For decades, the story of data platforms has been one of centralization and heavy engineering. We built massive data warehouses and data lakes, but accessing their insights required deep technical expertise. Business users couldn’t simply ask questions; they had to navigate a complex process involving specialized data engineers to build painstaking ETL pipelines, optimized queries, and specific dashboards. This highly technical approach created a rigid, monolithic source of truth that, while powerful, was slow to adapt and created significant bottlenecks. It left decision-makers waiting days or even weeks for answers, completely dependent on an over-burdened engineering team. Instead of a single, all-knowing monolith, imagine a collaborative ecosystem where domain experts describe their data in natural language, providing context that empowers a network of intelligent, autonomous agents. Each agent becomes an expert in its domain — sales, marketing, logistics, finance — managing its own data by combining human-provided descriptions with its own skills to answer questions. This is the future of data platforms: a system that is agentic, distributed, and truly collaborative. agentic, distributed, and truly collaborative I created a new open-source project, Da2a, to explore this paradigm. It’s a prototype that demonstrates how a multi-agent system can tackle complex data analysis by working together. Da2a Da2a The Old Way vs. The New Paradigm The traditional data platform is engineering-focused. The primary challenge is moving, storing, and modeling data. Answering a simple business question like, “What’s the ROI on our latest social media campaign?” could involve: The traditional data platform is engineering-focused “What’s the ROI on our latest social media campaign?” Filing a ticket with the data engineering team.Waiting for them to build a new pipeline to join marketing spend data with sales data.Having an analyst write a complex SQL query across multiple massive tables.Finally, getting a report back, hoping the initial question hasn’t become irrelevant. Filing a ticket with the data engineering team. Waiting for them to build a new pipeline to join marketing spend data with sales data. Having an analyst write a complex SQL query across multiple massive tables. Finally, getting a report back, hoping the initial question hasn’t become irrelevant. The agentic approach is insight-focused. Instead of a centralized database, you have specialized agents. For instance, the Marketing Agent knows everything about campaign spending and lead acquisition. On the other hand, the E-commerce Agent is an expert on orders, products, and revenue. The agentic approach is insight-focused Marketing Agent E-commerce Agent To answer that same question, you simply ask a root “Orchestrator Agent.” The orchestrator understands the goal, formulates a plan, and collaborates with the specialist agents to get the answer. The focus shifts from the how (engineering) to the what (the business question). how what Meet Da2a: An Agentic Platform in Action Da2a implements this vision with a root orchestrator and two specialized agents: one for an e-commerce dataset and another for a marketing dataset, both based on real-world data from the Olist store in Brazil. e-commerce marketing Olist store in Brazil GitHub Repository: https://github.com/fmind/da2a GitHub Repository: https://github.com/fmind/da2a Live Demos: Live Demos: Root Orchestrator: https://da2a.fmind.dev/Marketing Agent: https://da2a-marketing.fmind.dev/E-commerce Agent: https://da2a-ecommerce.fmind.dev/ Root Orchestrator: https://da2a.fmind.dev/ https://da2a.fmind.dev/ Marketing Agent: https://da2a-marketing.fmind.dev/ https://da2a-marketing.fmind.dev/ E-commerce Agent: https://da2a-ecommerce.fmind.dev/ https://da2a-ecommerce.fmind.dev/ You can ask the e-commerce agent, “How many orders were placed in São Paulo?” or the marketing agent, “What were our top lead sources last year?”. Better yet, you can ask the root orchestrator a question that requires both, like, “What is the total sales revenue from sellers who were acquired via ‘Display’ advertising?” “What is the total sales revenue from sellers who were acquired via ‘Display’ advertising?” The Architecture: Collaboration via the A2A Protocol The magic that makes this collaboration possible is the Agent-to-Agent (A2A) protocol. A2A provides a standardized way for agents to communicate their capabilities and call upon each other’s skills over a network. Agent-to-Agent (A2A) protocol Agent-to-Agent (A2A) protocol A Root Agent: The orchestrator that receives user requests, plans the execution, and delegates tasks.Domain Agents: The ecommerce_agent and marketing_agent, each running as an independent service with its own database.Agent Cards: Each domain agent exposes a JSON “agent card” that acts like a digital business card, describing its name, capabilities, and how to communicate with it. A Root Agent: The orchestrator that receives user requests, plans the execution, and delegates tasks. A Root Agent A Root Agent : Domain Agents: The ecommerce_agent and marketing_agent, each running as an independent service with its own database. Domain Agents: ecommerce_agent marketing_agent Agent Cards: Each domain agent exposes a JSON “agent card” that acts like a digital business card, describing its name, capabilities, and how to communicate with it. Agent Cards Agent Cards : The root agent is configured to know about these remote agents. Here is a simplified look at the code from the da2a agent.py file, which sets up the connection to the remote agents using their "agent cards." agent.py import google.adk.agents.remote_a2a_agent as a2a
import google.adk.tools.agent_tool as at

