What is a Large Causal Model? Reconciling three competing definitions
We define the Large Causal Model, and how it differs from three academic uses of the term and from a standard large language model.
ArticleCAUSALITY
Four Agents. One Unified Causal Clarity.
Most AI agents retrieve and summarize. POEM365's four causal Decision Agents forecast, plan, optimize and explain enterprise growth. See how they work.
I have been to many conferences recently. And agents are everywhere. Gartner put Multi-agent AI on the 2025 Hype Cycle. Every vendor has an agent story. Every deck has an agentic workflow slide.
But most of them sit at the application layer. A new wrapper on the same correlation engine. They retrieve, they summarize, they automate a workflow.
Ours do something different.
They are Decision Agents — Causal POETS — because they show causation, not just correlation. They tell you what is actually causing your growth to move, and what to do about it next.
The Four Decision Agents
01 Forecasting Agent · Answers: What’s coming
“What’s my revenue trajectory over the next 6 months?”
Causal forecast. Not extrapolation.
02 Planning Agent · Answers: What if
“How would shifting 30% of my budget impact revenue growth?”
Scenario simulation. Before you commit.
03 Optimization Agent · Answers: What to do
“How should I allocate my budget to maximize revenue growth?”
Prescriptive allocation. Not guesswork.
04 Insights Agent · Answers: Why
“What’s causing my revenue growth to accelerate or stall?”
Root cause. Not correlation.
AGENTIC SWARM ARCHITECTURE
Each Agent Owns One Step in the Growth Decision.
The Cycle That Closes the Loop
The four agents work as a cycle. You forecast, you plan, you optimize — and at any point, Insights tells you why the numbers are moving.
Forecasting
What’s coming
Planning
What if
Optimization
What to do
Insights
Why
Insights runs at every step — always explaining what’s causing the numbers to move
Most agents: retrieve, summarize, automate a workflow.
Causal POETS: diagnose, simulate, prescribe, explain.
That’s our multi-agent universe for growth.
Author:
All Authors
Bharath Gaddam
Founder & CEO
Founder Bharath Gaddam had a clear diagnosis: the problem wasn't data or talent, it was architecture. Correlation-based models were never going to cut it for the complexity of enterprise growth. The industry wasn't under-resourced. It was fundamentally mis-built.
See what Data Poem can do for you.
Let's talk about how we can help you grow your business.
