Engineering Lead for Agentic Infrastructure @databricks | Scout @greylockvc (angel investing in data/ML/cloud) | prev: @stanford @ucbrise
San Francisco, CA
Joined August 2013
- Tweets888
- Following780
- Followers625
- Likes30.8K
Ankit Mathur retweeted
Cheap tokens can still mean an expensive coding task.
Hear @ankit_math of @databricks at AIE CODE.
Thank you to Databricks, a Platinum Sponsor.
November 10 to 12, San Francisco.
Apply: ai.engineer/code
ALT AI Engineer Code Summit announcement featuring Ankit Mathur of Databricks. Black, white and pale yellow artwork by Vincent Wendy, with November 10 to 12 in San Francisco and ai.engineer/code.
Ankit Mathur retweeted
AI bills are exploding everywhere.
Since joining Databricks, I've seen brilliant engineers across the industry (Distinguished Engineers, Berkeley/MIT/Stanford PhDs) spend months figuring out where to buy AI tokens.
Let me save you some time.
Choose Databricks AI Gateway:
- Fast open-source and proprietary models, available on Day 0.
- Smart Routing cut our internal coding costs by 35%.
- Easily track spending and set budgets across teams.
Spend less time managing AI tokens. Spend more time building.
Ankit Mathur retweeted
やっぱり Databricks の DB ブランチ、いいな、、
> ブランチの作成は数秒で完了し、数分もかかりません。データベースのサイズにも依存しません。
エージェントの実行ごとにブランチを1本。何十も並べても、費用は DB の複製ぶんではなく、ほぼ変更したぶんだけとのこと。
databricks.com/blog/lakebase…
Ankit Mathur retweeted
One of the tweaks we recently made in our internal software factory, Foundry, is giving the agents the ability to spin off new sessions by cloning the sandbox it’s running in. This lets agents run many investigations and implementations in parallel.
We’ve also exposed tools that allow sessions to discover other sessions and send messages back and forth, creating a community of agents learning from each other and sharing outcomes from performance benchmarks, etc.
Turns out agents LOVE cloning themselves and messaging each other to coordinate work! They seem to be good at referencing work done by other agents in the community and also send each other relevant tasks related to the area of code they were working on.
Ankit Mathur retweeted
We’d love to have Snowflake as a customer of our AI Gateway! my DM is open.
nitter.cf/Yuchenj_UW/status/2115…
Ankit Mathur retweeted
“Since you're not doing this AI stuff”
🔥🔥🔥
I don't think we should fight. The two companies are complementary. Since you're not doing this AI stuff, I really think Snowflake should consider getting its AI tokens through Databricks. You can get both cheap OSS models as well as frontier (OAI/Ant/Gemini/Grok) models from our platform. It all goes through Unity Gateway which has Smart Routing, Budgets, and Access Control. You can even use Omnigent with any harness, including CoCo. Most of our customers used this to reduce token spend ~30% last few months while token count went up. Genie lets you then track, control, manage that spend, all your financials, marketing, etc. Quick POC?
Ankit Mathur retweeted
Ali and Sridhar (Snowflake CEO) are having their Kendrick vs. Drake moment on X.
To our friends at Snowflake: we'd love to onboard you to Unity Gateway and our AI products.
No hard feelings. But your latest DeepSeek model is 3 months old. We ship OSS models on Day 0.
Ankit Mathur retweeted
I don't think we should fight. The two companies are complementary. Since you're not doing this AI stuff, I really think Snowflake should consider getting its AI tokens through Databricks. You can get both cheap OSS models as well as frontier (OAI/Ant/Gemini/Grok) models from our platform. It all goes through Unity Gateway which has Smart Routing, Budgets, and Access Control. You can even use Omnigent with any harness, including CoCo. Most of our customers used this to reduce token spend ~30% last few months while token count went up. Genie lets you then track, control, manage that spend, all your financials, marketing, etc. Quick POC?
