{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "747",
  "slug": "developers-orchestrate-agent-code",
  "edition": "2026-10-29T00",
  "url": "https://hangingcontext.com/stories/2026-10-29/developers-orchestrate-agent-code/",
  "newsroom": "artificial-intelligence",
  "beat": "developers",
  "newsroom_title": "Artificial Intelligence",
  "angle": "Developers now orchestrate agents, pick models per task and pay by the token, so the job shifts to review",
  "headline": "Developers stop writing code and start orchestrating agents",
  "dek": "GitHub reports record agent-started work, multi-model sessions and a new orchestration layer, while cost data says how you run agents matters as much as which model you pick.",
  "published_at": "2026-10-29T01:05:59Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 4 sources",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 4,
  "publishers": [
    "github-old-blog",
    "pydantic-articles",
    "replit-engineering"
  ],
  "key_facts": [
    {
      "text": "As of September 2026, more than 40 percent of pull requests on GitHub are started with an agent, and agent-started pull requests change multiple files about 87 percent of the time.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793211651332244430",
          "claim_ids": [
            "1793211895034518072",
            "1793211895066522148"
          ]
        }
      ]
    },
    {
      "text": "Developers pushed code to GitHub 17.9 billion times in the past 12 months, and commits across all repository types climbed to 34.3 billion in 2026.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793211651332244430",
          "claim_ids": [
            "1793211895031136383",
            "1793211895033114809"
          ]
        }
      ]
    },
    {
      "text": "In September 2026, 61 percent of GitHub Copilot users selected more than one model for their sessions.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793211651332244430",
          "claim_ids": [
            "1793211895041962024"
          ]
        }
      ]
    },
    {
      "text": "Code mode roughly halved cost and wall time for long tasks across eight models in Pydantic AI internal benchmarking.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793227403842788278",
          "claim_ids": [
            "1793227681583976822"
          ]
        }
      ]
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "The scale of agent-started work",
      "paragraphs": [
        {
          "markdown": "Developer activity on GitHub reached record levels in 2026, with developers pushing code 17.9 billion times in the past 12 months and commits across all repository types climbing to 34.3 billion in 2026. GitHub now serves more than 225 million developers, and GitHub Actions ran a job 1,440 times every second in 2026, with 5.8 billion push protection scans run in the same year. The volume changes the job: review and orchestration now matter as much as writing the first draft.",
          "cites": [
            {
              "manifest_id": "1793211651332244430",
              "claim_ids": [
                "1793211895031136383",
                "1793211895033114809",
                "1793211895053927426",
                "1793211895046380833",
                "1793211895068432152"
              ]
            }
          ]
        },
        {
          "markdown": "As of September 2026, more than 40 percent of pull requests on GitHub are started with an agent, and agent-started pull requests change multiple files about 87 percent of the time. Agent work is not small, single-file edits. It arrives as multi-file changes that need review across a whole change set.",
          "cites": [
            {
              "manifest_id": "1793211651332244430",
              "claim_ids": [
                "1793211895034518072",
                "1793211895066522148"
              ]
            }
          ]
        },
        {
          "markdown": "TypeScript, Python and JavaScript are the top three languages on GitHub by contributor count, and Rust grew fastest by percentage among the top languages in 2026. Repositories serving mining, construction, health care and agriculture have grown several times over since 2022, which suggests agent-assisted development is spreading into industries that were not the early adopters of developer tooling.",
          "cites": [
            {
              "manifest_id": "1793211651332244430",
              "claim_ids": [
                "1793211895063199125",
                "1793211895065711189",
                "1793211895061649352"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Orchestration becomes the product",
      "paragraphs": [
        {
          "markdown": "At GitHub Universe 2026, GitHub presented its vision of an agentic software delivery system, with the GitHub Copilot app connecting agents and tools across projects so developers can direct work without manual handoffs. Copilot projects allow users to run agent work across multiple repositories in fully managed, parallel sessions, and session continuity allows cloud agent sessions to persist across the GitHub app, VS Code, the command line interface and the web.",
          "cites": [
            {
              "manifest_id": "1793211651331795478",
              "claim_ids": [
                "1793211890007668529",
                "1793211890013860507",
                "1793211890021124814",
                "1793211890025603256"
              ]
            }
          ]
        },
