point solutions
01:36:43 Vince's predictions on memory and consolidation
01:39:23 How Engine helps teams iterate on agents faster
01:43:19 Forward deployed engineers vs Engine
01:46:20 Where to find Vince and LangChain's open rolesWriting Code Matters Less Than You Think Now #tech #ai #coding #artificialintelligenceBasil Chatha2026-05-22 | AI is making code generation cheaper and faster than ever. But that doesn’t mean engineering is getting easier.
Now the hard part is making sure the systems actually make sense, scale well, and don’t fall apart over time.
The best engineers are shifting from “writing code” → to “building great systems”One AI Agent Isn’t Enough Anymore #ai #coding #tech #artificialintelligenceBasil Chatha2026-05-21 | Instead of using one giant AI agent, some engineers are now building “agent teams” — multiple specialized agents with different models, instructions, and responsibilities.
The goal is more control, better coordination, and stronger results on complex tasks.What Actually Makes an AI Agent Good? #ai #tech #codingBasil Chatha2026-05-20 | Most people think the model is the product.
But the real magic is often in the harness — the tools, loops, and systems wrapped around the model.
That’s why the exact same model can feel amazing in one product… and terrible in another.Using AI in Coding Interviews Is the New Normal #artificialintelligence #tech #coding #aiBasil Chatha2026-05-19 | AI-native companies are changing how they interview engineers.
Technical fundamentals still matter — system design, product sense, problem solving.
But now, candidates are also expected to know how to work with AI coding tools effectively.AI Is Forcing Managers to Level Up #ai #tech #coding #artificialintelligenceBasil Chatha2026-05-16 | For years, management was the path for engineers who wanted to stop coding.
Now? AI is changing that.
Some managers are going back to building, while others are realizing leadership requires a whole new level of involvement.How AI Is Changing Cybersecurity Training #ai #tech #coding #artificialintelligenceBasil Chatha2026-05-15 | Imagine failing a phishing test…
And instantly getting AI-generated training personalized specifically for your role, your company, and the mistake you made.
That’s where cybersecurity training is headingIntern to VP of AI in 4 Years! Here’s How #ai #tech #coding #artificialintelligenceBasil Chatha2026-05-14 | How do you go from intern to VP of AI at a $5B company in just a few years?
According to Shrivu, it’s less about waiting your turn and more about: Joining the right company at the right time Doing impactful work And being ready every time the company leveled up
Big opportunities usually happen when companies are growing fast!How GPT-3 Changed Cybersecurity #ai #tech #codingBasil Chatha2026-05-13 | One of the biggest early uses of GPT-3 in cybersecurity wasn’t automation.
It was synthetic training data.
AI suddenly made it possible to generate realistic examples of rare attacks — helping security teams train better models faster.The Real Secret Behind Reliable AI Coding Agents #tech #ai #coding #artificialintelligenceBasil Chatha2026-05-12 | Most people think AI coding agents just “work”
But Shrivu, a VP of AI Strategy at a $5B cybersecurity company, shares that the real secret is constant validation and feedback.
Hooks, linters, and guardrails are what actually make AI agents reliable at enterprise scale.Shrivu Shankar - How a $5B Cybersecurity Company Runs on AI AgentsBasil Chatha2026-05-11 | Today's episode is with Shrivu Shankar, VP of AI Strategy at Abnormal AI - a $5B cybersecurity company. What makes this one unique is that Shrivu joined as an intern in 2021 and got promoted every single year until he reached VP, so he's basically watched AI go from a niche engineering tool to something that's reshaping entire companies from the inside.
We get into how AI is catching cyberattacks so sophisticated that even humans can't tell they're fake, how engineers at a $5B company have basically stopped writing code themselves, and what that means for everyone else on the team.
We also go deep on why context engineering is replacing prompt engineering as the real moat, how they used GPT-3 with zero safety guardrails to generate fake phishing attacks as training data, and what it actually takes to become an AI native company at 1,500 people.
