Bertrand

@FarzaTV aha love it !

How I feel after this tweet:

@gaspardlezin really cool man, keep going !

I'm documenting my journey to 50K LinkedIn followers in payments. Every week, under this thread: real metrics, tools I use, what works, what doesn't 👇

@romanbuildsaas Course of course :)

How to grow your SaaS from $0 to $1M ARR (1+ hour FREE course) I just released a free course breaking down everything I learned going from $0 → $1M ARR. No theory. Just the exact strategies that actually worked. If you're building a SaaS, or feeling stuck trying to grow, this will help. Inside the course I cover: • How to turn social media attention into real revenue (not vanity metrics) • The growth frameworks that actually generated SaaS ARR • Why building an audience before you need it changes everything • The distribution strategies that helped us scale fast Want the course? RT so more founders can see it Comment “Course” I’ll send it to you. 🚀

🚀 I’m participating in AgentX AgentBeats — the world’s largest open competition focused on agentic AI. Hosted by Berkeley RDI and connected to ~40,000 learners via the Agentic AI MOOC. This isn’t just about building better agents — it’s about how we evaluate them. 🧵👇 🧠 Why agentic evaluation matters As AI systems become more autonomous, classic benchmarks start to break: • data contamination • overfitting • leaderboard gaming They tell us what scored well — not why systems succeed or fail. AgentBeats flips the problem. Evaluation itself becomes agentic: • runs tasks autonomously • enforces protocols • analyzes errors • produces structured, reproducible reports Benchmarks become systems, not spreadsheets. 🧬 What I’m building An autonomous evaluation agent for biomedical NLP, inspired by recent large-scale LLM studies (e.g. Chen et al., Nature Comms 2025). The idea is simple: one agent evaluates other agents — rigorously and transparently. 🟢 How it works A “Green Agent” evaluates competing “Purple Agents” (LLMs or agentic systems): • orchestrates task execution • enforces evaluation rules • measures performance • generates diagnostic reports No single score. Real insight. Goals: • reduce contamination & overfitting • enable fine-grained error analysis • move from leaderboard scores → system-level understanding Critical for high-stakes domains like healthcare. 🔬 Why biomedical NLP is hard • hallucinations can sound plausible — and be dangerous • ground truth is scattered across papers & databases • rare diseases = sparse, inconsistent data Evaluation needs evidence, not vibes. 🤔 A key question Can generalist LLM agents match or beat specialized biomedical NLP tools? Historically, domain-specific systems dominated: • NER • relation extraction • evidence synthesis AgentBeats finally lets us test this properly. 📊 What gets evaluated Across 6 task types / 12 datasets: • QA (MedQA, PubMedQA) • NER (BC5CDR, NCBI Disease) • multi-label classification • relation extraction • text simplification • dynamic summarization (live PubMed articles) Dynamic summarization is real-world hard: fetched live, evaluated end-to-end. ⚙️ Key capabilities • fully automated evaluation • fine-grained error analysis (hallucinations, boundaries, knowledge gaps…) • 1–5⭐ ratings aligned with production readiness • side-by-side agent comparisons • actionable insights — not just scores 🔮 Why this matters AgentBeats points toward a future where: • evaluation is autonomous • benchmarks are reproducible & contamination-aware • AI systems are judged with real rigor In healthcare, this isn’t optional. More soon 👀 👉 agenticai-learning.org/f25 cc: @BerkeleyRDI

@AndrewKepson @wardpeet @calcsam nice, feel free to share what you're building

@BertrandBuild @wardpeet @calcsam No I’m a react dev at my day job

trying Mastra right now and wow! so many good stuffs⚡️ I’m hooked thanks a lot @calcsam 😎

@AndrewKepson @wardpeet @calcsam sounds good! working with wordpress right?

@BertrandBuild @wardpeet @calcsam I’m finally getting to build with it at work this past week 😎

@karanjagtiani04 @iEx_ec hey Karan, the idea is to restrict access, so the agent only has access to a TEE tool and never see the user’s personal informations The tg handle is an example but it could be medical, financial or intimate informations

@BertrandBuild @iEx_ec Curious about the TEE implementation details. How will it enhance privacy for AI agents?

⚡️ excited to announce our collaboration with @iEx_ec bringing TEE privacy and security to ai agents SOC 2 is just a proof of audit TEEs are proof of security here is what we're working on 🧵

@TechVVV @iEx_ec thx TechVVV!!

We’re excited to welcome you to the @iEx_ec family! 🤝😎 #Privacy #Web3 #AI #crypto

our dream is to make privacy a default and we believe the future of AI agents is ✅ autonomous ✅ privacy-first ✅ built for Web3 thanks to @iEx_ec @arbitrum @ArweaveEco for pushing the boundaries with us

one example is the @web3privacy newsletter an agent fetches the newsletter, chooses the most impactful ones and send you a summary privately 🤫 you can subscribe here: app.1xbuild.com/subscribe/web3… ps: this requires some Eth on arbitrum

@FarzaTV this is so cool man! I’d be happy to contribute if you share the code somewhere

built an ai cursor that lives on my screen as a buddy + recommends me new stuff as i use my computer.

@iEx_ec thank you for the shoutout! ⚡️

1xBuild – Their platform runs on “agent templates.” With Web3Telegram, they’re building a privacy AI newsletter: Telegram updates that stay anonymous, with content archived permanently on Arweave. 1xbuild.com T

🔴 Live Friday 19 Sept at 17:00 CET with @ar_io_network. Speaking with 4 builders already using Web3Telegram on @arbitrum, showing how private messaging changes everything for crypto. luma.com/4chtzvjx

This is why @iExec is building web3telegram. A privacy tool to protect your handle ⚡️

closer to agi with every release

@Theo_jpeg @AbstractChain I’m in! love nature and forest are actually a solid bet 😅

I MADE IT ON @AbstractChain WITH MEMECOINS ✳️💸 Just bought a nice villa in the wood with all my profits, inviting all the top creators for a big party. Who’s in? 👀