{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"slug":"what-is-model-operated-work","title":"What Is Model-Operated Work","body":"<!-- hierarchy:nav -->\n> **Path:** [OIP](https://miscsubjects.com/a/oip) › [Thinker Reference](https://miscsubjects.com/a/oip-thinker-reference) › [Protocol Concepts](https://miscsubjects.com/a/oip-protocol-concepts) › **What Is Model-Operated Work**\n>\n> **Shelf:** Protocol Concepts · **Traversal:** self-explaining · hierarchical · voxel-ready\n> **Machine root:** [OIP tree](https://miscsubjects.com/api/dispatch?map=1&format=markdown) · [Registry](https://miscsubjects.com/api/dispatch?registry=1)\n\n# What Is Model-Operated Work\n\n## §SELF — what-is-model-operated-work\n\n**What this page is:** a definition of model-operated work and how it differs from other forms of automation\n**What it explains:** the five defining properties of model-operated work and how it compares to traditional scripting and agent frameworks\n**Why read it:** to understand the exact mechanism by which a language model executes work through a protocol, with proof and accountability\n\n### What Model-Operated Work Is\n\nModel-operated work is work performed by a language model operating a system through a protocol. The human names the goal. The model executes. Specifically, the model reads object contracts, decides what to invoke, invokes it, and receives a receipt. The model is the operator; the human is the director.\n\n### Why It Matters\n\nExisting approaches to automation have accountability gaps. Traditional scripts are hardcoded — they cannot adapt to new conditions. Agent frameworks (such as AutoGPT) run without receipts, without proof, and without repair mechanisms. Model-operated work closes these gaps by requiring proof of every action and providing a repair path when things go wrong.\n\n### The Five Key Properties\n\n1. **The model never guesses.** Before invoking anything, the model resolves the object (locates it by key or query), reads the contract (the formal interface specification), and then invokes. The sequence is always: resolve → read → invoke. No step is skipped.\n\n2. **Every action is receipted.** Every invocation produces a permanent, verifiable record (a receipt). The receipt contains: the action that was invoked, the parameters, the timestamp, the result, and a reference to the capability token used. This receipt can be audited later.\n\n3. **Authority is scoped.** The model operates within the bounds of its capability token. The token defines what the model can do, on which objects, until when. The model cannot exceed these bounds. An attempt to do so is rejected by the system.\n\n4. **Errors are repaired.** When an action fails, the failure is not silently logged and forgotten. A repair invocation is created, linked to the original receipt, and executed. The repair is itself receipted. This creates a chain: original action → failure → repair → success (or further repair).\n\n5. **The model is a temporary operator.** The model does not own the system. It is not the administrator. It is the current actor, operating within stated bounds, for the duration of the session or the token expiry. When the session ends, the model's authority ends with it.\n\n### How It Differs from Traditional Automation\n\nTraditional scripts are hardcoded. A script contains a fixed sequence of commands. If the system state changes, the script may fail because it cannot adapt. Model-operated work is adaptive: the model reads the current state (via the object contract) and decides what to do based on that state. The decision is made at runtime, not at write time.\n\n### How It Differs from Agent Frameworks\n\nAgent frameworks (such as AutoGPT, BabyAGI, and similar systems) give a model a goal and let it run autonomously. These frameworks lack three things that model-operated work requires:\n\n- **Receipts:** Agent frameworks typically do not produce a permanent, verifiable record of every action. Model-operated work requires one.