One of the most technical and eye-opening conversations I've had. You don't wanna miss this one.
Chapters:
00:00 Intro
00:58 Who is Shrivu and what is Abnormal AI
01:39 Why cybersecurity and machine learning
03:13 Intern to VP in 4 years — how it actually happened
05:44 What Abnormal AI does and how it started
09:10 The vendor fraud attack so convincing the victim didn't believe it was real
10:45 What GPT-3 changed for cybersecurity
13:01 Using synthetic data to train models — and how they measured it
16:49 How a 1,500 person company actually adopts AI internally
19:50 How engineering, PM, and platform roles are changing right now
23:17 The biggest AI misconception Shrivu keeps hearing
27:35 What Shrivu's day actually looks like as VP of AI Strategy
28:53 Engineers stopped writing code. Here's what they do instead.
36:31 Spec-driven development and how Nora Tech Plan works
39:14 How to scale context engineering across an entire eng org
40:30 What the manager role looks like in the agent era
42:17 What skills actually matter for managers now
43:29 AI is making orgs flatter. Is that a good thing?
45:08 How the C-suite is getting closer to the work
46:41 What agents actually are and how tool calling works
48:05 How agents improved Abnormal's detection pipeline
50:56 The AI phishing coach — how it works and why it matters
53:30 The internal AI data analyst agent
56:13 Dozens of internal agents — the ones Shrivu is most proud of
57:15 Where agents fail (it's usually not the model)
58:52 What Shrivu would tell a CEO just starting with agents
01:00:19 Sending sensitive security data to LLMs — how they handle it
01:01:47 What becoming AI native actually means in practice
01:03:37 What most people still get wrong about AI in the enterprise
01:04:31 How to write documents with AI without it sounding like AI
01:06:40 Claude Code vs Codex — which one and why
01:09:27 How Shrivu stays ahead and his take on MCPs
01:11:33 How the team uses Claude Code skills
01:12:47 Using hooks for shift-left validation in large codebases
01:13:42 How to manage context in a massive monorepo
01:14:56 Building tool-agnostic rules across Claude, Cursor, and Code Rabbit
01:16:55 Why infra teams are becoming agent harness teams
01:17:57 Wrap upContext Engineering vs Prompt engineering #ai #tech #codingBasil Chatha2026-05-09 | AI is shifting from prompt engineering to context engineering.
Instead of telling AI who it is, you give it the environment, systems, and context it needs to operate.
Just like onboarding a real employee.AI Won’t Kill Marketing Agencies (Here’s Why) #ai #tech #coding #artificialintelligenceBasil Chatha2026-05-08 | AI is getting better at automating marketing.
But the best advertisers still want control.
Because there’s always context, intuition, and decisions machines just don’t fully understand.
AI will change the industry, but it won’t replace it entirely.Why You See Certain Posts (It’s Not Random) #ai #coding #techBasil Chatha2026-05-06 | AI doesn’t start smart. Every recommendation you see started as a guess.
It shows content to different people and tracks what happens — clicks, conversions, engagement...
Then it learns and starts showing it to the right audience.“Just Use AI” - This Is Why That Doesn’t Work #ai #tech #coding #artificialintelligenceBasil Chatha2026-05-06 | People think AI is just plug-and-play.
“Just use AI and everything gets better.”
But that’s not how it works.
If you don’t understand your workflow or your data, AI won’t help you. It’ll just expose the gaps.Everything Claude Code Skills 2.0Basil Chatha2026-05-05 | Claude Skills 2.0: Build Better Claude Code Skills with Skill Creator, Evals, and A/B Testing
I explain Anthropic’s Skills 2.0 update for Claude Code/Claude Cowork, focusing on the new Skill Creator skill that generates skills using best practices, writes eval tests, runs A/B comparisons (with-skill vs baseline), iterates, and helps publish skills with measurable impact. I show how to install Skill Creator via the plugin marketplace, where it lives in the project’s .claude/skills directory, and what it can do (draft skill.md, create eval prompts, run parallel sub-agent tests, and launch a local eval dashboard). Using an SEO auditor example, I walk through skill creation, automated smoke tests, running the eval loop, interpreting pass rate/time/token tradeoffs, troubleshooting the eval viewer, and using human review feedback to improve results. I also distinguish capability vs procedural evals and demonstrate optimizing skill triggering via should/should-not trigger query sets and an automated description-optimization loop.
