โSamayaโ means moment in time. The moment where information becomes conviction. But that isnโt just about AI.
As AI systems get better at planning, reasoning, and decision-making, one thing becomes clearer:
They still need the right context and frameworks to succeed.
And that comes from humans.
In the latest @pioneersofAI episode, @maithra_raghu talks with @kaliouby about why human judgment isnโt going away - itโs becoming more critical.
Weโre excited to launch Samaya AIโs Agent Control Plane (ACP) and new investment from NVentures (@nvidia's VC arm) and @databricks .
Samayaโs ACP is a new architecture for AI agents that reason in real time. Accurate, auditable, enterprise-scale AI agents that can handle complexity and deep financial institutional context.
The new investment from NVentures and Databricks Ventures will further support development of the ACP and next gen AI Agents for finance.
Working with researchers from Princeton University, weโve created SLIM, the best open-sourced deep research system.
SLIM outperforms existing frameworks while using only 15โ25% of the tool calls and reduces hallucination by 2.5ร!
๐งฉ Blog, ๐ paper, and ๐ป code in comments.
Big news at Samaya: our Founder and CEO, @maithra_raghu, has been named to the @TIME 100 AI 2025 list! ๐
Through her AI research at Google Brain, working with the "Godfather of AI" Geoffrey Hinton, to building @samaya_AI, Maithra has been driven by the vision of Expert AIs that can partner in discovering key insights and high-stakes decision making.
Weโre so proud to see her recognized for the vision that drives what weโre building at Samaya.
Congratulations, Maithra!
Surprised and delighted to be on the @TIME 100 AI list! (And in very good company!)
Itโs especially meaningful to have this recognition this year, which has been one of incredible growth and milestones for Samaya. We closed our Series A led by NEA, and with other stellar investors earlier this year.
But most importantly, we went from a smaller set of initial users at the start of the year, to being live, globally, with thousands of users that rely on Samaya every minute of every day to help them navigate the financial information ecosystem.
Building a company is an exercise in sheer grit. There are many times you want to quit. The will to keep going comes from the real, measurable impact Samaya is having on our users, the trust and love our customers have for the product, and working with such a brilliant and talented team.
Thank you for your faith in us, and weโre excited to build towards the vision of a new type of financial ecosystem, where humans and AIs collaborate seamlessly on high-stakes investment workflows. Much more to come!
Live testing GPT-5 on challenging financial questions and still seeing hallucinations and other errors crop up.
The automatic routing to thinking is also frustrating at times --- GPT-5 thinks for a long time only to provide a subpar answer.
(See below for an example on Figma's IPO cash balance. The right answer is ~$618m for cash and cash equivalents. GPT-5 provides multiple, very different numbers, even after thinking, which turn out to be wrong. @samaya_AI takes a fraction of the time and provides the full breakdown.)
Most AI โdeep researchโ agents hallucinate ๐ค๐ญ
And almost none can connect second-order effects.
After 4 months of iteration with users, weโre launching Samayaโs Deep Research Agent, built to solve both problems.
(๐ธ example below โฌ๏ธ)
Under the hood: it draws from reasoning frameworks like Causal World Models ๐ (https://t.co/CGi1hvZdBT)
So it doesnโt just summarize headlines, it simulates ripple effects across markets, sectors, and systems.
๐ ๐๐น๐ผ๐ฏ๐ฎ๐น ๐๐ฟ๐ถ๐๐ถ๐ ๐๐ฒ๐บ๐ฎ๐ป๐ฑ๐ ๐๐น๐ฎ๐ฟ๐ถ๐๐ โ ๐ฆ๐ฎ๐บ๐ฎ๐๐ฎโ๐ ๐๐ ๐๐ด๐ฒ๐ป๐๐ ๐๐ฒ๐น๐ถ๐๐ฒ๐ฟ ๐๐ป๐๐ถ๐ด๐ต๐๐ ๐ถ๐ป ๐ฅ๐ฒ๐ฎ๐น ๐ง๐ถ๐บ๐ฒ.
As the Israel-Iran conflict unfolds, markets are shifting fast. Our latest agent-generated report breaks down the potential ripple effects across global sectors and companies, mapped out under multiple geopolitical scenarios.
โก ๐ช๐ต๐ฎ๐ ๐๐๐ฒ๐ฑ ๐๐ผ ๐๐ฎ๐ธ๐ฒ ๐ฎ๐ป๐ฎ๐น๐๐๐๐ ๐ต๐ผ๐๐ฟ๐, ๐ผ๐๐ฟ ๐ฎ๐ด๐ฒ๐ป๐๐ ๐ฑ๐ผ ๐ถ๐ป ๐บ๐ถ๐ป๐๐๐ฒ๐. They analyze thousands of data points across sectors and companies to surface second-order impacts in real-time.
Stay ahead of volatility.
This brings us closer to our goal:
An assistant that doesnโt just respondโit thinks ahead.
By detecting and filling gaps automatically, Samaya delivers answers experts can rely on.
Full story โ
https://t.co/OeypQghpTQ
Even great answers can have subtle gapsโmissing numbers, overlooked facts. In high-stakes workflows, those gaps cost time and trust.
At Samaya, we built a real-time self-correction engine that quality-checks our summaries and fills in missing info before the user notices.
๐งต๐
https://t.co/OeypQghpTQ
With over 3,000 carefully annotated queries and 8,000+ hours of expert annotations, Criteria-Eval has transformed how we monitor, debug, and continuously improve our platform.
Read more details in our blog post: https://t.co/BxidFqA7hc
Evaluating long-form answers to complex technical questions is very challenging.
Existing methods fall short in this setting.
At Samaya, we built Criteria-Eval, a checklist-based evaluation that aligns with how domain experts judge answers.
๐งตhttps://t.co/jKp7h7wvBp
โ๏ธ @cbaziotis