01What this guide helps you do
Build domain context around real services and boundaries.
This guide focuses on one task within chatbot knowledge. Its completion test is specific: The assistant has useful sector context without unsupported expertise claims. Use that result to decide whether the task is finished. Opening a page, entering a value or seeing a brief notification can be part of the process without establishing the complete result.
02When to use this workflow
Use this workflow when your immediate goal is to prepare knowledge for a new industry. Keep the scope limited to the relevant knowledge revision. If you are solving a different problem, use the related guides at the end rather than applying every action here to unrelated records.
The usual operational owner is the business knowledge owner. If another person owns the relevant business facts or permissions, involve that person before changing the shared record. Individual access and business authority are not always the same thing.
03Prepare the information you need
Start from approved business facts rather than a large unreviewed document. Give each block a clear subject, such as products, pricing, services or policies, and identify who can approve changes. Keep customer-facing knowledge separate from private operational notes. Include useful limitations and escalation routes so the assistant can respond honestly when the source does not support a requested promise.
Industry, products, common requests.
04Find the right workspace and feature
Start from Chatbot builder → Business Intel. Treat this as a feature locator: the arrangement of menus can differ between the web interface and the native application. Confirm the workspace name and the relevant record before proceeding, especially if you manage more than one business or use both India and UK accounts.
The target of this task is a knowledge revision. Keep its identity visible while you work. A similarly named record or a previously open browser tab can otherwise make a correct action affect the wrong context.
05Understand the information on screen
| Information | What it means | Practical check |
|---|---|---|
| Identity | Business and intended audience | Use accurate current context |
| Knowledge block | A focused set of business facts | Choose a clear subject and owner |
| Personality | Response language and tone | Test serious as well as routine cases |
| Publication state | Draft, saved or live revision | Confirm the explicit state |
Apply these distinctions to the specific inputs for this guide: industry, products, common requests. You do not need to collect every possible field in the workspace. Use the information needed to make this decision and to verify its result.
06Inspect the current state first
Read related blocks together and look for contradictory prices, dates, names and service boundaries. Business identity, knowledge blocks and personality settings serve different purposes. A friendly tone cannot correct an inaccurate fact. Distinguish evergreen information from seasonal offers and case-specific quotations. A historical customer document should not automatically become a general answer for every future customer.
If the intended result is already present, check whether any further action is necessary. This is particularly useful after an interrupted session or when another teammate may have completed part of the work.
07Step 1: Start with verified business facts
Begin with the relevant inputs: industry, products, common requests. Resolve any ambiguity that would change which record or business decision the task concerns. Keep a short note of the original state if you will need to compare it later. This creates a clear starting point for the next action instead of relying on memory after several screens have changed.
08Step 2: List tasks the assistant may handle
Use the result of the first action as the context for this one. Check the exact label, selected value or evidence involved rather than assuming that a default matches the intended task. If you identify an inconsistency, resolve it before proceeding. Keep the change narrow enough that its effect can be understood without comparing many unrelated edits.
09Step 3: Define tasks requiring staff judgment
Finish by checking the observable result, not only whether the interface accepted an interaction. If the result is still pending or cannot be verified, preserve that distinction in your notes. A clearly recorded unresolved state is more useful than announcing completion and discovering the missing part during a live customer task. Use the verification guidance below for the relevant feature.
10Worked example
A logistics company provides shipment enquiry guidance while routing claims to staff.
The useful lesson is the sequence of decisions, not a promised result for every business. In this scenario, begin with “Start with verified business facts”, continue with “List tasks the assistant may handle”, and finish with “Define tasks requiring staff judgment”. Compare the result with the completion test before applying the same process to a wider set of records.
Use invented names and references when practising this example. Keep the structure realistic, but do not copy a live customer conversation or payment record into training material simply to make the demonstration look authentic.
11Verify the result
Test representative questions against the saved knowledge before publishing. Include a straightforward question, a follow-up, an exception and a fact that is not supplied. Compare material claims with the approved source. Then use the explicit publication step when the update is ready. Saving, previewing and publishing are separate actions, so verify the state the interface actually reports.
The assistant has useful sector context without unsupported expertise claims.
12Decide what to do next
| What you observe | Appropriate next step | What to avoid |
|---|---|---|
| The expected result is visibly present. | Keep the result and continue with the intended business task. | Repeating a completed action without a reason. |
| The result is still pending or uncertain. | Review the current knowledge revision and the relevant status. | Calling the task complete without evidence. |
| The result conflicts with the intended choice. | Revisit: List tasks the assistant may handle. | Changing unrelated records to hide the symptom. |
Use the observed state to choose a branch. A recovery action should address the actual cause and preserve any work that is already correct. If several people are involved, make the next owner explicit so a pending state does not become an unattended task.
13The main mistake to avoid
An industry label alone does not make an assistant qualified to advise on regulated decisions.