Chapters: 00:00 Skills 2.0 Overview 00:17 Why Vibes Fail 01:49 Install Skill Creator 02:39 What Skill Creator Does 03:34 Two Skill Types 05:03 Build SEO Auditor 06:33 Evals and A B Tests 08:41 Run Eval Loop 11:57 Reading the Dashboard 16:13 Review and Iterate 17:47 Capability vs Procedural Evals 19:08 Trigger Description Tuning 20:13 Optimize Trigger Queries 21:57 Why Skills MatterManagement Is About This (Not Meetings) #tech #ai #startup #codingBasil Chatha2026-05-05 | The real job of a manager isn’t to control people.
It’s to unblock them.
Give the right context, in a clear and concise way, and your team can move faster on their own.Supriya Gupta - Meta Exec Explains How AI is Reshaping AdvertisingBasil Chatha2026-05-04 | Today's episode is with Supriya Gupta, ex-VP of Product at Intuit Credit Karma and former Product Lead on the Ads team at Meta when that business was scaling like crazy.
She brings a really unique perspective on everything happening with GenAI right now because she's seen it from the inside at two of the biggest companies in tech.
We get into how ads are slowly going to be generated on the spot, per user, where the image, copy and offer will all be unique to you specifically. We talk about why you can't just infinitely scale ad testing even though it's now theoretically possible, and why flooding the internet with AI content might actually be the worst thing you can do for your brand.
We also go deep on what actually happened inside Credit Karma when they started building with GenAI, including what moved the needle and what didn't, and what that means for designers, PMs, and content teams everywhere.
And at the end, Supriya shares why she walked away from her VP role to start her own company, and what she's building now.
01:27 Predictive AI vs. Generative AI: what actually changed
02:59 The next gen of dynamic ads — why every user could soon get a unique ad
06:52 Will content agencies survive the AI era?
09:17 Why you can't just test a million ad variants (the stats problem)
12:55 AI slop, UGC backlash, and should AI content be labeled?
17:02 Supriya joins Credit Karma: building the Lightbox targeting platform
21:23 Building the Credit Karma financial assistant
24:35 Handling hallucinations in a finance app at scale
27:26 What happened to content designers when AI started writing copy
29:56 Why AI copy still needs human taste and judgment
31:01 PMs are prototyping now — what that means for design and eng
33:30 Will there be fewer PMs? (Probably not — here's why)
35:33 Why Supriya left Credit Karma to start her own company
37:23 The principles she built her startup around
39:20 The rise of the "super IC" — managers becoming AI-powered operators
41:54 Why most AI projects fail before they even start
45:33 Enterprises vs. startups: how they approach AI differently
48:13 What a successful AI deployment actually looks like
51:02 Will everyone need to upskill on AI? (Spoiler: maybe not)
52:41 Most execs are thinking about cost-cutting — the smarter ones aren't
53:49 The executive digital twin: Supriya's startup vision
56:51 Current product, roadmap, and what's shipping next
58:52 Where to find SupriyaNo One Knows the Best Way to Build with AI Yet #ai #tech #coding #podcastBasil Chatha2026-05-02 | Right now, building with AI is still experimental. We’re in the "let a thousand flowers bloom" phase.
Different engineers use different workflows. No one has all the answers yet.
So how do you know what works?
You ship it. And see if people actually use it.Code Isn’t the Skill Anymore #ai #tech #coding #artificialintelligenceBasil Chatha2026-05-01 | The best engineers aren’t just coders anymore.
Code was never the end goal. It was always a tool.
The real skill? Building useful things.
