
the demo was the easy part 🫠 Second Opinion #2 is about everything after it: safety, prod access, and the token bill Nov 12, Paris, with @avec_alan , @Qovery_ & @AWS luma.com/4lhbur28

All things engineering @avec_alan

the demo was the easy part 🫠 Second Opinion #2 is about everything after it: safety, prod access, and the token bill Nov 12, Paris, with @avec_alan , @Qovery_ & @AWS luma.com/4lhbur28

We wrote about Hopper, the agent we built at Alan. It started as a coding agent for builders. Today 80% of Alaners use it, and 25% of our merged PRs come from it. More technical posts to follow in the coming weeks/months! medium.com/alan/hopper-we-bu…


Building a flashy agentic demo has never been easier. The real challenges start when you try to take it to production, at scale. Join us on October 8 at our Paris offices to hear Camille & Matthieu explain how they automated 40% of our customer tickets with AI.

For years, every claims feature at Alan meant building it twice. A year ago, we broke that cycle. Here's what that journey looked like — from expensive first steps to compounding returns, and AI's role in it all 👇. medium.com/alan/universalisa…

Part 3 of our document processing series is out — how we scaled our pipeline from French insurance docs to new countries and multiple use cases, without rewriting everything. This wraps up the series. Thanks for following along! buff.ly/9cQL4F3

We think we built the best Python caching library in the world! RAM+Redis, atomic writes, distributed invalidation, async refresh, warmup, observability... Dive into this 5-part series, packed with diagrams, code snippets, dashboards, and numbers! buff.ly/QVH9M71

Few-shot examples are only as good as their labels. Ours were hallucinating values from memory. The LLM learned to do the same. Part 2 of the doc processing series: curated datasets, backtesting every change and separating parsing from human knowledge buff.ly/mIQUqa7

Ever wondered how Alan reimburses health claims so fast? Spoiler: we automated 70% of document processing. We just dropped the first article of our doc processing series — stay tuned for more on how we're scaling this across other countries and use cases. buff.ly/2Lu7aWD

📣 We’re doing something a bit different at @alan: an on-site Engineering Recruitment Day 📍 Paris (Alan HQ) 🗓️ Tue, March 17 ⏳ Apply by Wed, March 11 👉 jobs.ashbyhq.com/alan/a8b3fe…

A button color took weeks to ship. Not because it was hard—but because the designer who spotted it couldn't fix it themselves. So we asked: what if everyone could build? #everyonecanbuild

"Claude did it almost on its own while I was boiling water for my tea" That's how our engineers now fix flaky tests at Alan. Read more about our journey from manual debugging to AI-powered investigation in our latest article 👇 medium.com/alan/from-gut-fee…

Don't chase leaderboards. There's always a score-latency tradeoff, and LLM providers often hide it. We reproduced Tau-bench to see for ourselves. Here's what we learned: medium.com/alan/benchmarking…

There are many LLM benchmarks such as MMLU and GSM8k, but they're useless for AI agents. Real agents need to handle database state, tool calling, and multi-turn conversations. Stateful benchmarks show the path forward. New post on agent evaluation 👇 medium.com/alan/benchmarking…

You've heard of the recent ISO27001:2022 certification of Alan by SGS, but want to know more about our journey towards certification? Head up to Maxime's post and enjoy the read! medium.com/alan/our-iso-2700…