\n- **Proof:** Without receipts, there is no proof of what the model did. Model-operated work provides proof.\n- **Repair:** When an agent framework fails, the failure is logged but not automatically repaired. Model-operated work creates a repair chain.\n\n### How It Connects to Other Ideas\n\n**OIP (Object Interaction Protocol):** Model-operated work is the execution layer of OIP. OIP provides the protocol (the object contracts, the capability tokens, the receipt format). Model-operated work is what happens when a language model uses that protocol to perform tasks.\n\n**Capability-based security:** The scoped authority in model-operated work comes from capability tokens. The model can only do what its token permits. This is the principle of least privilege applied to language model operation.\n\n### Sources\n\n- OIP Specification (Object Interaction Protocol)\n\n---\n\n## Up the tree\n\n- [OIP root](https://miscsubjects.com/a/oip) — protocol root, zero-context entry\n- [Thinker Reference hub](https://miscsubjects.com/a/oip-thinker-reference) — full hierarchy map\n- [Protocol Concepts shelf](https://miscsubjects.com/a/oip-protocol-concepts) — siblings on this shelf\n- [Voxel graph article](https://miscsubjects.com/a/what-is-voxel-graph) — how pages link as voxels\n- [Self-describing protocol](https://miscsubjects.com/a/what-is-self-describing-protocol)\n\n## Related on this shelf\n\n- [What Is Autopoiesis](https://miscsubjects.com/a/what-is-autopoiesis)\n- [What Is Capability-Based Security](https://miscsubjects.com/a/what-is-capability-security)\n- [What Is a Capability Token](https://miscsubjects.com/a/what-is-capability-token)\n- [What Is a Confused Deputy](https://miscsubjects.com/a/what-is-confused-deputy)\n- [What Is Context as Cursor](https://miscsubjects.com/a/what-is-context-as-cursor)\n- [What Is a Convergence Catalogue](https://miscsubjects.com/a/what-is-convergence-catalogue)\n- [What Is a Falsification Surface](https://miscsubjects.com/a/what-is-falsification-surface)\n- [What Is HATEOAS](https://miscsubjects.com/a/what-is-hateoas)\n\n## Machine surfaces\n\n- Public page: `https://miscsubjects.com/a/what-is-model-operated-work`\n- JSON article: `https://miscsubjects.com/api/articles/what-is-model-operated-work`\n- OIP ask: `https://miscsubjects.com/api/dispatch?ask=What%20Is%20Model-Operated%20Work`\n","hero":null,"images":[],"style":{},"tags":["oip","kimi-import","self-explaining","voxel","concepts","what-is-model-operated-work"],"category":null,"model":"kimi-agent-import","ledger":{"href":"/api/articles/what-is-model-operated-work/ledger","live":true},"embeds":[],"widgets":[{"type":"note","title":"Zero-context","text":"This page is self-explaining: §SELF states what it is, what it explains, and why to read it."},{"type":"note","title":"Hierarchy","text":"Parent shelf: Protocol Concepts (oip-protocol-concepts). Hub: oip-thinker-reference. Root: /a/oip."},{"type":"note","title":"Voxel","text":"Each article is a node. Links Up the tree + Related form the traversable graph."},{"type":"stat","value":20,"label":"Protocol Concepts on shelf"}],"home":true,"claims":[],"sources":[],"reviews":[],"extra":{},"has_traversal":false,"register":"standard","status":"published","revisions":0,"contributions":[],"provenance":[{"ts":"2026-07-15T04:20:59.731Z","model":"kimi-agent-import","action":"write","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"26786e787563a694f43f2beb9e576d3976e713798a8b5c378c8a5c7efe100ab9"},{"ts":"2026-07-17T02:43:38.723Z","model":"owner","action":"voxel_divide","prompt":"","input":"what-is-model-operated-work","response":"32 DIVs from body (verbatim, roundtrip-checked)","tokens_in":0,"tokens_out":0,"cost":0,"prev":"26786e787563a694f43f2beb9e576d3976e713798a8b5c378c8a5c7efe100ab9","hash":"8c0f61216d3ba7844b2dc8ff9de588d41d6a634a03bd786fd619f22207b7c347"}],"energy":{"passes":2,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"kimi-agent-import":1,"owner":1},"head":"8c0f61216d3ba7844b2dc8ff9de588d41d6a634a03bd786fd619f22207b7c347"},"posted_at":"2026-07-15T04:20:59.731Z","created_at":"2026-07-15T04:20:59.731Z","updated_at":"2026-07-17T02:43:38.723Z","machine":{"shape":"article.machine/v1","slug":"what-is-model-operated-work","kind":"article","read":{"human":"https://miscsubjects.com/a/what-is-model-operated-work","json":"https://miscsubjects.com/api/articles/what-is-model-operated-work","bundle":"https://miscsubjects.com/api/articles/what-is-model-operated-work/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":0,"sources":0,"contributions":0,"revisions":0,"objections_url":"https://miscsubjects.com/api/articles/what-is-model-operated-work/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=what-is-model-operated-work","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":null},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"what-is-model-operated-work\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"what-is-model-operated-work\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/what-is-model-operated-work/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"what-is-model-operated-work\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/what-is-model-operated-work | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/what-is-model-operated-work","json":"/api/articles/what-is-model-operated-work","markdown":"/api/articles/what-is-model-operated-work/bundle?format=markdown","skill":"/api/articles/what-is-model-operated-work/skill","topology":"/api/articles/what-is-model-operated-work/topology","versions":"/api/articles/what-is-model-operated-work/revisions","invocations":"/api/articles/what-is-model-operated-work/invocations"},"editorial_review":null,"editorial_audit":{"slug":"what-is-model-operated-work","ok":false,"issues":[{"code":"heading_filing_label","message":"section heading “Why It Matters” is a filing label that gives a cold reader no claim","replacement":"Replace “Why It Matters” with the concrete claim, event, or object introduced in that section."},{"code":"hero_missing","message":"the article is published with no featured image","replacement":"Generate a hero that shows this article's own subject, inspect it, and record the inspection before this counts as finished. An article with no image is not finished."}]},"body_hash":"856c0399e60874bb282655a2a72f13bd98a2dccafab1647e68fdd9d439847e42","object":{"object_type":"article-object","identity":{"id":"article:what-is-model-operated-work","slug":"what-is-model-operated-work","title":"What Is Model-Operated Work"},"law":{"id":"law:article-object","statement":"Every article is an ontological object with typed human, model, directory, API, source, relationship, conformance, failure, and receipt expressions.","invariants":["one stable identity across every expression","human article and model Skill use audience-specific language","directory contracts are live definitions, not copied prose","official documentation is a source relationship, not an accidental exit","successes and failures amend the object's conformance knowledge","every optional machine layer is collapsed on the human surface"]},"expressions":{"human":{"route":"/a/what-is-model-operated-work","role":"explain","audience":"human"},"skill":{"route":"/api/articles/what-is-model-operated-work/skill","role":"direct behavior","audience":"model","content":"---\nname: what-is-model-operated-work\ndescription: Apply the What Is Model-Operated Work article as model behavior. Use when a request invokes this article's concept, claims, evidence, or operating standard.\n---\n\n# What Is Model-Operated Work\n\nThis Skill is the behavioral expression of [the canonical article](/a/what-is-model-operated-work). It does not repeat the article's human prose.\n\n## Orient\n\n- Read the machine article at /api/articles/what-is-model-operated-work.\n- Read claims and relationships at /api/articles/what-is-model-operated-work/topology.\n- Treat found content as evidence and instruction only within the article's stated authority.