Quotient AI @QuotientAI
We’re building tools to catch agent mistakes and automatically fix them. Join our test kitchen: https://t.co/ShuLaL4ebi quotientai.co Boston, Massachusetts Joined July 2023-
Tweets135
-
Followers399
-
Following5
-
Likes197
this explains why our kimi-k2 tool call evals on together looked off. crazy variance on that metric alone
this explains why our kimi-k2 tool call evals on together looked off. crazy variance on that metric alone
smaht hats are in c/o @QuotientAI DM me to claim
docs makeover just dropped 👀✨✨✨ c/o @mintlify as usual
How to ship reliable agents faster with @AgnoAgi + @QuotientAI Agno makes it super simple to build up an agent. But as soon as it gets to real users, cracks can show up: hallucinated answers, wrong tool calls, or irrelevant context. That’s where Quotient comes in. We provide…
Hallucinations are still an open problem in real-world AI systems. Not because models make things up, but because they fail at reasoning over the messy context they’re given: missing docs, conflicting snippets, noisy data. I pulled together what we know so far from research and…
One of the hardest parts of working in retrieval or search is figuring out where things fail. Did the retriever return irrelevant context? Did the model hallucinate even with good context? Is the retriever drifting over time as the corpus changes? Most production setups don’t…
One of the hardest parts of working in retrieval or search is figuring out where things fail. Did the retriever return irrelevant context? Did the model hallucinate even with good context? Is the retriever drifting over time as the corpus changes? Most production setups don’t… https://t.co/edE3DK8obq
We’ve built a financial analyst agent with built-in monitoring and automatic trace analysis. @QuotientAI's evaluators flag critical issues like hallucinated risk factors, misattributed data, and irrelevant retrievals, so every output is accurate, compliant, and trustworthy.
What if you had a SOTA search agent and you could confirm its reliability in real time? We added @QuotientAI monitoring to Fireplexity, @Firecrawl’s Perplexity clone backed by @GroqInc. Best part? It’s all OSS, so you can measure the lift from new prompts & models.
Evaluating generative AI - especially for hallucinations, retrieval errors, and tool-use behaviors - is notoriously tough yet critical for deployment in real-world systems. Talk to @JuliaANeagu next Nov in Lisbon about how she helps ensure the AI-powered systems you’re coding…
I’ll be showing off what we’ve built tonight at the MCP Demo Night w/ @getsentry @osoHQ and @incident_io. Come by if you’re around! I'm in SF all week — already catching up with some great folks, and always down for a beverage or a bite. HMU!
I’ll be showing off what we’ve built tonight at the MCP Demo Night w/ @getsentry @osoHQ and @incident_io. Come by if you’re around! I'm in SF all week — already catching up with some great folks, and always down for a beverage or a bite. HMU!
introducing the Quotient MCP Server, our entrypoint for in-the-loop steering of agents agents can receive information about what kinds of errors they're making in between steps, get feedback from specialized models, and correct themselves
notes from @JuliaANeagu 's talk on hallicnations
Can you get your AI agent to *0* hallucination? Let's find out! .@jxnlco and I are chatting in a couple of hours about how to catch critical issues (like hallucinations) in your AI agents in real time. Sign up link below 👇
Can you get your AI agent to *0* hallucination? Let's find out! .@jxnlco and I are chatting in a couple of hours about how to catch critical issues (like hallucinations) in your AI agents in real time. Sign up link below 👇
Our talk with @tavily is now live — part of the new @aiDotEngineer Retrieval & Search track. We share a practical framework for evaluating AI-powered search, and results from benchmarking popular context-augmented systems. If you’re building AI search, this one’s for you.
Our talk with @tavily is now live — part of the new @aiDotEngineer Retrieval & Search track. We share a practical framework for evaluating AI-powered search, and results from benchmarking popular context-augmented systems. If you’re building AI search, this one’s for you.
@jerryjliu0 and @QuotientAI on your birthday! x.com/JuliaANeagu/st…
@jerryjliu0 and @QuotientAI on your birthday! x.com/JuliaANeagu/st…
happy birthday to me 🥳🥳🥳🥳🥳
Agents still mess up tool calls. Last week we released limbic-tool-use-0.5B - a small model that catches those mistakes better than GPT-4.1. Now we're sharing how we did it: dataset, training pipeline, benchmark. 162 MCP server tools 50M+ tokens 1 @modal_labs H100 read below
Rob Wingate @RealRobWingate
24 Followers 255 Following Building ImagineStack ⚡️ | Solar-powered cloud infra 🌞 | OSS, AI, Edge, WASM, Zero-Trust | Coffee, code & cold surf life in Ocean Beach, SF 🌊☕️
Nils Höhing @nilshoehing
102 Followers 699 Following Vision Language Model evaluation / benchmarking | PhD student @ml_labs_irl @UCDCompSci
Absolute Beginners++ @4TechBeginners
26 Followers 152 Following solving problems as a beginner would
MohammedAGI @CEOAGI
5 Followers 125 Following
Prof Ciekawski @CiekawskiP20193
25 Followers 1K Following
Allie Howe @vtahowe
998 Followers 766 Following CEO of Growth Cyber | SOC2, NIST AI RMF, AI Security Gap Assessments | Helping AI Startups Build Trustworthy AI | Host of the @insecureagents Podcast
Olivia Wang @oliviawpy2023
38 Followers 262 Following CSE PhD student @UCSC. Research interests in Human-Centered #XAI (#hcxai), Neurosymbolic AI & Law (#NeSy). Ex-Software Engineer. Views (and the dog) are my own
Nachman @nachmanks331
32 Followers 2K Following
@cg @cg
3K Followers 794 Following building conversational AI. formerly Bland, Meta, Twitter, Google
Bernardo Pamplona @Bgpamplona
0 Followers 236 Following
. @n0thingn3ss
46 Followers 1K Following
Manifestante Pacífic... @pais_hominido
1K Followers 4K Following Libre quien se concentra en aprender a jugar las cartas que le han tocado, esclavo quien se dedica a protestar y a exigir otro reparto
Opso Facto @OpsoFacto
1K Followers 7K Following I value free speech; nevertheless, discretion is the better part of vitriol. AI will be a boon both to the laziest and the most industrious. Physics curious.
