PDF Viewer

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

MVP Investment

$9K - $12K
6-10 weeks
Engineering
$8,000
Cloud Hosting
$240
SaaS Stack
$300
Domain & Legal
$100

6mo ROI

1-2x

3yr ROI

10-25x

Automation tools have long sales cycles but high retention. Expect $5K MRR by 6mo, accelerating to $500K+ ARR at 3yr as enterprises adopt.

Talent Scout

A

Alfio Massimiliano Gliozzo

IBM

J

Junkyu Lee

IBM

N

Nahuel Defosse

IBM

Find Similar Experts

AI experts on LinkedIn & GitHub

References (13)

[1]
Agentic Design Patterns: A System-Theoretic Framework
2026Minh-Dung Dao, Quy Minh Le et al.
[2]
Measuring Agents in Production
2025Melissa Z. Pan, Negar Arabzadeh et al.
[3]
OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning
2025Marianne Menglin Liu, Sai Ashish Somayajula et al.
[4]
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
2025Jonathan Bragg, Mike D'Arcy et al.
[5]
Transduction is All You Need for Structured Data Workflows
2025A. Gliozzo, Naweed Khan et al.
[6]
DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
2024Bodhisattwa Prasad Majumder, Harshit Surana et al.
[7]
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
2024Taicheng Guo, Xiuying Chen et al.
[8]
DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
2024O. Khattab, Arnav Singhvi et al.
[9]
A survey on large language model based autonomous agents
2023Lei Wang, Chengbang Ma et al.
[10]
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
2023Jinyang Li, Binyuan Hui et al.
[11]
ReAct: Synergizing Reasoning and Acting in Language Models
2022Shunyu Yao, Jeffrey Zhao et al.
[12]
Iso/iec
2008Shashi Shekhar, Hui Xiong
[13]
: Large
Nghia Duong-Trung, Xia Wang et al.

Founder's Pitch

"Agentics 2.0 is a Python framework enabling reliable and scalable agentic data workflows with logical transduction algebra."

AI Workflow AutomationScore: 8View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

3/4 signals

7.5

Quick Build

4/4 signals

10

Series A Potential

2/4 signals

5

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 3/4/2026

🔭 Research Neighborhood

Generating constellation...

~3-8 seconds

Why It Matters

This research matters because it provides a structured method for creating reliable and scalable agentic AI workflows which are crucial for transitioning AI from research to production in enterprise settings.

Product Angle

To productize Agentics 2.0, transform it into a robust enterprise solution with integrations into existing data processing tools and platforms, emphasizing its reliability and scalability features.

Disruption

Agentics 2.0 could replace less reliable AI workflow automation tools that do not offer strong typing or semantic observability, which are critical for enterprise-scale deployment.

Product Opportunity

The market includes companies transitioning to AI for data processing, particularly those needing reliability and observability in their workflows. Companies in finance, healthcare, and logistics could pay for a more reliable AI solution in their data workflows.

Use Case Idea

Enterprise data automation in industries requiring reliable AI workflows, such as finance for credit risk assessment and administration for automated document processing.

Science

Agentics 2.0 utilizes a programming model that transforms LLM inferences into typed, composable functions that enforce schema validity and facilitate asynchronous, parallel processing. This model is based on logical transduction algebra which converts LLM inference into typed semantic transformations called transducible functions.

Method & Eval

Agentics 2.0 was tested on challenging benchmarks like DiscoveryBench and Archer, demonstrating state-of-the-art performance, particularly in data-driven discovery and NL-to-SQL semantic parsing tasks.

Caveats

The success of Agentics 2.0 depends on its integration simplicity with existing systems and the ability of users to effectively adapt to its programming model, which could be complex for teams not familiar with functional or typed paradigms.

Author Intelligence

Alfio Massimiliano Gliozzo

IBM
gliozzo@us.ibm.com

Junkyu Lee

IBM
junkyu.lee@ibm.com

Nahuel Defosse

IBM
nahuel.defosse@ibm.com