Ankit Mathur retweeted
Every company can rent the same frontier models, so the edge comes from what a company's agents learn about its own business. Databricks' answer is a system of record built for agents.
Before an agent can be trusted with real work, that record has to tell it:
1. What's true: the company's own data
2. What it means: how the business defines things (grounding agents in it raised accuracy from about 50% to 84.5% in Databricks' testing)
3. What it's allowed to do: an identity, a budget, and guardrails
4. Whether it worked: grading against the company's own definition of good
Feed every correction back into the record, and the company keeps what it learns even when the model changes.
"If you replace the AI model at your company and the new one inherits your definitions, permissions, evaluated cases, customer history, and hard-won exceptions, that is a foundation for a sustainable competitive advantage."
From the latest Profiles of the Future by @bhorowitz and @mikemcg0 on Databricks & the Future of the Firm: a16z.news/p/databricks-and-t…
Ankit Mathur retweeted
I came back to Google to work on AI infra. Instead we got pulled in to solving the problem of exploding use of agents across the company.
Announcing Agent Compute Engine: bringing planet scale agentic infra to Google services and now to Google Cloud.
cloud.google.com/blog/topics…
Ankit Mathur retweeted
What if the next big leap in AI agents comes from better memory, not bigger models?
@theDeepView explores MemCurrent. In our internal benchmark of 114 enterprise tasks, agent success rose from 22.3% without memory to 68.4% with episodic and derived memory.
thedeepview.com/articles/why…
Ankit Mathur retweeted
Here’s how we’re building memory in Genie and the new Agent Bricks Memory service you can use in your own agents. MemCurrent automatically synthesizes new memories from traces to produce better results than alternatives.
Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero.
MemCurrent combines episodic memory with derived memory across three access patterns:
• Plugins to log and load context automatically
• Tools the agent calls on demand
• An offline “dreaming” pipeline that consolidates memory in the background
Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session.
On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie.
Read the research: databricks.com/blog/memcurre…
Ankit Mathur retweeted
Powered by Lakebase!
Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero.
MemCurrent combines episodic memory with derived memory across three access patterns:
• Plugins to log and load context automatically
• Tools the agent calls on demand
• An offline “dreaming” pipeline that consolidates memory in the background
Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session.
On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie.
Read the research: databricks.com/blog/memcurre…
Ankit Mathur retweeted
Building agents on databricks keeps getting better and better! Come build with us :D
Most agent memory is a guess.
When to distill? What to keep? What to pull back into context?
Guess wrong, your agent gets worse.
Our research team's MemCurrent architecture: 3x more tasks passed, 31% fewer tokens.
Agent Memory is live on @Databricks
databricks.com/blog/introduc…
Ankit Mathur retweeted
Check out our latest research: MemCurrent, a persistent agent memory architecture, which consistently stays on the cost-accuracy Pareto frontier on our internal and three public benchmarks. Try it in the new Agent Bricks Memory and Genie 🚀
Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero.
MemCurrent combines episodic memory with derived memory across three access patterns:
• Plugins to log and load context automatically
• Tools the agent calls on demand
• An offline “dreaming” pipeline that consolidates memory in the background
Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session.
On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie.
Read the research: databricks.com/blog/memcurre…
Ankit Mathur retweeted
Most agent memory is a guess.
When to distill? What to keep? What to pull back into context?
Guess wrong, your agent gets worse.
Our research team's MemCurrent architecture: 3x more tasks passed, 31% fewer tokens.
Agent Memory is live on @Databricks
databricks.com/blog/introduc…
Ankit Mathur retweeted
Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero.
MemCurrent combines episodic memory with derived memory across three access patterns:
• Plugins to log and load context automatically
• Tools the agent calls on demand
• An offline “dreaming” pipeline that consolidates memory in the background
Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session.
On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie.
Read the research: databricks.com/blog/memcurre…