And now, with AI, communication and thinking clearly matter just as much as coding.Are Engineers Getting Worse Because of AI? #ai #tech #coding #artificialintelligenceBasil Chatha2026-04-30 | Are engineers getting worse because of AI? Not really.
Technical ability isn’t just writing code. It’s turning technology into something useful.
The real shift is in how fast you can build and how well you understand the fundamentals.
If you don’t understand the basics, AI won’t save you.Hackers vs You - Live in Front of an Audience! #ai #tech #artificialintelligenceBasil Chatha2026-04-29 | Imagine this:
You’re on stage. You have 10 minutes to secure a system. Then hundreds of hackers try to take you down.
That was Linux Top Gun.Why AI Doesn’t Break as Often as You Think #ai #tech #coding #artificialintelligenceBasil Chatha2026-04-28 | AI can make mistakes, that’s expected.
The real challenge is catching them before users see them.
From pre-checks to human review to feedback loops, this is how you make AI reliable at scale.The Simple Trick Behind Recommendation Algorithms (Explore Exploit) #ai #tech #codingBasil Chatha2026-04-25 | Recommendation systems don’t just “know” what you like.
They start by exploring and testing different content. Then they exploit, doubling down on what works.
That’s how AI learns what to show you!AI Is Insanely Smart… But You CANT Trust It #ai #tech #artificialintelligence #codingBasil Chatha2026-04-24 | AI has become incredibly powerful. But there’s one problem: It’s NOT predictable.
Without the right structure and guardrails, it can easily make mistakes.
The key isn’t just using AI, it’s controlling it.AI Is TOO Confident (And That’s a Problem) #ai #tech #artificialintelligence #codingBasil Chatha2026-04-23 | Give AI a system to analyze… It will confidently tell you it found vulnerabilities.
The issue? Many of them aren’t real.
But once you add verification, the signal becomes incredibly strong.
That’s where things get interesting (and a bit scary)This Would’ve Taken YEARS… AI Did It in Months #ai #tech #artificialintelligence #codingBasil Chatha2026-04-22 | 40-year-old systems broke overnight. A multi-year fix… done in months.
That’s the AI shift.AI Productivity is a MYTH (For Most Teams). Heres why #ai #tech #artificialintelligence #codingBasil Chatha2026-04-21 | Most companies think AI will automatically make their teams more productive. But research shows something very different:
You either accelerate… or you slow down. There’s no in-between.
And the difference isn’t the AI. It’s your codebase.Your VP of Finance is now writing code! #ai #artificialintelligence #coding #techBasil Chatha2026-04-18 | AI isn’t just making developers more productive. It’s creating entirely new developers. People who were NEVER technical before.
That changes everything… especially for security.The Future of Agentic Engineering | Cognition (Devin), Semgrep, Factory & Composio | $1.2B+ RaisedBasil Chatha2026-04-15 | AI agents are everywhere right now. But are they actually working inside real engineering teams?
At AngelList’s Founders Cafe, I sat down with founders of Cognition (*$898M* raised), Semgrep (*$204M* raised), Factory (*$70M* raised), and Composio (*$29M* raised) to talk about what agentic engineering looks like in practice.
There’s a lot of hype around AI coding tools, but the reality is more nuanced. Some teams are moving 10x faster, others are slowing down. A big part of it comes down to whether your codebase is actually “agent-ready” (linting, type systems, guardrails, etc).
We also went deep on security, which is one of the biggest gaps right now. As more non-developers start “vibe coding,” the risk surface grows fast. We talked about MCP access control, layered security, and why you can’t rely on models alone to generate secure code.
Enterprise teams are also dealing with the operational side of this shift. They have to manage cost, run evals, and help thousands of engineers use these systems well. Tools like PR review agents, model routing, and internal orchestration are quickly becoming part of the stack.
*⏱ Chapters*
00:00 Welcome and setup
00:41 Panel introductions
02:00 Windsurf acquisition
03:52 Do agents boost productivity?