        {
          "markdown": "In September 2026, 61 percent of GitHub Copilot users selected more than one model for their sessions, and Copilot Fusion is generally available to provide model orchestration. Fusion evaluates tasks across reasoning, code generation, debugging and tool use to choose the best model for execution, and GitHub reports that Fusion Max scored within two points of Opus 5.5 Max at half the cost and 40 percent less time per task. Copilot automations allow users to create AI-powered workflows that learn from outcomes to propose improvements, and Copilot code review Max posted the highest F1 score on ReviewBench for high-severity issues.",
          "cites": [
            {
              "manifest_id": "1793211651332244430",
              "claim_ids": [
                "1793211895041962024",
                "1793211895062294167"
              ]
            },
            {
              "manifest_id": "1793211651331795478",
              "claim_ids": [
                "1793211890015434340",
                "1793211890019741119",
                "1793211890028447632",
                "1793211890029522438"
              ]
            }
          ]
        },
        {
          "markdown": "GitHub Enterprise customers can use all Copilot features without a separate subscription by paying for AI credits, and GitHub added 4 million CPU cores, 160 petabytes of high-speed storage and 50 terabits per second of network capacity this year. The pricing shift to credits points the same way as the infrastructure build: agent work is expected to be metered and parallel, not occasional.",
          "cites": [
            {
              "manifest_id": "1793211651331795478",
              "claim_ids": [
                "1793211890035071519",
                "1793211890037775813",
                "1793211890038258563"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "How you run the agent changes the bill",
      "paragraphs": [
        {
          "markdown": "Pydantic AI internal benchmarking of code mode, where models write and execute code loops instead of calling tools one by one, found that code mode roughly halved cost and wall time for long tasks across eight models. Success rates for long tasks of 200 items dropped to 62 to 79 percent without code mode, compared with 92 to 100 percent with it. Code mode reduces the volume of tokens processed in each request rather than just reducing round trips, and it allows models to design workflows on the fly by writing code that acts as a graph.",
          "cites": [
            {
              "manifest_id": "1793227403842788278",
              "claim_ids": [
                "1793227681583976822",
                "1793227681586736788",
                "1793227681589315725",
                "1793227681596737374"
              ]
            }
          ]
        },
        {
          "markdown": "The same benchmarking found a trade-off at small scale. At 5 items, code mode cost 21 to 38 percent more than standard tool calling on three of five tasks, and code mode guidance adds a flat fee of approximately 2,600 characters per request. Models like gpt-6.1-sol and Claude models already perform batching of tool calls without code mode, and Pydantic notes that speculative execution showed higher costs and lower success in initial tests, while code mode failures can lead to repeated writes if a snippet is rerun after a partial failure. The lesson is to match the orchestration to the task size rather than treating one mode as always cheaper.",
          "cites": [
            {
              "manifest_id": "1793227403842788278",
              "claim_ids": [
                "1793227681588338613",
                "1793227681592350891",
                "1793227681594629773",
                "1793227681597868522",
                "1793227681599674185"
              ]
            }
          ]
        },
        {
          "markdown": "The interpreter used in Pydantic AI Harness, Monty, starts with no host access and enforces a 30-second execution limit, which is a reminder that letting a model write and run code needs a sandbox with real limits. Replit makes the same point at platform level: it uses microVMs to provide isolated execution environments for AI agents, its credential broker retrieves secrets from a vault and adds them to requests only after authorization, and its Agent Habitat framework provides governance tools including audit logs and role-based permissions.",
          "cites": [
            {
              "manifest_id": "1793227403842788278",
              "claim_ids": [
                "1793227681591828438"
              ]
            },
            {
              "manifest_id": "1793225009138867843",
              "claim_ids": [
                "1793225316534283510",
                "1793225316536657881",
                "1793225316538005247"
              ]
            }
          ]
        },
        {
          "markdown": "Replit runs AI red teaming around the clock, offers Bring Your Own Cloud so companies can host agent harnesses in their own cloud tenant, and is developing an agent-action policy system with organization-wide limits. Replit also reports that internal code output for a consistent cohort of engineers grew 2.9 times between January and June. That company-reported growth figure should be read alongside the isolation detail, because output growth without isolation is a liability, not a win.",
          "cites": [
            {
              "manifest_id": "1793225009138867843",
