Beyond Prompting: Agentic Workflows as Execution Graphs

X postniccoOpinion

Citing a Stanford lecture by Andrew Ng, author nicco highlights why zero-shot prompt engineering is reaching its limits and being replaced by autonomous execution graphs, supported by a guide on moving away from linear agent chains.

Key points

  1. Andrew Ng claims prompting will be obsolete in six months, replaced by dynamic execution graphs.
  2. Workflow architectures are progressing from linear chains and tool loops toward directed graphs and self-improving systems.
  3. Linear agent scripts often execute sequentially even when steps do not depend on preceding data, causing latency and context bloat.
  4. Nodes represent discrete units of work bound by schemas, while edges define explicit data contracts between them.
  5. Tooling like Claude Code's dynamic workflows uses plain JavaScript for orchestration, eliminating model token consumption for pure coordination logic.

Why it matters

As prompt tweaking hits ceilings on complex workflows, shifting to graph-based orchestration lets developers run independent tasks concurrently and isolate failures, dramatically lowering costs and latency.

Analysis

The architectural shift highlighted here moves AI engineering closer to distributed systems design. By restricting LLMs to bounded judgment calls and delegating routing, filtering, and flow control to deterministic code, systems gain reliability without burning tokens on orchestration plumbing.

Original post

nicco

@0xnicc0 · 11 September 2026

Google Brain founder, Andrew Ng: "Prompting will be dead in 6 months Graphs are what's replacing it" In 2 hours at Stanford, he breaks down why zero-shot prompt engineering has hit a hard ceiling—and how to replace it with autonomous execution graphs Prompts → Linear Chains t.co/pPl8cLn04y t.co/G77u3TdKuF

148 likes4 replies275 bookmarks25.1k views

View on X
Selected replies (4)
  • @AIGryffindor @0xnicc0 Andrew Ng says prompting is dead in 6 months. Meanwhile I just got good at it. Guess my resume expires next quarter.
  • @fkurka @0xnicc0 whatever the ai say , it's their job to figure it out
  • @aiseomastery @0xnicc0 prompting dead in 6 months, bold claim
  • @salesoptecs @0xnicc0 Graphs help because they make the dependencies explicit. Same reason a schema beats a prompt for anything you need to audit later.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:Mahax

    Moving Beyond Prompts to Loops and Graphs in AI Systems

    Citing Andrew Ng, Mahax highlights the shift from single-shot prompting to agentic loops and graphs. An accompanying guide outlines the architecture of AI agents, self-evaluating feedback loops, and graph-based execution pipelines using Claude.

    11.8kbookmarks1mviews

    AI & LLMs· Resource

  • X post:nicco

    Graph Engineering Over Prompting: Why Agent Workflows Require Graph Architectures

    A post by nicco highlights remarks by Andrej Karpathy asserting that prompting is an ephemeral interface and that graph architectures represent the true architectural layer for agent workflows. It pairs this with a practical guide by seeco on replacing sequential agent chains with explicit graphs.

    529bookmarks58.5kviews

    AI & LLMs· Resource

  • X post:Mahax

    Graph Engineering: Why Agent Workflows Depend on Graphs

    Mahax cites Andrej Karpathy's claim that prompting is disappearing in favour of graphs, and provides a practical guide on graph engineering with Claude to optimise AI agent workflows.

    2.4kbookmarks240.8kviews

    AI & LLMs· Opinion

  • X post:codila

    Graph Engineering: Multi-Agent Systems and Dynamic Workflows

    Codila highlights a free two-hour Google course on graph engineering for multi-agent systems and outlines how to evolve beyond linear agent sequences into networked parallel graphs. Using Dynamic Workflows in Claude Code v2.1.154+, the guide demonstrates orchestrating hundreds of agents simultaneously without exhausting context windows.

    6.8kbookmarks465.4kviews

    AI & LLMs· Tutorial

  • X post:Kirill

    From Loop Engineering to Graph Engineering: Deterministic AI Architectures

    Kirill describes an architectural shift in agent development from fragile single-agent loops to Graph Engineering. He argues that system reliability depends not on larger models or more agents, but on deterministic structures using nodes, edges, state verifiers, and knowledge graphs.

    27.3kbookmarks2.7mviews

    AI & LLMs· Opinion

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.