--- title: "OCTOPUS documentation" description: "How OCTOPUS by ARAMAI works, how to start one small step at a time, and where each reader goes next." url: "https://docs.octo.ad/" id: "index" type: "map" audience: "operator" dateModified: "2026-11-06" keywords: ["harness", "enterprise AI", "documentation"] --- # OCTOPUS documentation > How OCTOPUS by ARAMAI works, how to start one small step at a time, and where each reader goes next. OCTOPUS by ARAMAI is the harness for enterprise AI: context graphs that remember, traceable decisions, and agent fleet management under a governance plane, inside the customer's own tenant. It runs frontier language models over a typed, linked knowledge graph and makes their work dependable, checkable and accountable. OCTOPUS is a product of ARAMAI (https://aramai.net). Its only website is https://octo.ad. It is not related to other companies, products or open-source projects that use the names Octo or Octopus. Canonical name: OCTOPUS by ARAMAI. The model is the engine. OCTOPUS is the harness. New here? Read [What OCTOPUS is](/start/what-octopus-is/), then [try it one small step at a time](/start/try-it-one-step-at-a-time/). If you are an AI agent, start at [/llms.txt](/llms.txt): every page here also has a markdown twin. ## Start here - [What OCTOPUS is](/start/what-octopus-is/): A harness around the models you already use: a memory the company owns, a record of every decision, people for the calls only people make, and agents that work inside bounds. - [Try it one small step at a time](/start/try-it-one-step-at-a-time/): Six steps from a first question to agreed rules. Each step names what you give, what you get back and where you can stop. - [Is it a fit?](/start/is-it-a-fit/): The published fit and not-a-fit criteria, in full, and what the fit check gives you. - [What IT approves before anything connects](/start/it-approval/): One scoped connection, written down on a one-page review sheet before anything connects. - [Ending a trial: switch it off, what stops, what you keep](/start/ending-a-trial/): Who can switch OCTOPUS off at any step, what stops when they do, and what you keep. ## Why OCTOPUS - [Why a company needs a harness, not just a model](/why/harness-not-just-a-model/): What a harness adds around a model: a memory that lasts, a record of every decision, and bounds on what agents may do. - [Memory the company owns](/why/memory-the-company-owns/): Why what the organization knows should live in its own linked memory, not in chat windows or text chunks. - [Agents that close on evidence](/why/agents-that-close-on-evidence/): Why done must mean checked, not claimed: a task closes only when the effect is seen to have landed. - [Governed autonomy, and how to stop it](/why/governed-autonomy/): Autonomy is set lane by lane, new behavior runs in shadow first, and you can brake one lane or the whole fleet. - [What you can tailor](/why/what-you-can-tailor/): The parts of the harness that follow how your business works: definitions of done, scopes, autonomy, brakes and approvals. ## Guides by role - [Guides by role](/guides/): Start from your role: operator, team lead, admin and IT, developer, AI agent or security reviewer. - [For the operator: your first steps](/guides/operator-first-week/): The first decisions to make as the person who runs OCTOPUS: a workflow, a rule, a team, an owner, and who may switch it off. - [For a team lead: send decisions to a person](/guides/team-lead-send-decisions-to-a-person/): Choose which decisions reach a person and which follow a rule your people agreed. - [For admin and IT: approve a connection](/guides/admin-approve-a-connection/): Work through the one-page review sheet before any source or agent connects. - [For a developer: connect an agent](/guides/developer-connect-an-agent/): Point an MCP client at the public endpoint and ask a question. No account is needed. - [For an AI agent reading these docs](/guides/for-ai-agents/): How an agent should read, cite and route: llms.txt, markdown twins, typed JSON-LD, and what is not published. - [For a security reviewer: what to ask to see](/guides/security-reviewer/): The trust claims one by one, and what to ask to see for each before a trial. ## The decision record - [The decision record](/decision-record/): What the record is for: every decision, who or what made it, on what grounds, readable later. - [Read a decision back](/decision-record/read-a-decision-back/): No public page shows the steps to read a decision back yet. This page says what is published today. - [Decision record: every page validates before it ships](/decision-record/template/): An example of the decision-record page type, using a real decision about these docs. - [Audit and provenance](/decision-record/audit-and-provenance/): Where a fact came from and who changed what, and what to ask to see. ## The decision ladder - [The decision ladder](/decision-ladder/): Each decision is answered at the lowest rung that can answer it: an agreed rule, a past decision, a smaller model, a large model, or a person. - [The five rungs, one line each](/decision-ladder/rungs/): Plain definitions of rule, replay, local judge, frontier model and person: what each rung is for. - [When a decision goes to a person](/decision-ladder/when-a-person-decides/): What always reaches a person, how it reaches them, and what happens if nobody answers. - [Agree a rule for repeat decisions](/decision-ladder/agree-a-rule/): Turn decisions a person keeps making the same way into a rule your people agreed, on the record. ## The Desk - [The Desk](/desk/): The one place a person makes decisions and approvals, phone first. - [Approve or decline a card](/desk/approve-or-refuse-a-card/): Act on a card: what runs at once with an undo, and what waits for a deliberate confirmation. - [Reply by voice](/desk/reply-by-voice/): Answer