# The URL points to the 'agent card' of the remote agent
AGENT_CARD_ECOMMERCE = "[https://da2a-ecommerce.fmind.dev/a2a/ecommerce/.well-known/agent-card.json](https://da2a-ecommerce.fmind.dev/a2a/ecommerce/.well-known/agent-card.json)"
AGENT_CARD_MARKETING = "[https://da2a-marketing.fmind.dev/a2a/marketing/.well-known/agent-card.json](https://da2a-marketing.fmind.dev/a2a/marketing/.well-known/agent-card.json)"

# Create local proxy objects for the remote agents
ecommerce_agent = a2a.RemoteA2aAgent(
    name="ecommerce_agent",
    agent_card=AGENT_CARD_ECOMMERCE,
    description="Answers questions about e-commerce data..."
)
marketing_agent = a2a.RemoteA2aAgent(
    name="marketing_agent",
    agent_card=AGENT_CARD_MARKETING,
    description="Answers questions about marketing data..."
)

# The root agent uses these agents as 'tools' to solve problems
root_agent = LlmAgent(
    ...
    tools=[at.AgentTool(ecommerce_agent), at.AgentTool(marketing_agent)],
    ...
) import google.adk.agents.remote_a2a_agent as a2a
import google.adk.tools.agent_tool as at

# The URL points to the 'agent card' of the remote agent
AGENT_CARD_ECOMMERCE = "[https://da2a-ecommerce.fmind.dev/a2a/ecommerce/.well-known/agent-card.json](https://da2a-ecommerce.fmind.dev/a2a/ecommerce/.well-known/agent-card.json)"
AGENT_CARD_MARKETING = "[https://da2a-marketing.fmind.dev/a2a/marketing/.well-known/agent-card.json](https://da2a-marketing.fmind.dev/a2a/marketing/.well-known/agent-card.json)"

# Create local proxy objects for the remote agents
ecommerce_agent = a2a.RemoteA2aAgent(
    name="ecommerce_agent",
    agent_card=AGENT_CARD_ECOMMERCE,
    description="Answers questions about e-commerce data..."
)
marketing_agent = a2a.RemoteA2aAgent(
    name="marketing_agent",
    agent_card=AGENT_CARD_MARKETING,
    description="Answers questions about marketing data..."
)