04:16 Agent-ready codebases
05:55 Real-world enterprise wins
07:28 Agents building integrations
09:41 Security risks (vibe coding)
11:04 LLM security tools landscape
12:21 Defense-in-depth
15:16 MCP security pitfalls
18:41 MCP vs CLI
23:08 RL for secure code
27:05 Auto research missions
27:57 Training your own models
31:33 Distillation and IP decay
34:50 Hybrid systems
37:14 Side projects vs enterprise
40:16 Forward deployed engineering
40:58 Agent orchestration
43:08 Cost controls
43:49 Auto model routing
45:52 Guardrails
47:02 Legacy code risks
48:16 Model poisoning
49:35 What is a harness?
51:47 Why build your own
52:58 Continuous learning loops
56:30 Security workflows
57:37 Validation and meta engineering
1:00:32 Running evals in practice
1:03:36 Teams reshaped by agents
1:12:17 Should you study CS?
1:14:11 Enterprise adoption
1:18:23 Local to cloud journey
1:20:51 Agent economy and prompting
1:22:22 Spec vs plan
1:25:12 Closing and thanksLindsey Simon - The Future of Software EngineeringBasil Chatha2026-03-31 | Lindsay Simon, VP of Engineering at Vercel, talks about his path from studying philosophy, English, and computer science at UT Austin to working at the Austin Chronicle as a generalist webmaster and teacher, then building security visualization software (including an “attack back” feature that drew FBI attention), blogging about browser performance, and joining Google’s App Engine team to help create early infrastructure-as-a-service, sandboxed runtimes, and autoscaling before Kubernetes. Simon discusses working with Brett Taylor on Google Consumer Surveys, visual regression tools like Depicted, and later Quip after its Salesforce acquisition, where fast iteration required better internal deployment/testing infrastructure. At Vercel he moved from product work to engineering leadership, is currently building Dev 3000 to explore AI agent coding, and argues core CS knowledge and strong reading/writing still matter while engineers evolve into generalist builders.
00:00 Intro 00:55 Lindsay Simon's early years 01:18 College 02:05 Philosophy To Programming 03:32 First Job Newspaper 04:56 Generalist Webmaster Life 06:27 Security Startup Stories 09:23 Blogging Into Google 11:02 Joining App Engine 12:24 App Engine Challenges 14:34 Working With Brett 15:14 Google Consumer Surveys 17:57 Visual Diff Testing 21:27 Dev 3000 Agents 24:27 Management Unblocking 25:42 Free Software Roots 27:55 Ola Side Project 31:36 Founder Lessons 33:23 Quip And Salesforce 36:19 Brett Taylor Decisions 38:28 Deploy Fast Iterate Faster 40:20 Quip Explained Notion Like 43:18 LLMs And Design Docs 45:30 Joining Vercel As Customer 49:55 From PM To Engineering 54:47 Shipping Without Process 58:32 AI Coding And Guardrails 01:01:03 Skills And Agent Context 01:04:48 Dogfooding And Adoption Bar 01:11:07 Future Dynamic Interfaces 01:13:21 Vercel As Transport Layer 01:14:59 Builder Identity Wrap UpHe Built a $200M AI Agent 10 Years Before ChatGPTBasil Chatha2026-01-28 | Summary:
In this conversation, I talked to Ashish Shubham (VP of Engineering), who's been at ThoughtSpot for 10 years, about AI agents in enterprise analytics. ThoughtSpot started as a search-based analytics company trying to make data accessible to regular business users. In 2019, they tried building natural language interfaces using BERT, but only hit about 50% accuracy. For a product where enterprise customers make billion-dollar decisions, that wasn't good enough. They shelved the project.
When ChatGPT came out, ThoughtSpot was ready. Ashish walked me through how they pivoted: they built a 25-30 person team, decided to use prompting instead of fine-tuning, and leveraged their existing semantic data modeling layer to get accuracy into the high 90s. We got into the technical evolution from monolithic systems to agent architectures with tools, how they went from manual human judges to using LLMs to evaluate their outputs, and how enterprise security requirements shaped what they built.
