Back to AI Jason

I don't prompt agents anymore...

AI JasonAugust 25, 202622m

Topics10

What is Graph Engineer0:00 Three Types of Graphs Being Discussed0:30 The Shift from Human Prompting to Agent Prompting3:00 The Need for Reliability6:30 Control Graph Components7:00 Existing Graph Examples8:00 Two Implementation Methods11:00 Design Patterns for Large Model as Graph12:30 Super Design Implementation Examples15:00 Key Recommendations21:00

In a Nutshell

The core shift is that humans now prompt orchestrator agents who manage teams of sub-agents rather than directly prompting individual agents. This requires control graphs—dynamic workflows with nodes (agent actions), edges (next steps), and state (persistent data)—implemented either as documented SOPs that large models follow or as code-based systems like LangGraph. Reliability demands separate verifier nodes, clear input/output boundaries, and deterministic scripts for testing, since agents can no longer self-verify their work effectively.

AI-Generated Notes

These notes were generated by AI and may contain inaccuracies.

The term "graph engineer" has become confusing because people are mixing three different concepts under the same term. Peter Wei's tweet about shifting from loops to graphs was the catalyst, but the discussion became muddled as people conflated control graphs, knowledge graphs, and graph of loops.

Control Graph

Control graph refers to dynamic workflow systems like LangGraph or dynamic workflow features. These are essentially SOPs (standard operating procedures) that ensure agents produce more reliable results. This is the graph Peter Wei was actually referring to, as his use case involved shipping code changes with defined control flow.

Knowledge Graph

Knowledge graphs represent relationships between different entities for more effective data retrieval. This concept is completely different from control graphs but got conflated when Andrew Ng released a one-hour course on building knowledge graphs. Companies like Graphiti have been shipping with graph memory for years.

Graph of Loops

This concept, brought forward by Colors, addresses how to manage multiple loops running simultaneously in future companies. The challenge is ensuring all loops execute well and improve continuously, since errors and improvements compound quickly across multiple loops. This remains an unexplored space with no established solutions yet.

The fundamental shift occurring is teams moving from humans prompting agents to having other agents prompt agents on behalf of humans. Two patterns are emerging:

Loops Pattern: Instead of human prompting for every task, triggers can be:

Time-based (daily GitHub issue fixes)
Goal-based (continuous frontend optimization)
Event-based (email-triggered agent responses)

Humans only become involved when agents determine it's necessary.

Octra Trader Pattern: Humans communicate with an orchestrator agent that has full context and can spin up teams of agents for execution and monitoring. Boris (creator of Claude Code) noted he now talks to Claude who talks to other Claudes rather than prompting agents directly.

Sign in to read the full notes

Get access to AI-generated notes, topic timestamps, and more.