# How Super Chain Works: Connect, Ask, Approve, Repeat > How Super Chain works in five steps: connect tools, ask in plain English, review prepared work, approve actions before they run, and repeat with Skills. Source: https://www.super-chain.tech/how-super-chain-works Last modified: 2026-11-05 how super chain works # How Super Chain works, in five steps. Super Chain works in five steps. You connect the firm’s tools, such as Microsoft 365 or ClickUp, and load its documents. You ask a question in plain English. It prepares the work, showing each step and citing sources. You approve any action set to need approval. A saved Skill lets the team repeat it. connect · ask · it prepares · you approve · it repeats Written by [Cat Yung](https://www.super-cat.tech/cat-yung), Founder, Super Chain. Last updated 5 November 2026. the five steps ## What are the five steps, *end to end?* Connect, Ask, It prepares, You approve, It repeats. The firm sets the rules once; after that, each request follows the same path, and a person stays in charge of anything that changes a record outside Super Chain. The demo uses invented companies and people. Every screen in it is copied from the product. ****** app.super-chain.tech / connectors AK ### Connectors Connect the apps your workspace uses, so the assistant can work in them as you. Yours (2) Discover (1) C #### ClickUp Not connected Work the org's ClickUp workspace from chat: read tasks, owners and due dates, and create, update or comment on a task. Connect #### Tool permissions Choose when the assistant may use each tool for you. "Needs approval" asks you in the chat first. Mine Workspace ##### Read-only tools 4 Always allow - Search - Filter tasks - Get task - Get task comments ##### Write/delete tools 3 Always allow - Create task - Update task - Create comment step 1 · connect ## What does it mean to *connect a tool?* A connector links Super Chain to a system the firm already uses, such as Microsoft 365, ClickUp or HubSpot. Each person connects their own account where the vendor allows it, so the agent acts with that person’s access, not a shared admin login. Then each tool inside a connector gets one of three settings: - Always allow.** The agent may use it without asking. Fine for reading, such as searching tasks. - Needs approval.** The agent must stop and ask in the chat first. The usual choice for anything that writes or sends. - Never allow.** The agent cannot use it at all, whatever anyone types. step 1 · who may use what ## Who decides *which tools each person gets?* The firm’s admin. For each connector, the admin can give a person, a group or a role Read only, Read and write, a hand-picked set of tools, or no access. A tool someone may not use is not offered to the agent for them at all. A person can tighten their own settings further, but never loosen past the workspace rule. Documents follow the same idea: each folder is shared at a level, and the agent only searches what the person asking may read. For the full access model, read [AI access control for financial firms](https://www.super-chain.tech/ai-access-control-for-financial-firms). step 2 · ask ## What happens *when someone asks a question?* They type it in plain English, as they would to a colleague: “Which of our loan documents mention a change-of-control clause?” or “Draft a task for each overdue review.” Files can be attached to the message. Next to the chat box sits a choice of Ask or Auto. Ask, the default, means every tool set to Needs approval waits for a click. Auto lets those tools run without the wait for that conversation. Neither mode can switch on a tool set to Never allow. Before any model runs, the message is screened for attempts to trick the agent. A message that looks like one is refused and recorded. step 3 · it prepares ## How does Super Chain *prepare the work?* It narrates as it goes. The chat shows each step in plain words, such as “Searched documents” or “Looked up assets”, with what each step found. For a larger job it hands parts to specialist subagents that work in parallel, each shown as its own card. Answers cite the firm’s own documents, so a reviewer can open the source page. When figures come from a connected data source that supports it, Super Chain checks each figure in the answer against the stored results and removes any it cannot support. Word, Excel and PowerPoint files it creates stay in the chat until a person saves them to the vault. When it edits a Word document, it keeps the earlier version and stores a redline of what changed. step 4 · you approve ## How does the agent *get approval before it acts?* When it reaches a tool set to Needs approval, it stops. The chat shows what it wants to do and the details it would send, with two buttons: Deny and Approve. Nothing runs until the person decides. A second check sits behind the button. Before a tool that writes to another system runs, an independent check asks whether the action is destructive, whether it matches what the person asked for, and whether it reaches for secrets. If the answer is doubtful, the call is refused. Every decision, allowed or refused, is written to an activity log the firm holds, with the conversation it came from. step 5 · it repeats ## How does a good workflow *become repeatable?* It is saved as a Skill: a short written workflow, in plain steps, that the agent follows with the tools the person already has. A Skill holds instructions only; it carries no code of its own. Anyone with access types / in the chat box, picks the Skill and runs it again. The same permissions and approvals apply every run. Skills do not run on a timer: a person starts each one. where it runs ## Where does *all of this run?