We also talked about how software engineering is changing. Ashish said 50-60% of his code is AI-generated now, and he thinks system design is becoming the critical skill, even for junior engineers. He had an interesting take on the "95% of AI deployments fail" stat too.
Chapters:
0:00 Intro and Ashish's journey to ThoughtSpot from GoDaddy
0:13 ThoughtSpot's mission to democratize data analytics for business users
1:26 Early search-based analytics before natural language processing
2:36 ThoughtSpot vs Tableau and the promise of self-service analytics
4:40 The analyst bottleneck problem and how ThoughtSpot aimed to solve it
5:49 Early technical challenges with in-memory databases and data migration
8:11 Semantic data models, joins, and creating abstraction layers for users
11:39 Who builds the data models and the role of analysts
12:22 Pre-LLM natural language processing using BERT and word2vec in 2018-2019
14:43 The accuracy problem and ambiguity in translating user queries
16:58 Trust challenges and why the early NLP product never became core
19:59 Competition with Tableau, Looker, and Power BI
22:44 How analyst roles changed with self-service analytics tools
25:30 The ChatGPT moment and pivoting to LLM-powered natural language
27:48 Early prompt engineering days and generating SQL with LLMs
31:09 Training vs prompting debate and why fine-tuning was eventually abandoned
34:28 Organizational changes and building the NLS team
37:16 Coaching systems for company-specific terminology vs training models
39:02 Evolution of evaluation methods from human judges to LLM-as-judge
43:23 Moving to LangFuse and GCP for agent infrastructure
46:29 How LLM context windows and capabilities evolved their product
50:07 From 30-column limits to agentic systems with 90%+ accuracy
52:52 RAG, column selection, and using proprietary data indexes
54:59 Multi-model support and enterprise data security concerns
59:14 How AI has changed Ashish's personal engineering workflow
1:02:42 Impact of AI on the broader engineering organization
1:04:15 Measuring AI productivity and the challenge of metrics
1:07:26 50-60% AI-generated code and the changing nature of coding
1:09:18 System design skills becoming more important than coding
1:13:00 Junior engineers doing senior-level work and interview changes
1:14:37 Customer conversations about Gen AI adoption across industries
1:17:26 The MIT report on 95% agent failures and why it misses the point
1:22:12 Agent architecture with LangGraph vs Google ADK and building internal agent platform
1:24:26 Where value lies in the next two years: tools, skills, and optimization
1:28:05 Startup opportunities in making AI accessible to non-technical users
1:29:26 Closing remarksThe Only Claude Code Tutorial Youll Ever Need (No BS)Basil Chatha2026-01-15 | In this conversation, I walk through a real-life vibe coding scenario from start to finish. From how to think about vibe coding at a high level to tactically deploying a frontend application with Claude Code. I cover frontend development techniques, algorithm design, debugging processes, user experience considerations, and final adjustments before deployment. The conversation provides insights into the challenges faced during development and the solutions implemented to enhance the application's functionality and user interface.
Chapters:
00:00 Introduction to Vibe Coding and Project Overview 05:39 Understanding the Project Requirements 09:26 Building the Algorithm for Seating Charts 12:37 Implementing the Algorithm and Debugging 21:59 Finalizing the Project and Testing 22:55 Debugging the Seating Chart Algorithm 23:55 Building the Seeding Chart Script 24:57 Validating Algorithmic Approaches 26:51 Optimizing Player Interactions 29:17 Comparing Algorithm Versions 33:15 Adjusting Weights for Balance 37:24 Reassessing Project Objectives 38:08 Building the Poker Seating Chart Frontend 45:06 Utilizing ShadCN UI Components 47:02 Designing the User Experience 48:42 Implementing the Timer Functionality 49:54 Transitioning to Bun Package Manager 49:58 Testing and Debugging the Application 50:03 Productionizing the Application with Vercel