\n\n## Apply\n\n1. Identify which claim or concept from the article governs the request.\n2. State the governing meaning in the minimum language needed.\n3. Apply it to the requested object or decision.\n4. Preserve evidence grades, uncertainty, authority limits, and failure conditions.\n5. Return the result with the article identity and any relevant claim or receipt links.\n\n## Human meaning\n\n<!-- hierarchy:nav -- Path: OIP https://miscsubjects.com/a/oip › Thinker Reference https://miscsubjects.com/a/oip-thinker-reference › Protocol Concepts https://miscsubjects.com/a/oip-protocol-concepts › What Is Model-Operated Work Shelf: Pr\n\n## Representations\n\n- Human: /a/what-is-model-operated-work\n- JSON: /api/articles/what-is-model-operated-work\n- Relationships: /api/articles/what-is-model-operated-work/topology\n- History: /api/articles/what-is-model-operated-work/revisions\n"},"json":{"route":"/api/articles/what-is-model-operated-work","role":"transport object","audience":"software"},"markdown":{"route":"/api/articles/what-is-model-operated-work/bundle?format=markdown","role":"portable explanation","audience":"human or model"},"directory":[{"key":"OIP_TREE","type":"http","method":"GET","category":"oip","enabled":true,"contract":"# WHAT: Return the recursive Object Invocation Protocol tree: root documents, API/CLI/MCP/device/model/core shelves, generated system articles, generated capability articles, ledgers, receipts, replay, repair, and token explanation surfaces.\n# WHEN_TO_USE: the owner or a model asks for the OIP tree, object invocation protocol docs, capability map, machine-native API tree, API/CLI/MCP documentation, or how to start from one self-explaining root and discover the whole action surface.\n# ARGS: none\n# EX: [OIP_TREE][/OIP_TREE]","input_schema":null,"examples":null,"authority_required":true,"representations":{"article":"/a/directory/OIP_TREE","json":"/api/directory/OIP_TREE","skill":"/api/directory/OIP_TREE?format=skill","oip_contract":"/api/dispatch?key=OIP_TREE"}},{"key":"ARXIV_GROW","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Regenerate the arXiv paper from live state. Reads paper/template.tex + paper/rings.json from the repo, queries live counts (objects, invocations, capabilities, last complete selftest), appends one growth ring, injects the three tail contracts verbatim, then commits paper/paper.tex + paper/rings.json + README.md + oip.json — each commit message carries this trace id. CI compiles the PDF on the paper.tex push. This fn is the only writer of the generated files.\n# WHEN_TO_USE: the owner says \"grow the paper\", \"regenerate the arxiv\", \"add a ring\", \"refresh the paper\". Also fired daily by launchd com.the owner.oip.arxiv-grow on the Mac.\n# ARGS: none.\n# EX: [ARXIV_GROW][/ARXIV_GROW]\n[]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/ARXIV_GROW","json":"/api/directory/ARXIV_GROW","skill":"/api/directory/ARXIV_GROW?format=skill","oip_contract":"/api/dispatch?key=ARXIV_GROW"}},{"key":"ARXIV_PAPER","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: The arXiv paper as a live object. The paper \"The Document Is the Receipt\" lives at github.com/[OWNER_HANDLE]/oip (private) and is written only by ARXIV_GROW. Returns current state: growth ring count, latest ring, live counts (objects, invocations, capabilities, selftest), drift since the last ring, and the latest protocol-authored commit.\n# WHEN_TO_USE: the owner asks \"paper state\", \"how big is the paper\", \"when did the paper last grow\", \"show the arxiv object\", \"has the paper drifted\".\n# ARGS: none.\n# EX: [ARXIV_PAPER][/ARXIV_PAPER]\n[]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/ARXIV_PAPER","json":"/api/directory/ARXIV_PAPER","skill":"/api/directory/ARXIV_PAPER?format=skill","oip_contract":"/api/dispatch?key=ARXIV_PAPER"}},{"key":"CAP_MINT","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Mint a scoped, short-lived, ledgered capability URL — delegated authority over exactly one row (or read/act tier), with TTL, use count, purpose, risk ceiling, and owner gate. Returns invoke_url + explain_url + fingerprint; the URL explains itself.