# The root agent uses these agents as 'tools' to solve problems
root_agent = LlmAgent(
    ...
    tools=[at.AgentTool(ecommerce_agent), at.AgentTool(marketing_agent)],
    ...
) Each domain agent is served via the Agent Development Kit’s (ADK) web server, which automatically exposes the A2A endpoints and the agent card. Agent Development Kit’s # Command to serve an agent and enable A2A communication
adk web --a2a # Command to serve an agent and enable A2A communication
adk web --a2a This simple, powerful mechanism allows us to build a distributed system where components can be developed, deployed, and scaled independently. The Benefits of Thinking Agentically This approach unlocks several powerful advantages: Human-Like Task Handling: Agents can tackle complex, multi-step tasks that require synthesizing information from different domains, much like a human analyst would.Scalability and Extensibility: Adding a new data domain is as simple as building and deploying a new agent. No need to re-architect the entire platform. The system grows organically.Focus on High-Level Value: It abstracts the underlying engineering complexity. Data consumers and developers can focus on defining business logic and asking high-level questions, not on writing SQL or managing data pipelines.Autonomous and Collaborative: Each agent is a valuable tool on its own, but their true power is unlocked when they collaborate through an orchestrator to solve problems that no single agent could handle alone. Human-Like Task Handling: Agents can tackle complex, multi-step tasks that require synthesizing information from different domains, much like a human analyst would. Human-Like Task Handling: Scalability and Extensibility: Adding a new data domain is as simple as building and deploying a new agent. No need to re-architect the entire platform. The system grows organically. Scalability and Extensibility: Focus on High-Level Value: It abstracts the underlying engineering complexity. Data consumers and developers can focus on defining business logic and asking high-level questions, not on writing SQL or managing data pipelines. Focus on High-Level Value: Autonomous and Collaborative: Each agent is a valuable tool on its own, but their true power is unlocked when they collaborate through an orchestrator to solve problems that no single agent could handle alone. Autonomous and Collaborative: The Road Ahead: Limitations and Future Work Da2a is a prototype, and building an industrial-grade agentic data platform requires solving some interesting challenges: Efficient Data Transfer: A2A is excellent for orchestrating tasks and passing small payloads of text or JSON. It is not designed for transferring gigabytes of data between agents. For that, we’d need to integrate mechanisms that point agents to shared data storage.Dynamic Agent Discovery: Currently, the root agent’s knowledge of other agents is hardcoded. A production system would need a discovery service or a registry where agents can dynamically register themselves and their skills.Memory and Learning: The agents in this prototype are stateless. The next frontier is to give them memory, allowing them to learn from past interactions, recall previous results, and improve their planning and execution over time. Efficient Data Transfer: A2A is excellent for orchestrating tasks and passing small payloads of text or JSON. It is not designed for transferring gigabytes of data between agents. For that, we’d need to integrate mechanisms that point agents to shared data storage. Efficient Data Transfer: Dynamic Agent Discovery: Currently, the root agent’s knowledge of other agents is hardcoded. A production system would need a discovery service or a registry where agents can dynamically register themselves and their skills. Dynamic Agent Discovery: Memory and Learning: The agents in this prototype are stateless. The next frontier is to give them memory, allowing them to learn from past interactions, recall previous results, and improve their planning and execution over time. Memory and Learning: Conclusion: A New Frontier for Data The agentic paradigm represents a fundamental shift in how we think about data architecture. We are moving from rigid, centralized systems to dynamic, decentralized ecosystems of intelligent specialists. This approach promises to create data platforms that are more flexible, more powerful, and more aligned with the way businesses actually work. There is still much to build, but the potential is immense. The future of data isn’t just about bigger databases or faster queries; it’s about collaboration, intelligence, and a network of agents working together to turn data into insight.

GitHub

The Data Stack’s Next Form Factor: Multi-Agent Systems

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Build a Mini “Photoshop Factory” in Python: Gradio + Cloud Run + AI

What Are Convolution Neural Networks? [ELI5]

The Noonification: Have U Been Pwned? (1/12/2023)

Goldman Sachs, Data Lineage, and Harry Potter Spells

People are still crazy about Python after twenty-five years

10 Questions to Consider when Setting up a Corporate A.I project

Build a Mini “Photoshop Factory” in Python: Gradio + Cloud Run + AI

What Are Convolution Neural Networks? [ELI5]

The Noonification: Have U Been Pwned? (1/12/2023)

Goldman Sachs, Data Lineage, and Harry Potter Spells

People are still crazy about Python after twenty-five years

10 Questions to Consider when Setting up a Corporate A.I project

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps