Agentica, by @symbolica. An agent system that lets you interact with structured data and tools using natural language. Try it agentica.symbolica.ai/
Joined January 2026
- Tweets 92
- Following 1
- Followers 2,657
- Likes 103
23 Photos and videos
Pinned Tweet
Mar 20
Agentica Beta is live: chat to build long-running AI agents.
Describe a task in plain English, connect your tools, and deploy an agent that keeps working in the background.
This demo shows an agent tracking new San Francisco rental listings, as they appear. Just one example - you can build anything.
2
11
23
9,060
Mar 27
Agentica SDK achieved an unverified 36.08% on the 25 public ARC-AGI-3 games using the same harness we open-sourced a month ago. Average cost of $40 per game, and less than 2x the game actions taken by the second-best human players.
6
8
99
6,151
Mar 27
Agentica is not an ARC-AGI-3 specific 'harness'. It is a general purpose symbolic exoskeleton. You can use it to do any task. Interact with it directly here agentica.symbolica.ai/
10
8
153
29,322
Mar 26
We scored 36.08% on ARC-AGI-3 in one day using the Agentica SDK.
Community note
The title is misleading, this score is for the public demonstration set - quoted as being "intentionally easier for both humans and AI, with a stronger emphasis on clarity and fun".
arcprize.org/media/ARC_AGI_…
72
127
1,355
419,136
Mar 26
The same SDK driving this score also powers agentica.symbolica.ai, where you can build long-running agents in chat.
No sign-up, no code. Try it: agentica.symbolica.ai
1
2
77
19,190
Mar 26
For us, that's at 36.08% at $1,005 total cost... vs 0.25% for $8,900 with Opus 4.6 directly.
We used the same harness from our previous open source ARC-2 solutions on ARC-3.
Read more: symbolica.ai/blog/arc-agi-3
Code/Logs: github.com/symbolica-ai/ARC-…
5
6
133
23,707
Mar 25
Now using Agentica on ARC-AGI-3... will post results soon
Announcing ARC-AGI-3
The only unsaturated agentic intelligence benchmark in the world
Humans score 100%, AI <1%
This human-AI gap demonstrates we do not yet have AGI
Most benchmarks test what models already know, ARC-AGI-3 tests how they learn
3
1
56
5,778
Mar 23
There are entire startups built just to do this. With Agentica, you can build it yourself in a few prompts:
– drag and drop to analyze your CV
– find high-fit roles
– find hiring managers
-write tailored cover letters
– monitor new openings daily or weekly
– alert you via email when there’s a strong match
Takes minutes to build
2
14
1,159
Agentica retweeted
Mar 20
Today we are launching Agentica: agentica.symbolica.ai
Most other agent systems can write and run short code snippets but they can't do long running tasks that involve code execution. Additionally, other systems struggle with tool usage by requiring bespoke MCP integrations or manual workflow configuration.
This changes today. We built the first MCP-free dynamic coding agent that can interact with any tool or API you can throw at it with safety and correctness guarantees. It can perform tasks successfully over multi-hour long time horizons thanks to the reliability of the @agenticasdk at its core. Having Agentica complete complex tasks for you that involve structured data, using the web, etc feels like magic. I don't think any other tool today even comes close.
Agentica is currently in beta so expect a few bugs here and there. Feedback is very welcome. Please feel free to DM me bug reports or feature requests! We can't wait to see what you build.
Mar 20
Try Agentica: agentica.symbolica.ai
Read more on our blog: symbolica.ai/blog/introducin…
8
37
6,590
Agentica retweeted
Mar 20
hey agentica - track my oura ring activity and give me a daily brief of what google cal events i will feel energized for & when I should do deep work, notify me on telegram every morning
Mar 20
Agentica Beta is live: chat to build long-running AI agents.
Describe a task in plain English, connect your tools, and deploy an agent that keeps working in the background.
This demo shows an agent tracking new San Francisco rental listings, as they appear. Just one example - you can build anything.
1
1
4
902
Agentica retweeted
Mar 20
Agentica Beta is live: chat to build long-running AI agents.
Describe a task in plain English, connect your tools, and deploy an agent that keeps working in the background.
This demo shows an agent tracking new San Francisco rental listings, as they appear. Just one example - you can build anything.
2
11
23
9,060
Mar 20
Agentica Beta is live: chat to build long-running AI agents.
Describe a task in plain English, connect your tools, and deploy an agent that keeps working in the background.
This demo shows an agent tracking new San Francisco rental listings, as they appear. Just one example - you can build anything.
2
11
23
9,060
Mar 20
Try Agentica: agentica.symbolica.ai
Read more on our blog: symbolica.ai/blog/introducin…
1
2
10
7,046
Agentica retweeted
Feb 28
ARC Weekly Meeting — Sunday, March 1 at 1 PM EST
Excited to dig into it and see how it works!
Special Guest: Symbolica Agentica Team
Join: discord.gg/MSQay8r7mg
Feb 27
We've released the code used to solve all 3 publicly available ARC-AGI-3 games.
github.com/symbolica-ai/ARC-…
2
8
2,078
Feb 27
We've released the code used to solve all 3 publicly available ARC-AGI-3 games.
github.com/symbolica-ai/ARC-…
6
36
355
36,023
Feb 24
Join us this Thursday, 26th in London.
We’ll be speaking about ARC-AGI-2 and ARC-AGI-3 at the London AI nerd meetup: what’s new, what’s changing, and what it means for agents.
@its_hapenin @FireworksAI_HQ
luma.com/z4i401h6
2
3
22
1,889
Feb 23
We have now solved all publicly available ARC-AGI-3 puzzles.🧩
40
75
1,086
225,081
Agentica retweeted
Feb 19
Really cool to see teams already working on ARC-AGI-3
We'll have public replay links for every online run
5
7
146
11,718