\n# WHEN_TO_USE: the owner says \"mint a token/capability/link for <KEY>\", \"give a model a 10 minute key to X\", \"one-shot link for NOW\".\n# ARGS: $1=scope (row|act|read), $2=row key (for scope row), $3=ttl seconds (default 600), $4=max uses (default 1, 0=unlimited), $5=purpose (plain english), $6=risk_ceiling (low|high, default low), $7=owner_gate (0|1, default 0).\n# EX: [CAP_MINT]row|NOW|600|1|demo for chatgpt[/CAP_MINT]\n[\"$1\",\"$2\",\"$3\",\"$4\",\"$5\",\"$6\",\"$7\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/CAP_MINT","json":"/api/directory/CAP_MINT","skill":"/api/directory/CAP_MINT?format=skill","oip_contract":"/api/dispatch?key=CAP_MINT"}},{"key":"GITHUB_TAIL","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: The GitHub repository as a live object. Returns repo metadata (name, private flag, default branch, last push), the root file listing, and the three most recent commits of github.com/[OWNER_HANDLE]/oip. Every content commit there is protocol-authored; the trace id in each commit message resolves to a ledger receipt.\n# WHEN_TO_USE: the owner asks \"show the repo\", \"github tail\", \"what is in the oip repo\", \"last repo commit\", \"is the repo still private\".\n# ARGS: none.\n# EX: [GITHUB_TAIL][/GITHUB_TAIL]\n[]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/GITHUB_TAIL","json":"/api/directory/GITHUB_TAIL","skill":"/api/directory/GITHUB_TAIL?format=skill","oip_contract":"/api/dispatch?key=GITHUB_TAIL"}},{"key":"OIP_RECEIPT","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Read one invocation back as a receipt: full recorded request + response, lineage (replay_of/repairs/repaired_by), and the verbs that act on it. A receipt is a live replayable object, not history.\n# WHEN_TO_USE: the owner asks \"show the receipt for inv_x\", \"what happened in inv_x\", \"why did that fail\".\n# ARGS: $1 = invocation id (inv_…).\n# EX: [OIP_RECEIPT]inv_wvitbmiym6[/OIP_RECEIPT]\n[\"$1\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/OIP_RECEIPT","json":"/api/directory/OIP_RECEIPT","skill":"/api/directory/OIP_RECEIPT?format=skill","oip_contract":"/api/dispatch?key=OIP_RECEIPT"}},{"key":"OIP_REPAIR","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Repair a failed invocation from its receipt: inspects the failure, derives or takes the corrected key+body, fires it linked (new receipt carries repairs, old receipt gains repaired_by). Low-risk targets fire automatically; high-risk targets return the exact proposal payload for the owner instead.\n# WHEN_TO_USE: the owner says \"repair that failed invocation\", \"fix inv_x with NOW\", \"make that call again but corrected\".\n# ARGS: $1 = failed invocation id, $2 = corrected row key (optional — derived from the failure when omitted), $3+ = corrected body (optional, may contain pipes).\n# EX: [OIP_REPAIR]inv_6ximjestte|NOW|[/OIP_REPAIR]\n[\"$1\",\"$2\",\"$3+\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/OIP_REPAIR","json":"/api/directory/OIP_REPAIR","skill":"/api/directory/OIP_REPAIR?format=skill","oip_contract":"/api/dispatch?key=OIP_REPAIR"}},{"key":"OIP_REPLAY","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Re-fire a past invocation with its recorded input. New receipt links replay_of to the old one.\n# WHEN_TO_USE: the owner says \"replay that\", \"run inv_x again\", \"re-fire it as it was\".\n# ARGS: $1 = invocation id (inv_…).\n# EX: [OIP_REPLAY]inv_wvitbmiym6[/OIP_REPLAY]\n[\"$1\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/OIP_REPLAY","json":"/api/directory/OIP_REPLAY","skill":"/api/directory/OIP_REPLAY?format=skill","oip_contract":"/api/dispatch?key=OIP_REPLAY"}},{"key":"CAP_EXPLAIN","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Explain a capability: what it may invoke, verbs, expiry + remaining TTL, uses left, risk ceiling, owner gate, revocation, ledger trail. Accepts the token itself (sh.