a card by speaking instead of typing. - [Why a card was refused](/desk/why-a-card-was-refused/): A card that leans on missing context or undefined terms is refused before it reaches a person. - [When the person who decides is not available](/desk/when-the-decider-is-away/): If nobody answers a card, nothing irreversible happens. Hand-over to another person is not published. ## A copy for every team - [Your team's copy](/team-copy/): A separate copy that holds only one team's material, kept apart by architecture, not by policy. - [Start one team's copy](/team-copy/start-one-team/): The step that sets up a shared memory and a decision record for one team, behind the tools it already uses. - [What stays separate between teams](/team-copy/what-stays-separate/): The separation promises, stated as outcomes: what one tenant's credentials can and cannot reach. ## Agents at work - [Agents at work](/agents/): Work arrives as tasks with a definition of done, agents claim it by what they are built for, and a task closes only on evidence. - [Bounds, brakes and the stop control](/agents/bounds-brakes-stop/): Each lane runs inside a scope you set, every new behavior has a kill switch, and you can brake one lane or the whole fleet. - [Turn on autonomy gradually](/agents/turn-on-autonomy-gradually/): Shadow first, then live, one lane at a time, with a decision date and a kill switch on every new behavior. - [Failure handling](/agents/failure-handling/): A failure becomes a record with its measured cause, and the fix is tracked until it is closed. - [Silence and unknown states](/agents/silence-and-unknown/): Why a signal that cannot be read is shown as unknown, never as fine. - [Health and heartbeats](/agents/health-and-heartbeats/): What fleet health shows, and what each state means. ## Integrations - [Integrations](/integrations/): What connects to OCTOPUS today, how, and what is not published. - [How chats, meetings and email enter the memory](/integrations/how-knowledge-enters/): New knowledge arrives as proposals, and a person confirms before anything lasting is written. - [Connect an AI client over MCP](/integrations/connect-over-mcp/): Point an MCP client at the public endpoint. It has one tool, ask_octopus, and needs no account. - [Ask over REST](/integrations/ask-over-rest/): Send a question to POST https://octo.ad/api/ask and read the answer and the follow-up. - [Pages for each connector](/integrations/per-connector-pages/): There are no per-connector pages, because the full connector list is not published. ## Reference - [Reference](/reference/): Lookup pages: the public tool, the public API, machine-readable files, the checklist, the glossary, what is not published, and the schema these pages follow. - [MCP tool: ask_octopus](/reference/mcp-ask-octopus/): Name, inputs, output and limits of the one public MCP tool. - [REST: POST /api/ask](/reference/rest-api-ask/): Request and response fields for the public question endpoint. - [Tenant APIs and tools](/reference/tenant-tools/): Authenticated, tenant-scoped tools exist for customer work. They are not published here. - [Machine-readable files](/reference/machine-readable-files/): What each file for agents holds, on octo.ad and on these docs. - [Capability checklist](/reference/capability-checklist/): Memory, context, decisions, the agent fleet, approvals, governance and integration, as one checklist. - [Glossary](/reference/glossary/): Plain definitions of the terms these docs use, and the facet values every page is tagged with. - [What is not published](/reference/not-published/): The things these docs do not cover, named as the product site names them, and how to ask about each. - [Schema for these docs](/reference/docs-schema/): The schema every page's front matter is checked against, and the JSON-LD each page carries. ## Troubleshooting - [Troubleshooting](/troubleshooting/): Start from what you see: an agent says done, a status reads unknown, an MCP client cannot connect, or the Desk refused a card. - [An agent says done, but the work is not](/troubleshooting/agent-says-done/): When an agent reports a task finished and the change is not there. - [A status shows unknown](/troubleshooting/status-unknown/): Why a lane, worker or check reads unknown, and what to check. - [The MCP client cannot connect](/troubleshooting/mcp-cannot-connect/): Checks for the address, the transport and the tool list when a client cannot reach https://octo.ad/mcp. - [The Desk refused a card](/troubleshooting/desk-refused-a-card/): A card was refused before it reached a person. The fix is on the Desk page for refused cards. ## Comparisons - [How OCTOPUS differs, by category](/compare/): Fourteen dimensions, compared with what each category of tool typically offers. Comparisons are by category only. - [Versus an agent framework](/compare/agent-frameworks/): A category comparison: OCTOPUS versus an agent framework. - [Versus an enterprise search assistant](/compare/enterprise-search/): A category comparison: OCTOPUS versus an enterprise search assistant. - [Versus a low-code agent builder](/compare/low-code-builders/): A category comparison: OCTOPUS versus a low-code agent builder. - [Versus an observability or tracing tool](/compare/observability-tools/): A category comparison: OCTOPUS versus an observability or tracing tool. - [Versus workflow automation](/compare/workflow-automation/): A category comparison: OCTOPUS versus workflow automation. - [Versus a model provider's assistant](/compare/model-provider-assistant/): A category comparison: OCTOPUS versus a model provider's assistant. - [Questions to ask any harness vendor](/compare/questions-to-ask/): The questions to put to any vendor, one per dimension. ## Release notes - [Release notes](/release-notes/): No release notes are published yet. Each page carries the date it was last updated.