I ship production AI, document every update, and keep the systems running live — for 128,000 people doing the same.
An automation to find top stories, generate AI-narrated videos with related visuals, and publish them as reels and podcasts.
The mission
I experiment with AI agents and automations that work on a Tuesday and don't break on Fridays.
Now shipping
A SaaS product that calls the leads for you, speaks naturally, books meetings, and updates your CRM — built in a weekend with no-code tools and LLMs.
Ongoing · Thinking
A complete team of AI agents to run anything — from content creation, to customer support, to growth and operations.
Live demos
A RAG chat, a voice agent, and a multi-agent dashboard — all on the same design system. Click through to use them live.
LiveUpload PDFs and images, get cited answers grounded in your docs.
LiveOne agent. Unlimited phone workflows — booking, follow-ups, FAQs.
LiveDashboard to create, list, and test-call voice agents on Vapi.
Inside one run
A 21-second inbound call. Transcribed, reasoned through, two tool calls, calendar updated, email sent. Shown here as a step-by-step replay.
pod.cuts · the engine
Every Byte Sized episode goes in as a 5-minute video and comes out as 12 ten-second vertical reels, captioned, branded, scheduled. Fully unattended. This is what one run looks like.
From 5-min Byte Sized recording → 12 × 10-second vertical reels · captioned · branded · scheduled to IG + YouTube Shorts + TikTok the moment the encoder finishes.
The audience
A field-log across every platform — for people who actually ship.
Now
The projects and initiatives on my desk right now.
YouTube · Shorts
One concept per swipe. Under three minutes. The slot for everything that didn't deserve a full episode.
Instagram · daily
One agent technique. One repo. One carousel. Every single morning at 9am PT.
Byte Sized · weekly
One hour with someone who has actually shipped. Audio for the commute, video for the desk. New episode every Wednesday.
Writing · long-form
Slower than the feeds. Closer to first principles. Written and published here.
Most teams already use ChatGPT. Most still wait the same number of days for a quote, a reply or a decision. AI is speeding up one step. The handoffs between steps haven't moved. Rewrite one end-to-end process first, give it one owner, then put AI inside it.
AI isn't mainly wiping out entry-level jobs. It's taking over entry-level tasks, like research, summaries and first drafts, and those tasks were how juniors learned the job. Young workers in AI-exposed jobs are already being hired less, while the roles that remain ask for senior skills on day one. If your team uses AI, decide how a junior will learn the judgement the busywork used to teach.
AI agents don't learn from their mistakes on their own. The model is the same tomorrow as it was today, so a lesson only sticks once it's written into the rules the agent reads before it acts. Review every miss, write each one as a single rule with evidence, and make sure someone actually decides which rules go live.
The feed
Daily on Instagram. Weekly on YouTube. Hourly on X. Bi-weekly on the blog.
One agent technique & one repo to clone — every day.
Open feed ›Long-form, real stuff. Real talk. Real knowledge — no edits.
Watch latest ›Threads, hot takes, the fast feedback loop. Where ideas are workshopped first.
Read threads ›Loading latest…
The boring middle. The unsexy plumbing. The wins worth writing down. Owned and undistributed.
Read essays ›The stack
Twelve tools. Zero compromises. Updated whenever the models leapfrog each other.
Agents · Engineering · Talks · Podcasts · Interviews · Automations.