The agentic data workspace. Built for anyone who works with data. zerve.ai

Joined February 2024
70 Photos and videos
Introducing the Agentic Report. Describe what you want, and an agent turns your notebook analysis into a live, shareable report — grounded in every number, chart, and claim. Stakeholders can highlight a section, ask the agent to go deeper, and chat with the report directly. Same analysis. Many audiences. Every answer traced to the source.
1
3
5
156
We just wrapped the @Zerve_AI x @HackerEarth Hackathon, and we want to take a moment to celebrate our three winners: Nikhita Shankar, Michael Pabon and Sukriti Dubey 🥳 🏆 . A huge thank you to the thousands and thousands of participants who took part from all over the globe. We were blown away by the quality of submissions which made picking winners very hard. Keep your eyes pealed for our next hackathon going live soon 👀
1
1
10
174
We built Zerve to be serverless by default. Fast scaling, no babysitting. But for development, sometimes you want persistent compute for a tighter loop. In Zerve you can: → Run fully serverless when you want scale → Use persistent compute for development → Switch compute for a project in seconds → Target specific compute per cell → Give deployments their own compute profiles Best of both worlds. #Serverless #CloudCompute #DataScience
1
9
152
Every broken environment started with "just pip install it." Zerve environments let you define and version your Python, R, and Linux packages in one place. Upload a requirements.txt or pyproject.toml, reuse across projects, run multiple environments in one workflow, and go from dev to deployment without the usual mess. One less thing between you and the actual work. #Python #DataScience
3
6
239
Most notebooks die with the person who wrote them. Zerve changes that: → Drag and drop your notebook → Auto-parsed into a DAG → Run with full state and context → Deploy an API or app in minutes Already have notebooks? This is the fastest path forward.
2
4
223
Final two weeks. $10,000 in prizes. Deadline March 30. If you've been on the fence, now's the time. hubs.la/Q040d_B30

2
156
Stop looping. Start parallelizing. Zerve Fleet: → Spread inputs across a DAG → Execute in parallel (not sequentially) → Aggregate results in one cell Hyperparameter tuning, data processing, LLM evals. If it loops, it can scale. #DistributedComputing #ParallelProcessing
1
2
8
197
Software Engineering After AI: What Changes and What Doesn’t x.com/i/broadcasts/1aJbdbkNR…

110
Recurring work is where value compounds. Zerve scheduling: → Run on-demand or on a schedule → Auto-versioning so updates don't break prod → Completion error notifications → Full cron support Set it once. Trust it. Iterate safely.
4
10
163
Every Zerve cell run is fully inspectable. Code that executed. Output produced. Errors. Runtime. No more guessing what broke or why. Just click back and see exactly what happened. Debugging and collaboration, fixed. #DataScience #DeveloperProductivity
5
8
225
The #1 frustration with AI agents isn't the model. It's losing context. Zerve persists execution state automatically. Outputs, variables, everything. So your agent always knows what already ran. No starting over. No re-running. Just momentum. #AIAgents #DataScience #AgenticDataWorkspace #DecisionGradeDataWork
2
9
178
One month left in the Zerve hackathon. Real data. AI built for data work. $10K in prizes. hubs.la/Q040d_fF0

3
121
Most data science platforms call it "collaboration" when they let you share a link. That's file hosting with extra steps. Read what WE mean by collaboration here at Zerve. hubs.la/Q044Mnhy0
3
95
Hackathon update: Great submissions are rolling in. Still time to join. $10K in prizes, real usage data, AI that actually gets data context. Open through March 30: hubs.la/Q040dYRV0

1
90
Took Zerve to hackathons across India, Berlin, Paris, and online One winner cut cost per acquisition from $15.70 to $1.72. 29 teams competed at IIT Bombay. Two longevity sprints in Europe. Full recap plus an open $10K challenge hubs.la/Q043KMtW0
1
100
Next weekend Zerve is hosting the data analytics track at UA Innovate, a 24-hour hackathon at the University of Alabama. Teams of up to 4, all majors and experience levels welcome. Feb 28 - March 1. Register: hubs.la/Q043hNp70
1
1
96