Graph Engineering for Agents: Roadmap for Parallel Workflows in Claude Code

X postCodezResource

An X post by Codez quotes Claude Code creator Boris Cherny claiming that agent systems will shift from manual prompting to graphs and loops. The post introduces a guide outlining graph-based architectures for multi-agent execution.

Key points

  1. Codez attributes a statement to Boris Cherny predicting that developers will transition to 'graph engineering' for agentic systems within 3 to 6 months.
  2. Public replies point out that Cherny did not explicitly mention 'graphs' or 'loops' during the referenced interview.
  3. The linked article advocates replacing linear chains (step A, then B) with dependency graphs where nodes represent tasks and edges represent data flow.
  4. Subagents can run concurrently via `parallel()` barriers, avoiding context window bloat in the main session.
  5. Orchestration is handled via plain JavaScript scripts, meaning task coordination incurs zero model token costs.

Why it matters

Linear multi-step agents are inherently slow, fragile, and prone to context exhaustion. Designing agent workflows as execution graphs unlocks concurrency, clear data contracts, and scalable fleet execution.

Analysis

The post pairs an attention-grabbing quote attributed to Boris Cherny with a technical breakdown of graph engineering. Although commenters dispute whether Cherny used those exact terms, the linked framework details practical orchestration techniques: isolating subagents with strict JSON schemas, executing tasks in parallel, and handling dependencies in code rather than through continuous LLM conversation.

Original post

Codez

@0xCodez · 7 August 2026

Creator of Claude Code: “I’m not prompting my agents anymore. I’m building "graphs" and "loops" - they’re building my agent. in 3-6 months, we’ll all be doing graph engineering for our agentic systems.” in 10-minute talk, Boris Cherny revealed what the future of agentic t.co/TvZhMmhx4t t.co/Iv8LpdGaPB

2.5k likes80 replies5.4k bookmarks549.2k views

View on X
More posts in the thread (4)
  1. @adiix_official Thanks Adix. Have you read this article on Graphs already ?
  2. @0xcato_ That’s how everyone coding setup will looks like very soon
  3. @0xShoopy Yeah. Totally agree on this bro
  4. @AnhV4htj Real chad ! Time to deep dive into graphs
Selected replies (5)
  • @hfinn000 @0xCodez He does not mention graphs or loops anywhere in the interview.
  • @mafiaboy_tk @0xCodez 야 그만해! t.co/n2vHCpNbrd
  • @randomlife2104 @0xCodez @grok did he really said „graph“ in that Video?
  • @iamalnewkirk @0xCodez REPEAT AFTER ME: THESE ARE LUXURY WORKFLOWS. THIS IS NOT FOR THE POOR!!! (or cost conscious)
  • @Rolfsselas @0xCodez @grok eli5 graphs and loops, and point me in the direction to learn more most economic and time effective way possible

Mentioned links

Links and tools from this entry

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: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:rvaniaaa

    Graph Engineering for AI Agents: Replacing Linear Chains with Parallel Workflows

    rvaniaaa contends that the primary bottleneck in multi-agent workflows is geometry rather than model intelligence. Switching from sequential agent chains to graph-based architectures allows parallel execution and substantially reduces overall execution time.

    2.9kbookmarks233.5kviews

    AI & LLMs· Tutorial

  • 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:nicco

    Beyond Prompting: Agentic Workflows as Execution Graphs

    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.

    275bookmarks25.1kviews

    AI & LLMs· Opinion

  • 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

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.