找到 13 篇相关文章
Each year, we get a huge influx of applicants to speak at TechCrunch’s events, and this year’s Founder Summit in Boston on November 4 will be no different!
I started my career as a software developer, Initially a front end developer and then became a full stack developer where success often meant solving difficult technical problems, building reliable systems, and delivering good software. Becoming a co-founder changed that perspective. Suddenly, building a product wasn't just about writing code. It was about understanding the problem deeply, making decisions with incomplete information, taking responsibility for outcomes, building a team, and constantly deciding what not to build. Now, as an Engineering Director at an AI company, I'm learning to balance both sides staying close to technology while thinking about people, product, strategy, and long-term engineering decisions. Honestly, The transition from developer to founder hasn't been a straight line. It's been a continuous process of learning, unlearning, and becoming comfortable with uncertainty. I'm starting this blog to document some of those lessons from building AI products and engineering teams to the technical decisions and challenges that come with growing a technology company. I know I'm just beginning my journey and that I thought I could perhaps share it with my tech community.
Forbes Called It a Playbook. I Call It a Production Log. Forbes published a piece recently calling AI agent startups "the new solo-founder playbook." I read it twice. The framing bothered me both times. A playbook implies steps. A sequence. Something you can hand to someone and say: follow this, and you will get the result. What Forbes described is not that. It is a description of an outcome, written by people who did not have to fix anything at 2 AM when the agent broke. Let me tell you what it actually looks like. The Night 871 Emails Went to the Wrong People Fourteen months ago I built my first agent that could send emails on behalf of the system. It was an outreach automation, nothing exotic. The agent would identify leads, draft a message, and send it after a human approval step. Except the approval step had a race condition. Two concurrent jobs both read "pending" from the database, both approved, and both dispatched. One lead received 871 emails over 40 minutes before I caught it. No company, no legal team, no PR buffer. Just me and an inbox full of angry replies. That night I wrote my first hard guardrail: #!/bin/bash # email-dedup-guard.sh LEAD_ID = " $1 " LOCK_FILE = "/tmp/email-lock- ${ LEAD_ID } " if [ -f " $LOCK_FILE " ] ; then echo "BLOCK: email already dispatched for lead ${ LEAD_ID } " > &2 exit 1 fi touch " $LOCK_FILE " # proceed with send Embarrassingly simple. But I did not know I needed it until I needed it. This is what Forbes leaves out. The playbook is written in retrospect, after someone else absorbed the cost of learning. The Model Is Not the Problem Every conversation about AI agents eventually becomes a conversation about which model to use. GPT-4 versus Claude versus Gemini. Benchmarks and context windows and reasoning scores. Here is what I learned: the model is the easy part. My current system runs 86 containers across two Hetzner servers. 240 automated jobs. Every day, these jobs do things: post content, process leads, trigger builds,
85 containers. 24 PostgreSQL databases. 67 domains. 232 cron jobs. One developer. 120 EUR/month in Hetzner bills. This is not a startup fantasy pitch. This is my production infrastructure for a SaaS ecosystem serving German golf clubs, a golf school management platform, a community platform, a CRM, and an auth service. Every customer gets their own database. Physical tenant isolation, not software filters. People tell me this cannot work. The containers disagree. The Stack Next.js for all frontends. Single-tenant PostgreSQL per customer (Supabase stacks). Docker on bare metal. Coolify for deployment orchestration. Traefik as the reverse proxy handling 67 domains. Two Hetzner servers in Germany. Total infrastructure cost: 120 EUR/month. The single-tenant architecture is a deliberate trade-off. Multi-tenant saves infrastructure cost, but one RLS bug exposes every customer's data. One compromised tenant enables lateral movement to all others. GDPR Article 17 deletion in multi-tenant requires complex cross-tenant queries. In single-tenant, deletion is DROP DATABASE . No residual risk. The cost is more operational complexity. Which is exactly why automation is not optional. 176 Guard Rules: The Immune System My AI agents (Claude Code with custom hooks) execute roughly 80% of daily development and operations work. That is dangerous without constraints. So I built a guard system: 176 shell scripts that fire on every command, every file edit, every session end. The architecture is simple. Four dispatchers route to context-specific guards: #!/bin/bash # Pre-Bash-Dispatcher: Loads guards based on command profile. # Not all 176 guards fire on every command. Profiling classifies # each command (git, docker, npm, database, deploy, comms) and # loads only relevant guards. set -uo pipefail GUARDS_DIR = " $( dirname " $0 " ) /guards" INPUT = $( cat ) CMD = $( echo " $INPUT " | jq -r '.tool_input.command // ""' ) # 8 security gates fire ALWAYS, non-negotiable: # tabu-gate, pii-gate,
Want to tap into the energy of 1,100+ startup founders, investors, and tech leaders descending on Boston for the Founder Summit 2026 on June 9? Host your own Side Event during “Founder Summit Week,” happening June 4-10!
