CTO at Bindary. Building AI-native insurance broking: agents that take a risk from first email to bound cover. Notes on agentic engineering & AI ops.bindary.com Oxford, UKJoined October 2026
@hguerreroo Agreed, and in insurance it won't pass at all. Each fact in a submission needs a source someone can open. What do you log beyond tool calls to make that review quick?
@sh_reya Metrics first makes sense. In insurance broking the one I'd care about is whether every fact traces to a source. Have you seen a cost model work when the test material is documents?
@hwchase17 Identity is the part I'd want most detail on. In insurance every fact an agent acts on has to trace to a source, so: do you record which identity and which source each action used?
@dexhorthy Same logic applies to agent hand-offs: fewer of them means fewer places where a fact can lose its source. Where have you actually seen subagents pay off?
@mattpocockuk Agreed it's checkable. Same idea applies to agent output: if every claim must point to a source, a reviewer can check mechanically instead of re-reading. Would your tool treat 'coverage not worse' as a hard gate?
What I'll write about: agentic engineering (how agents ship code we can trust), AI ops (evals, durable workflows, data residency, cost) and what changes when an insurance workflow becomes AI-native.
I'm Dmitry, CTO at Bindary. We're building AI-native insurance broking: agents that take a risk from the first client email to bound cover, with every fact traced to its source. This account is where I share how we build it.
126K Followers 1K FollowingAgents & Gemini API, MTS @GoogleDeepMind | prev: Tech Lead at @huggingface, AWS ML Hero 🤗 Sharing my own views and AI News 🧑🏻💻 https://t.co/7IosdlO6RA
602K Followers 3K FollowingNVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.
408K Followers 594 FollowingProfessor @Wharton studying AI.
New book, Co-Existence, is out now: https://t.co/hsDYf1xU9K
My Substack: https://t.co/UIBhxu4bgq
1.1M Followers 6K FollowingPresident & CEO @ycombinator —Founder @garryslist—Creator of GStack & GBrain—designer/engineer who helps founders—SF Dem accelerating the boom loop
59K Followers 821 FollowingIncoming assistant professor @CSDatCMU @CMUDB. Putting LLMs in databases and BI tools. Created https://t.co/PmuOqAXVgS and https://t.co/8MQt4na2cj.
55K Followers 2K Followingbuilding @humanlayer_dev, YC alum, @aitinkerers sf lead, prev @replicatedhq @SproutSocial @nasa ai that works pod @ https://t.co/69BhaNtWfd
1.6M Followers 268 FollowingThe engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
5.5M Followers 4 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6LgzPA
2.0M Followers 2 FollowingClaude is an AI assistant built by @anthropicai to be safe, accurate, and secure. Talk to Claude on https://t.co/ZhTwG8d1e5 or download the app.
1.8M Followers 2 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
1.9M Followers 1K FollowingCo-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
2.0M Followers 179 FollowingNobel Laureate. Co-Founder & Chair @GoogleDeepMind; Chief Scientist of Alphabet. Founder & CEO @IsomorphicLabs. Building the future...