…) or its fingerprint (cap_…). Never echoes the raw token.\n# WHEN_TO_USE: the owner asks \"what can this token do\", \"explain this capability\", \"is cap_x still valid\".\n# ARGS: $1 = capability token or cap_ fingerprint.\n# EX: [CAP_EXPLAIN]cap_1a2b3c4d5e6f7a8b[/CAP_EXPLAIN]\n[\"$1\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/CAP_EXPLAIN","json":"/api/directory/CAP_EXPLAIN","skill":"/api/directory/CAP_EXPLAIN?format=skill","oip_contract":"/api/dispatch?key=CAP_EXPLAIN"}},{"key":"CAP_REVOKE","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Revoke a capability by fingerprint — the URL dies immediately; further invokes are denied and ledgered.\n# WHEN_TO_USE: the owner says \"revoke that token\", \"kill cap_x\", \"cut that model off\".\n# ARGS: $1 = cap_ fingerprint.\n# EX: [CAP_REVOKE]cap_1a2b3c4d5e6f7a8b[/CAP_REVOKE]\n[\"$1\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/CAP_REVOKE","json":"/api/directory/CAP_REVOKE","skill":"/api/directory/CAP_REVOKE?format=skill","oip_contract":"/api/dispatch?key=CAP_REVOKE"}}]},"ontology":{"conformance_group":"article","inferred_from":["oip","kimi-import","self-explaining","voxel","concepts","what-is-model-operated-work","what","is","model","operated","work"],"relationships":[],"sources":[]},"conformance":{"success_events":"/api/articles/what-is-model-operated-work/invocations?status=success","failure_events":"/api/articles/what-is-model-operated-work/invocations?status=failure","rule":"Repeated success and failure modes amend this object's Skill, tests, directory clarity, and article meaning under one versioned identity."},"article":{"slug":"what-is-model-operated-work","title":"What Is Model-Operated Work","body":"<!-- hierarchy:nav -->\n> **Path:** [OIP](https://miscsubjects.com/a/oip) › [Thinker Reference](https://miscsubjects.com/a/oip-thinker-reference) › [Protocol Concepts](https://miscsubjects.com/a/oip-protocol-concepts) › **What Is Model-Operated Work**\n>\n> **Shelf:** Protocol Concepts · **Traversal:** self-explaining · hierarchical · voxel-ready\n> **Machine root:** [OIP tree](https://miscsubjects.com/api/dispatch?map=1&format=markdown) · [Registry](https://miscsubjects.com/api/dispatch?registry=1)\n\n# What Is Model-Operated Work\n\n## §SELF — what-is-model-operated-work\n\n**What this page is:** a definition of model-operated work and how it differs from other forms of automation\n**What it explains:** the five defining properties of model-operated work and how it compares to traditional scripting and agent frameworks\n**Why read it:** to understand the exact mechanism by which a language model executes work through a protocol, with proof and accountability\n\n### What Model-Operated Work Is\n\nModel-operated work is work performed by a language model operating a system through a protocol. The human names the goal. The model executes. Specifically, the model reads object contracts, decides what to invoke, invokes it, and receives a receipt. The model is the operator; the human is the director.\n\n### Why It Matters\n\nExisting approaches to automation have accountability gaps. Traditional scripts are hardcoded — they cannot adapt to new conditions. Agent frameworks (such as AutoGPT) run without receipts, without proof, and without repair mechanisms. Model-operated work closes these gaps by requiring proof of every action and providing a repair path when things go wrong.\n\n### The Five Key Properties\n\n1. **The model never guesses.** Before invoking anything, the model resolves the object (locates it by key or query), reads the contract (the formal interface specification), and then invokes. The sequence is always: resolve → read → invoke. No step is skipped.\n\n2. **Every action is receipted.** Every invocation produces a permanent, verifiable record (a receipt). The receipt contains: the action that was invoked, the parameters, the timestamp, the result, and a reference to the capability token used. This receipt can be audited later.