This mistake can make the task appear finished while leaving the business outcome unresolved. Return to the inputs and the named steps when the result is unclear. Keep a useful distinction between what you observed and what you expected. If a weaker signal is all that is available, describe the remaining uncertainty and identify how it can be checked.
14Diagnose an unexpected result
Compare the expected result with the exact current state of the knowledge revision. Record which of the three actions was last completed and what happened next. Keep the exact validation message or visible status where one exists. This separates an input problem from a saved-state problem and helps another person reproduce the same example.
Check the workspace, selected record and current view. Change one relevant factor at a time. If you change several unrelated settings together, a later success may not explain which change actually resolved the issue.
15Recover without duplicating work
When an answer is wrong, preserve the exact question and response as a test case. Find the source of the incorrect or missing fact before changing unrelated settings. Remove conflicting statements rather than adding another competing explanation. If the answer needs a business decision that the knowledge cannot supply, improve the human escalation route instead of inventing a universal policy.
If the result depends on a provider or another authorised person, record that dependency and use the appropriate route. Do not simulate success by manually changing an unrelated display value or by removing evidence of the original outcome.
16Use the workflow on web and mobile
Long knowledge fields are harder to review on a small screen. Check headings, paragraph breaks and the end of the text after closing the keyboard. Use concise factual blocks that another editor can maintain on either device. If a change is saved on one device, reopen the record on the other before editing so you do not accidentally work from an older visible draft.
When comparing devices, match the same account, record and relevant filters. A desktop screenshot and a mobile screen from different contexts are not evidence of inconsistent data. If a layout problem prevents completing the task, report the screen name, device context and the affected control with private details removed.
17Keep a useful operational record
Retain only the information needed to explain the task: its purpose, the relevant knowledge revision, the action taken and the observed result. If the operation produced a safe reference, keep it with the time and workspace context. This makes a later handover or support query more precise than a screenshot with no explanation.
| Record | Useful content |
|---|---|
| Purpose | Build domain context around real services and boundaries. |
| Inputs reviewed | Industry, products, common requests |
| Outcome to verify | The assistant has useful sector context without unsupported expertise claims. |
| Next owner | Business knowledge owner |
18Protect private information
Use the minimum customer or business information needed for the task. Restrict access to authorised colleagues, and redact unrelated names, numbers and message content when sharing a screenshot. An evidence reference is often more suitable than copying the underlying private document into a general field or support message.
For this workflow, the useful input categories are industry, products, common requests. They should help you make and verify the decision; they are not a reason to publish a customer database, credentials or internal operating notes. The fictional example in this guide can be used for training without exposing live records.
19Know the limits of this workflow
Saving knowledge and publishing it to the live assistant are separate decisions. Customer-facing knowledge should not contain internal credentials or private customer records.
Write concise factual blocks with clear ownership and dates. Separate established policy from suggestions, seasonal offers and information that needs a human check.
Read the linked source material for decisions controlled by a provider or by the applicable commercial terms. A practical guide explains how to approach the task; it does not add a new contractual guarantee or establish that every business use is legally suitable. Use the responsible business owner for unresolved exceptions.
20Review the process over time
Review time-sensitive blocks after price, product, policy or staffing changes. Keep a short baseline test set and repeat affected cases after an update. Record ownership so a new editor knows which source is authoritative. A knowledge library should become clearer as it grows; duplicated marketing paragraphs and contradictory old offers can increase consumption while making answers less reliable.
Update related instructions when the underlying business fact or product behaviour changes. Keep a representative example from this workflow so a future revision can be compared with an explicit expectation rather than judged from memory.
21Practical questions
What should I check before starting?
Prepare industry, products, common requests. Then confirm the workspace and the relevant knowledge revision. The first action is “Start with verified business facts”. Starting there keeps later decisions grounded in the correct record and avoids trying to solve a different problem with this workflow.
How do I know the task is complete?
Use this observable test: The assistant has useful sector context without unsupported expertise claims. If a state is pending, describe it as pending. If a save or provider operation is uncertain, inspect the current record before repeating it. The result matters more than whether a button was pressed.
What if the result still does not match?
Review this risk first: An industry label alone does not make an assistant qualified to advise on regulated decisions. Keep the exact symptom, the relevant reference and the last completed action. Ask the business knowledge owner or the appropriate support route to review the remaining issue, using a small reproducible example rather than a broad export of customer data.
22Completion checklist
Use this checklist as a final review of the task, not as a substitute for the steps above. If an item remains unresolved, identify the next action and its owner. Do not mark a provider-dependent or unverified result complete merely because the rest of the checklist is finished.
- The intended workspace and knowledge revision were identified.
- The necessary inputs were reviewed: industry, products, common requests.
- Start with verified business facts.
- List tasks the assistant may handle.
- Define tasks requiring staff judgment.
- The result was checked: The assistant has useful sector context without unsupported expertise claims.
- The task-specific risk was considered: An industry label alone does not make an assistant qualified to advise on regulated decisions.
- Any unresolved issue has an accountable next owner and a useful evidence reference.