Knowledge base writer
Finds the questions your helpdesk keeps getting and drafts FAQ articles for them, from your policies and solved tickets.
How it works
It groups your company's solved helpdesk tickets of the last 90 days (or 30, 60, up to 180) by similar question and lists the questions asked 3 or more times that no article answers yet. For one of them it drafts an FAQ article: a title, a short answer, the steps, and the related passages of your policies, citing the policy and the solved tickets it used. Names, employee IDs, amounts and contact details from the tickets are left out, and a policy quote that isn't word for word in the policy is dropped. Nothing is published until you confirm; then the article is saved in People › Documents as a policy “FAQ: …” shared with everyone, as you, so the Ticket resolver and the assistants answer from it. It can also check your published articles against tickets solved since and flag the ones newer answers contradict.
Finding repeat questions is free; each draft and each check of old articles uses AI credits (the larger model).
What it reads
- Your company's solved helpdesk tickets and the answers given, as far as you may see them
- Your company's synced policies (shared with everyone), only your own company's
When it starts
- When you look for repeat questions on the agent's page, or ask the assistant on the web
What it can do
- Publish the drafted article to People › Documents, shared with everyone, as you (after you confirm)
What it never does
- Reply to tickets, change or delete an existing document, or put a person's details in an article
Safe by design
- One assistant, many agents. Ask the Employee assistant in the app or on WhatsApp; it calls the agents your company has hired that you may use.
- Hired, not switched on. Your admin hires each agent from the catalogue and chooses who can use it.
- Agents propose, people confirm. Anything that changes data, like a leave request, waits for a person to confirm it.
- Same access as the user. An agent sees only what the person asking is allowed to see.
- AI processing in India. Agents run on models hosted in India (AWS Mumbai).
- Budgets and a hard stop. Set a monthly credit limit per agent; agents stop when credits run out.
- Every run recorded. Admins see each run, the credits it used and what it did.
Frequently asked questions
What does the Knowledge base writer do?
It groups your company's solved helpdesk tickets of the last 90 days (or 30, 60, up to 180) by similar question and lists the questions asked 3 or more times that no article answers yet. For one of them it drafts an FAQ article: a title, a short answer, the steps, and the related passages of your policies, citing the policy and the solved tickets it used. Names, employee IDs, amounts and contact details from the tickets are left out, and a policy quote that isn't word for word in the policy is dropped. Nothing is published until you confirm; then the article is saved in People › Documents as a policy “FAQ: …” shared with everyone, as you, so the Ticket resolver and the assistants answer from it. It can also check your published articles against tickets solved since and flag the ones newer answers contradict.
Can the Knowledge base writer change data on its own?
No. It asks a person to confirm before it will: publish the drafted article to people › documents, shared with everyone, as you. It never does the following: reply to tickets, change or delete an existing document, or put a person's details in an article.
How much does the Knowledge base writer cost?
Finding repeat questions is free; each draft and each check of old articles uses AI credits (the larger model).. Credits are a paid add-on to any flowwork.ai plan at ₹100 (US$ 1.19) per 1,000 credits, and new companies get 500 free trial credits for 30 days.
Where is the data processed?
Agents run on AI models hosted in India and see only what the person using them is allowed to see. Admins see every run and the credits it used.
Other agents
Drafts an answer to a ticket from your policies and similar solved tickets, with its sources and how sure it is.
Suggests category, priority and group for a ticket and drafts a first reply from similar solved tickets.
Tell it about your company in plain words; it plans departments, offices, holidays, leave, work week, payroll and expenses for you to confirm.