              "claim_ids": [
                "1793225316539697253",
                "1793225316545906136",
                "1793225316547828461",
                "1793225316548340812",
                "1793225316541851277"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "What changes for developers",
      "paragraphs": [
        {
          "markdown": "This suggests the developer job is becoming a review and orchestration job. When more than 40 percent of pull requests start with an agent, when most Copilot users already pick more than one model, and when the orchestration choice can halve the cost of a long task or raise it on a short one, the skill that matters is judging a multi-file change, picking the right model and mode for the task, and keeping agent execution inside a sandbox with audit logs. Writing the first draft is no longer the scarce step.",
          "cites": [
            {
              "manifest_id": "1793211651332244430",
              "claim_ids": [
                "1793211895034518072",
                "1793211895041962024"
              ]
            },
            {
              "manifest_id": "1793227403842788278",
              "claim_ids": [
                "1793227681583976822"
              ]
            }
          ]
        }
      ]
    }
  ],
  "unresolved": [
    "Whether agent-started pull request share keeps rising or levels off as review burden grows",
    "Whether Fusion-style model selection holds its cost and time advantage on customer workloads",
    "Whether code mode advantage for long tasks holds across models beyond the eight tested"
  ],
  "decision_card": {
    "useful_for": [
      "AI developers building agent workflows",
      "Engineering leaders setting agent tooling policy"
    ],
    "not_for": [
      "Teams comparing single models in isolation",
      "Readers looking for language popularity rankings alone"
    ],
    "compare_against": [
      "Single-model coding assistants",
      "Manual code review workflows"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-10-29T00-A"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1793211651332244430",
    "1793227403842788278",
    "1793211651331795478",
    "1793225009138867843"
  ],
  "manifests": [
    {
      "manifest_id": "1793211651332244430",
      "title": "Octoverse: Commits, pushes, reach new highs in 2026 as developers build with agents",
      "source_name": "github-old-blog",
      "source_url": "https://github.blog/news-insights/octoverse/octoverse-commits-pushes-reach-new-highs-in-2026-as-developers-build-with-agents",
      "published_date": "2026-10-28"
    },
    {
      "manifest_id": "1793227403842788278",
      "title": "Why code mode could cut your agent bill",
      "source_name": "pydantic-articles",
      "source_url": "https://pydantic.dev/articles/why-code-mode-is-the-future",
      "published_date": "2026-10-28"
    },
    {
      "manifest_id": "1793211651331795478",
      "title": "GitHub Universe 2026: Evolving every layer of the stack",
      "source_name": "github-old-blog",
      "source_url": "https://github.blog/news-insights/company-news/github-universe-2026-evolving-every-layer-of-the-stack",
      "published_date": "2026-10-28"
    },
    {
      "manifest_id": "1793225009138867843",
      "title": "Replit's Architecture Behind Secure Agent Work",
      "source_name": "replit-engineering",
      "source_url": "https://replit.com/blog/architecture-behind-secure-agent-work",
      "published_date": "2026-10-28"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1793211651332244430",
      "1793227403842788278",
      "1793211651331795478",
      "1793225009138867843"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1793211651332244430",
      "all": "for id in 1793211651332244430 1793227403842788278 1793211651331795478 1793225009138867843; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-10-29/developers-orchestrate-agent-code/",
    "json": "https://hangingcontext.com/stories/2026-10-29/developers-orchestrate-agent-code/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-10-29/developers-orchestrate-agent-code/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-10-29T00/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-10-28/harness-geometry-agent-design/",
      "headline": "The Harness Is the Product: Why Agent Design Starts Outside the Model",
      "slug": "harness-geometry-agent-design"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-28/diffusion-decoding-efficiency/",
      "headline": "Inference Is Getting Cheaper From Three Directions at Once",
      "slug": "diffusion-decoding-efficiency"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-28/cross-embodiment-world-models/",
      "headline": "One World Model, Many Robot Bodies: The New Playbook for Robot Learning",
      "slug": "cross-embodiment-world-models"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-28/agent-security-research-trust-stack/",
      "headline": "The Agent Trust Stack Gets Measurable: Injection, Leakage and Watermarks",
      "slug": "agent-security-research-trust-stack"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Run the cited Manifests yourself",
    "text": "Every claim in this paper points to a Manifest id. Get a Synorb Key and read the Manifests behind it. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons.",
    "cta": {
      "label": "Get a key",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-10-29/developers-orchestrate-agent-code/"
  }
}