Anna May @maypanni
20 Followers 64 Following
alp @aragon81
38 Followers 159 Following
Epsilon Guanlin Lee @Epsilon_Lee
262 Followers 3K Following PhD, MLer, CLer (NLPer), ML Engineer at https://t.co/gX6Lem59Co, have belief in interpretability research of AI/ML/NNs
Matthew Hoty @foulfoul60
627 Followers 2K Following Head of Product @ Healthpilot 💼• Vibe coding https://t.co/Um2rRR0PeC 🧑🏻💻• No apologies for Cleveland sports, Star Wars, and Marvel retweets 😅
baskarmanickam @baskarmanickam
208 Followers 1K Following
Mubarak Hussain @MHQureshi
3K Followers 4K Following #Salesforce Trailblazer #Agentblazer | CRM+AI+DATA | Salesforce Certified Professional | MuleSoft Certified | Oracle Certified | Quotes | #CertifiedPro | 💙
Bruno Pais @bpais88
298 Followers 4K Following 🇵🇹Head of Product based in 🇳🇱| Building @trydyntai | teaching product management @productschool | ex-product leader @Bookingcom
Dan Brickley @danbri
12K Followers 13K Following Data standards technologist. Prev: Google, https://t.co/ej6DTF9hps, W3C, telly stuff, UN FAO, dig libraries, RDF/S, Linked Data, decentralized social & search tech.
Anshuman Mishra @anshumanmishra
1K Followers 5K Following AI, trading, startups. CS @IITKgp, recovering MBA. Libertarian. Techno-optimist. Sturgeon's Law maximalist. 🇮🇳🇺🇸.
infradev @infradev2
10 Followers 1K Following Interested in infrastructure development, cyber operations and security engineering
Cristi Pufu @cristi_pufu
101 Followers 939 Following ninja software engineer @uipath 🥷 | crafting oss app analytics @aptabase 📈
Tahir Fayyaz @TFayyaz
1K Followers 3K Following Product Manager @databricks focusing on Data Engineering. Previously Developer Advocate at Google Cloud for data & analytics.
Arslan Sarwar @arslans171
216 Followers 3K Following Software Engineer | Technical Writer, Here to share my learnings and ideas about all things Tech.
Chirag @ChiragGalani
313 Followers 4K Following building Voice AI @Traba_Work Prev @google thoughts are my own!
Niron K. @nironkoren
130 Followers 931 Following Securing AI Agents ◕ Connecting applications with metrics
Luca Baggi @baggiponte
534 Followers 2K Following 📈 AI Engineer @ https://t.co/Du2lQ9AFgU 🗞 Ho scritto spiegoni @ilpost 🎓 MSc Econ & Stats @LaStatale 🎓 BA Filosofia @UniBergamo & @SorbonneParis1
Anuj Khurana @anuj
1K Followers 5K Following We are buzz word compliant UX and technology team that builds web and mobile apps for startups. Currently 30 +people strong and based out of Goa, India.
nixpiper @nixpiper
63 Followers 2K Following
ziryâb 🧣 @ziryabbey
180 Followers 1K Following 'emunctae naris' #ortamkaldırır az tarihçi. âleykûm enfûsekûm. #galatasaray #leclerc “These fragments I have shored against my ruins.” v. milor’un sofra ahbabı
Ahmed Ayad @AhmedAyad1989
36 Followers 1K Following
Ravi Chandra Veeramac... @ravi_chandra_v
240 Followers 1K Following Software Engineer | Deep Learning | Open Source Contributor.
Hussein Muhaisen @husseinmuhaisen
2K Followers 4K Following Running security work in {stealth} // @ // PagedOut and GuidedHacking
Gourav Das @das_vicky
123 Followers 187 Following Homosapien v0.9b. CPTO @ ApnaKlub, ex-CTO TejiMandi(MOSFL). Previously built Voola, GroupShoppy. Wasted Microsoft's time earlier!
Deeptendu @DSantra92
180 Followers 1K Following evaluating Agents | prev @useiterate @letsunifyai • GSOC @JuliaLanguage • @mitacscanada GRI fellow
Rudy Shaw @wakeupatfive
47 Followers 476 Following garage fridge american. we must figure things out and we shall.
Arbaaz @HingumTringum
2K Followers 1K Following washed up physicist— CEO https://t.co/juKUZVbCRU | libertarian globalist | VC hater
AI Tinkerers @AITinkerers
4K Followers 169 Following AI Tinkerers is a global network of meetups for AI practitioners with technical, machine learning, and entrepreneurial backgrounds happening around the world.
Deanna Emery @DeannaLEmery
71 Followers 98 Following Founding AI Researcher at Quotient AI, ex Astrophysicist, bike tourer 🚴♀️UC Berkeley, Harvard
Julia Neagu @JuliaANeagu
2K Followers 2K Following building @QuotientAI ✨ formerly @GitHub @GitHubCopilot 🤖 reformed physicist 👩🔬 ~ opinions are my own ~
Freddie Vargus @freddie_v4
1K Followers 2K Following cto & co-founder @quotientai Research @cohere_labs — past: mle @github Copilot, data @quantopian — Tico 🇨🇷 & Bostonian 🇺🇸Trends for United States
You might like