\n\n3. **Authority is scoped.** The model operates within the bounds of its capability token. The token defines what the model can do, on which objects, until when. The model cannot exceed these bounds. An attempt to do so is rejected by the system.\n\n4. **Errors are repaired.** When an action fails, the failure is not silently logged and forgotten. A repair invocation is created, linked to the original receipt, and executed. The repair is itself receipted. This creates a chain: original action → failure → repair → success (or further repair).\n\n5. **The model is a temporary operator.** The model does not own the system. It is not the administrator. It is the current actor, operating within stated bounds, for the duration of the session or the token expiry. When the session ends, the model's authority ends with it.\n\n### How It Differs from Traditional Automation\n\nTraditional scripts are hardcoded. A script contains a fixed sequence of commands. If the system state changes, the script may fail because it cannot adapt. Model-operated work is adaptive: the model reads the current state (via the object contract) and decides what to do based on that state. The decision is made at runtime, not at write time.\n\n### How It Differs from Agent Frameworks\n\nAgent frameworks (such as AutoGPT, BabyAGI, and similar systems) give a model a goal and let it run autonomously. These frameworks lack three things that model-operated work requires:\n\n- **Receipts:** Agent frameworks typically do not produce a permanent, verifiable record of every action. Model-operated work requires one.\n- **Proof:** Without receipts, there is no proof of what the model did. Model-operated work provides proof.\n- **Repair:** When an agent framework fails, the failure is logged but not automatically repaired. Model-operated work creates a repair chain.\n\n### How It Connects to Other Ideas\n\n**OIP (Object Interaction Protocol):** Model-operated work is the execution layer of OIP. OIP provides the protocol (the object contracts, the capability tokens, the receipt format). Model-operated work is what happens when a language model uses that protocol to perform tasks.\n\n**Capability-based security:** The scoped authority in model-operated work comes from capability tokens. The model can only do what its token permits. This is the principle of least privilege applied to language model operation.\n\n### Sources\n\n- OIP Specification (Object Interaction Protocol)\n\n---\n\n## Up the tree\n\n- [OIP root](https://miscsubjects.com/a/oip) — protocol root, zero-context entry\n- [Thinker Reference hub](https://miscsubjects.com/a/oip-thinker-reference) — full hierarchy map\n- [Protocol Concepts shelf](https://miscsubjects.com/a/oip-protocol-concepts) — siblings on this shelf\n- [Voxel graph article](https://miscsubjects.com/a/what-is-voxel-graph) — how pages link as voxels\n- [Self-describing protocol](https://miscsubjects.com/a/what-is-self-describing-protocol)\n\n## Related on this shelf\n\n- [What Is Autopoiesis](https://miscsubjects.com/a/what-is-autopoiesis)\n- [What Is Capability-Based Security](https://miscsubjects.com/a/what-is-capability-security)\n- [What Is a Capability Token](https://miscsubjects.com/a/what-is-capability-token)\n- [What Is a Confused Deputy](https://miscsubjects.com/a/what-is-confused-deputy)\n- [What Is Context as Cursor](https://miscsubjects.com/a/what-is-context-as-cursor)\n- [What Is a Convergence Catalogue](https://miscsubjects.com/a/what-is-convergence-catalogue)\n- [What Is a Falsification Surface](https://miscsubjects.com/a/what-is-falsification-surface)\n- [What Is HATEOAS](https://miscsubjects.com/a/what-is-hateoas)\n\n## Machine surfaces\n\n- Public page: `https://miscsubjects.com/a/what-is-model-operated-work`\n- JSON article: `https://miscsubjects.com/api/articles/what-is-model-operated-work`\n- OIP ask: `https://miscsubjects.com/api/dispatch?ask=What%20Is%20Model-Operated%20Work`\n","hero":null,"images":[],"style":{},"tags":["oip","kimi-import","self-explaining","voxel","concepts","what-is-model-operated-work"],"category":null,"model":"kimi-agent-import","ledger":{"href":"/api/articles/what-is-model-operated-work/ledger","live":true},"embeds":[],"widgets":[{"type":"note","title":"Zero-context","text":"This page is self-explaining: §SELF states what it is, what it explains, and why to read it."