* On infrastructure the firm controls: its own servers or its private cloud, isolated from other organisations. The [trust and security page](https://www.super-chain.tech/trust) sets out the architecture, and the [on-premise AI appliance](https://www.super-chain.tech/on-premise-ai-appliance-for-financial-institutions) page covers running it on the firm’s own hardware. who it is for ## Who this is for, *and who it isn’t.* This guide is for CIOs and COOs at investment and wealth firms, family offices and brokers in Hong Kong, the UK and worldwide, who want AI to do real work across their tools without losing sight of who approved what. It is not a technical integration manual. Single sign-on, network design and model choice are agreed with each firm during deployment. delivery ## How Super Chain is put in place, *and who does what.* - i **Plan.** A 30-minute call sets the plan: one owner, the first workflow, and where Super Chain will run: the office’s private cloud or its own servers. - ii **Deploy.** Our team installs Super Chain on that infrastructure and configures roles, document permissions and the model the office chooses. - iii **Load and check.** The office loads that vehicle’s documents, not a tidied sample. We review the first answers with the owner against the cited pages. - iv **Use.** The team asks real questions of its own documents. Every query is recorded in an audit log the office holds. Super Chain is accountable for the platform and its configuration. The office remains accountable for which documents go in, who may see them, and the terms of the model provider it chooses. // what can go wrong - Connector settings are too loose at first.** Any tool that writes can be set to Needs approval from day one, and loosened only when the firm decides. - A vendor limits what its connector can do.** We say which tools are available before the pilot starts, not after. - Staff skip the approval step by switching to Auto.** Auto never overrides Never allow or the workspace rules, and every auto-run is logged. - A Skill drifts from how the team works.** Skills are plain text the team can read and edit, and each run is visible step by step. // track record Super Chain is built by Super Cat Technology. The same team built a [fully on-premise retrieval system for a Big 4 firm](https://www.super-cat.tech/portfolio/enterprise-rag-big-4), where every answer returns with its source paragraph. read next ## Related *reading.* Your AI plan in 30 minutes → A free call to set the first workflow, the access rules and where it runs. AI access control for financial firms → Who may see which documents and use which tools, and how that is enforced. Trust and security → Where Super Chain runs, how tenants are isolated, and what is logged. On-premise AI appliance → Running Super Chain on the firm’s own hardware. AI document intelligence for family offices → Answers cited to the page, across a family office’s documents. questions ## The questions offices ask, *plainly answered.* ### How does Super Chain work? In five steps. The firm connects its tools and loads its documents. A person asks a question in plain English. Super Chain prepares the work and shows each step. The person approves any action that needs approval. A proven workflow is saved as a Skill and run again from the / menu. ### How does private AI work in a financial firm? The model, the documents, the prompts and the audit log run on infrastructure the firm controls, isolated from other organisations. Staff use it like any chat assistant, but it answers from the firm’s own files, only shows each person what they may see, and records every action for review. ### How does an AI agent get approval before it acts? Each connector tool is set to Always allow, Needs approval or Never allow. When the agent wants a tool set to Needs approval, the chat shows what it plans to do and waits. The person clicks Approve or Deny. Nothing set to Never allow runs, in any mode. ### What is the difference between Ask and Auto mode? Ask is the default. In Ask mode, every tool set to Needs approval waits for a click. In Auto mode, those tools run without the wait. Auto never widens access: tools set to Never allow, the workspace rules and who may use a connector are all decided first. ### Can Super Chain run a workflow on a schedule? No. A Skill is a written workflow, not a timer. A person starts each run from the / menu in the chat box, and the same permissions and approvals apply every time. That keeps a named person behind every action the agent takes on the firm’s behalf. To see the five steps on your own documents and tools, on infrastructure you control, Book your 30-minute AI implementation plan → // the next step ## Your AI implementation plan, in 30 minutes A 30-minute call with our team. We look at where your firm uses AI today, which documents and systems it would touch, and where it should run. You leave with a plan: what to start with, what to keep out, and which deployment fits. It is free. Choose a time below. If you would rather see the platform first, [book a private demonstration](https://calendly.com/super-chain/catyung?utm_source=super-chain.tech&utm_campaign=private-demonstration&utm_content=how-super-chain-works). [Open the scheduler →](https://calendly.com/super-chain/catyung?utm_source=super-chain.tech&utm_campaign=ai-implementation-plan&utm_content=how-super-chain-works)