Learnings from implementing Multi-Agent Systems & Sequential Workflows

Part of my learning experience to understand agentic systems and how Deep-Research works

I wanted to replicate deep research pipeline to learn more about agents for use cases like automating market research reports. Instead of relying on existing frameworks like Agents SDK, I decided to implement agents myself to understand the concepts better and also have control over state and storage.

My Initial Multi-Agent Approach

I built a single master orchestrator agent that analyzed incoming messages and routed them to specialized agents for:

• Web search

• Tool calls

• Analysis

• Summary

• Chat

This worked at first, but revealed some issues as the context grew:

• After 5–10 messages, the orchestrator started sending queries to the chat agent instead of the analysis agent, likely due to memory handoff issues.

• The tool call accuracy dropped to 50-60% after 10 messages.

• It would call the web search tool 3 times for the same question

• The orchestrator struggled to keep track of what it was doing, a common limitation of simple master-agent setups without structured memory.

• Despite extensive prompt engineering, the fundamental issues persisted.

Moving to Sequential Workflows

To overcome these issues, I rebuilt the system with a deterministic, stage-based workflow:

1. Clarification check - asks clarifying question after assessing user request

2. Topic generation - generates topics to analyze based on user query

3. Question generation - generates 5-10 questions related to the topic for the user query

4. Answer research - web search enabled LLM request to answer the question

5. Analysis on Data - LLM request to analyze data uploaded by user in context of the query.

6. Summary generation - Final summary generation covering all topics

7. Chat - Chat on the summary and data generated during the analysis

Benefits of this architecture:

• Each stage is independent and resumable (if stage 3 fails, retry just that stage), with proper handoff and state

• Defined Scope reduced hallucinations — each LLM call has one specific job.

• Deterministic tool use — no agent confusion about whether to use tool or not, is defined by the stage.

Key learnings for complex workflows

• No method is absolutely perfect: For well-defined workflows, let code enforce orchestration, retries, and state — while agents handle judgment tasks like clarification, research, and synthesis.

• For reliability, make tool calls stage driven, not agent decided. Yes, this means unnecessary web searches when entering the "research" stage, but the trade-off is worth it for predictable, reliable behavior.

• Agents work better when scope is staged narrowly and state is saved, so errors are contained and retries only affect that step, not the whole workflow.

Next target: Implementing the same deep-research workflow using Agents SDK to explore structured memory, state persistence, and more reliable task handoff.

---

Interested in reading more content on AI systems and startup journey? Subscribe to thought.bitsnbytes.in