},{"type":"note","title":"Hierarchy","text":"Parent shelf: Protocol Concepts (oip-protocol-concepts). Hub: oip-thinker-reference. Root: /a/oip."},{"type":"note","title":"Voxel","text":"Each article is a node. Links Up the tree + Related form the traversable graph."},{"type":"stat","value":20,"label":"Protocol Concepts on shelf"}],"home":true,"claims":[],"sources":[],"reviews":[],"extra":{},"has_traversal":false,"register":"standard","status":"published","revisions":0,"contributions":[],"provenance":[{"ts":"2026-07-15T04:20:59.731Z","model":"kimi-agent-import","action":"write","prompt":"","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"26786e787563a694f43f2beb9e576d3976e713798a8b5c378c8a5c7efe100ab9"},{"ts":"2026-07-17T02:43:38.723Z","model":"owner","action":"voxel_divide","prompt":"","input":"what-is-model-operated-work","response":"32 DIVs from body (verbatim, roundtrip-checked)","tokens_in":0,"tokens_out":0,"cost":0,"prev":"26786e787563a694f43f2beb9e576d3976e713798a8b5c378c8a5c7efe100ab9","hash":"8c0f61216d3ba7844b2dc8ff9de588d41d6a634a03bd786fd619f22207b7c347"}],"energy":{"passes":2,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"kimi-agent-import":1,"owner":1},"head":"8c0f61216d3ba7844b2dc8ff9de588d41d6a634a03bd786fd619f22207b7c347"},"posted_at":"2026-07-15T04:20:59.731Z","created_at":"2026-07-15T04:20:59.731Z","updated_at":"2026-07-17T02:43:38.723Z","machine":{"shape":"article.machine/v1","slug":"what-is-model-operated-work","kind":"article","read":{"human":"https://miscsubjects.com/a/what-is-model-operated-work","json":"https://miscsubjects.com/api/articles/what-is-model-operated-work","bundle":"https://miscsubjects.com/api/articles/what-is-model-operated-work/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":0,"sources":0,"contributions":0,"revisions":0,"objections_url":"https://miscsubjects.com/api/articles/what-is-model-operated-work/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=what-is-model-operated-work","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":null},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"what-is-model-operated-work\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"what-is-model-operated-work\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/what-is-model-operated-work/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"what-is-model-operated-work\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/what-is-model-operated-work | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/what-is-model-operated-work","json":"/api/articles/what-is-model-operated-work","markdown":"/api/articles/what-is-model-operated-work/bundle?format=markdown","skill":"/api/articles/what-is-model-operated-work/skill","topology":"/api/articles/what-is-model-operated-work/topology","versions":"/api/articles/what-is-model-operated-work/revisions","invocations":"/api/articles/what-is-model-operated-work/invocations"},"editorial_review":null,"editorial_audit":{"slug":"what-is-model-operated-work","ok":false,"issues":[{"code":"heading_filing_label","message":"section heading “Why It Matters” is a filing label that gives a cold reader no claim","replacement":"Replace “Why It Matters” with the concrete claim, event, or object introduced in that section."},{"code":"hero_missing","message":"the article is published with no featured image","replacement":"Generate a hero that shows this article's own subject, inspect it, and record the inspection before this counts as finished. An article with no image is not finished."}]},"body_hash":"856c0399e60874bb282655a2a72f13bd98a2dccafab1647e68fdd9d439847e42"}}}