Ryan Beiermeister, who demonstrated cool analysis in the Founders Fund YouTube series "Mafia," has joined the firm as a partner.
Marc Lou read a tweet, slept on it, and woke up still annoyed. The tweet, from Pieter Levels, was about all the fake revenue screenshots on X. By the next evening Lou had built a thing to fix it. By the day after that, the thing had made $20,378. That is the part everyone retweets. I want to walk you through it, and then I want to show you the line in his own year-end letter that complicates the whole legend. The setup Lou got fired by Tai Lopez in November 2021, was broke and depressed, and moved to Bali. He started shipping tiny products in public, copying the playbook of, yes, Pieter Levels. His breakout was ShipFast , a Next.js starter kit that did $40,000 in its first month in September 2023. By December 2025 he was running 15 startups generating about $84,900 a month, with cumulative revenue past $2.26 million, per his verified TrustMRR data. The reason I trust his numbers more than most is that he verifies them through Stripe on his own product, TrustMRR , which brings me to the 24-hour story. The moment something worked, absurdly fast TrustMRR exists to kill fake MRR screenshots. You connect a read-only Stripe key, and it shows your verified revenue on a public page nobody can edit. Lou built it in a day on top of his own boilerplate, which is the cheat code here. He was not starting from zero, he was starting from ShipFast. "TrustMRR is 24 hours old and was built in 24 hours." @marc_louvion on X He monetized it with sidebar ad slots. He listed them at $299 a month, then raised the price each time one sold, all the way to $1,499. In his newsletter he wrote that within three days every slot was gone and the side project had made $20,378. He called it the third fastest-growing thing he has ever built. Five days in, he posted the run-rate dream out loud. "20/20 spots filled! TrustMRR went from $0 to $18,380 MRR in 5 days. That's $220,000 ARR if I'm allowed to dream a little" @marc_louvion on X It kept going. By December 2025 TrustMRR was his single biggest inco
We just opened the waitlist for Something, and the part that surprised me most while building it wasn't the multi-agent orchestration — it was how hard it is to make an AI actually disagree. Every model we tested defaults to being helpful, which in practice means agreeable. Even when explicitly prompted to "find flaws," the outputs would soften into "here are some considerations" instead of a real critique. We had to engineer around this specifically: Separate system prompts with opposing reward framing — one agent optimizes for identifying growth potential, the other is explicitly told its only success metric is surfacing a disqualifying flaw Structured output forcing a verdict, not a summary — the skeptic agent (Nothing) has to commit to a specific weakness category (unit economics, timing, technical feasibility) rather than hedging across all of them A reconciliation step where both outputs get merged into one conviction score, so the founder isn't just reading two contradictory paragraphs If anyone's built adversarial agent setups and hit the same "it just wants to agree with me" problem, curious how you solved it. [Everyone who has a brain is a founder here] something-waitlist.vercel.app
2 days left to lock in your spot at TechCrunch Founder Summit 2026 and save up to $190 before Early Bird rates expire on June 26 at 11:59 p.m. PT. Register here.
You have just 3 days left to save up to $190 on your pass to TechCrunch Founder Summit 2026 before Early Bird rates end on June 26 at 11:59 p.m. PT. Register here.
The debut episode, moderated by Founders Fund chief marketing officer Mike Solana, included a star-studded cast of current tech luminaries.
Layup Parts co-founder Zack Eakin has drawn on a motorsports background, and his experience working for Palmer Luckey and Elon Musk, to tackle making faster, cheaper, and better composites.
Speaking to TechCrunch, Crunchbase’s head of research Gené Teare, said the factors holding back Black founders include “access to networks, relationships, and early introductions."