The Future of Agentic Workflows with Gemini 2.5
For the past couple of weeks, I’ve been conducting experiments with a couple of different types of agentic frameworks, mainly:
Workflows: predictable, code-driven pipelines with LLMs + tools.
Hierarchical Agents (aka Supervisors): an agent design with dynamic feedback where a Supervisor agent guides the process by delegating to other agents; agents can take actions and make decisions with autonomy.
Supervisors have a high degree of autonomy, including making decisions around which agents to delegate to and when to end the workflow.
Agent architectures are more attractive when you want to combine already pre-built ReAct agents with existing toolsets in a workflow.
Workflows are more reliable for production apps when orchestration needs to be deterministic.
OpenAI’s “Agentic” Whitepaper Missed the Point
Two days after OpenAI released their agentic whitepaper, Harrison Chase (LangChain’s Co-founder) wrote a sharp critique on how to think about agentic apps.
If you care even a little bit about where AI workflows and LLM orchestration are headed—you’ll want to read this.
Everything You Need to Know about AI Agents
Chatbots answer questions.
AI agents get things done.
Earlier in the week, I shared an Agentic JIRA POC and joked that it would automate the rest of my JIRA stories…