Knowledge Assistants
AI Knowledge Agent for Microsoft 365
Answers staff questions from your documents with citations, connected natively to Microsoft 365 so it reads and cites SharePoint, OneDrive and Teams…
Knowledge Assistants
AI Policy Q&A
Employees ask about leave, expenses or conduct and get the exact policy clause, not a guess.
HR teams answer the same leave, expenses and conduct questions every week, and a paraphrased answer can cause real trouble. This chatbot answers employee policy questions by quoting the exact clause from your own policy documents, so staff and HR can both trust it. Anything outside written policy, such as a personal case, goes straight to your HR inbox.
- Every answer quotes the exact policy clause it used
- HR stops answering the same leave and expense emails
- Personal cases routed to your HR inbox, not the bot
$4,400
20–30 working days
Optional maintenance $249/mo
What it is
AI Policy Q&A is a chatbot that answers employee questions about HR, compliance and operational policy, such as leave, expenses or code of conduct, and quotes the exact clause it drew the answer from. Personal cases are routed to your HR inbox.
Why businesses buy it
Policy questions look small, but they add up: hours of HR time each week, inconsistent answers between managers, and the occasional costly misunderstanding about leave or expenses. Because this bot quotes the clause itself rather than paraphrasing, employees get the same correct answer every time and HR keeps control of the wording. It works across your intranet, Slack or Microsoft Teams. The Scope Card fixes the channel, document limit, intents and testing before you order, so HR and IT know exactly what is being built.
Problems this solves
HR answers the same leave and expense questions every week
Employees ask the chatbot in Slack, Teams or a web widget. It answers from your policy documents and quotes the exact clause, so HR stops being the first stop for routine lookups.
Staff read policies differently and apply them unevenly
Because each answer quotes the clause it relied on, everyone sees the same wording. Managers and staff can check the source instead of relying on memory or a colleague's version.
Personal situations need a person, not a chatbot reply
Questions about an individual case are routed to your HR inbox through the single handoff connection. Guardrails and up to five intents are set up so the chatbot recognizes these cases.
A good fit if
Your questions are specifically about HR and operational policy, such as leave, expenses, remote work or code of conduct, not general company documents.
You have up to 100 policy documents or 200 web pages, and HR fields the same questions by email every week.
You want every answer to quote the exact clause it came from, so staff and HR both trust it over a paraphrase.
You are comfortable routing anything outside written policy, such as a personal HR case, to your HR inbox instead of the bot.
Not the right fit if
Your questions cover documents beyond policy, such as product specs or finance procedures too. See AI Company Knowledge Hub, which spans multiple departments.
You need a single technical document set answered, not HR policy specifically. See AI Document Q&A, built for one general document set.
You want to know what policy questions people ask that are not yet written down. See AI Knowledge Gap Finder.
Your policies are not written up yet and need drafting first. See AI FAQ Generator, which drafts FAQ content from source material.
How it works
- You give us the HR and policy documents this bot should learn, such as the employee handbook, leave policy and expense rules, up to 100 documents or 200 web pages.
- We index every clause and build your top 20 approved FAQs into it, so the bot answers only from policy you have signed off, never a general guess.
- An employee asks a plain-language question, such as how much notice a resignation needs, on your intranet, Slack or Microsoft Teams.
- The bot matches the question to the right clause and answers with the policy's own wording, quoted and attributed, not paraphrased from memory.
- A question outside written policy, such as a personal case, hands off to your HR inbox instead of being answered by the bot.
- We test it against 40 documented policy questions with pass/fail results before launch, so you see exactly what it gets right before employees do.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- The HR and policy documents this bot should learn, such as the employee handbook, leave and expense policies.
- Your top 20 policy FAQs, with the answers HR currently gives.
- Your HR inbox or helpdesk address for questions the bot should not answer itself.
- Intranet, Slack or Microsoft Teams admin access to install the bot.
- Your logo and brand colors, so the widget matches your intranet or workspace.
- Admin access and API keys for every connected system, shared by adding our team as a user or creating a key you control, never by email.
- One decision-maker, usually from HR, who can approve the policy answers before launch.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake confirmed, with the policy set and top 20 FAQs agreed with HR.
Weeks 1–2
Policy documents indexed and the FAQ set built into the bot's approved answers.
Week 3
Widget and HR handoff path connected to your intranet, Slack or Microsoft Teams.
Weeks 3–4
Tested against 40 documented policy questions, with pass/fail results delivered.
Week 4
Your review and two rounds of changes.
Go-live
Live, with a recorded handoff session, and 30 days of support starts.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $4,400 |
| Express | 15–25 working days | $5,150 |
| Rush | 10–20 working days | $5,950 |
What you receive at handover
- The policy chatbot deployed on one channel: Slack, Microsoft Teams or a website widget
- Your HR, compliance and operational policies loaded, up to 100 documents or 200 web pages
- Prompt and guardrail settings, including routing of personal cases to your HR inbox
- Test report with 40 documented questions and pass/fail results
- Admin guide and a recorded 60-minute handoff session
- 30 days of post-launch support
Expected benefits and how to measure them
- Can give employees a consistent, sourced answer at the moment they need it.
- Helps HR spend more time on personal cases and less on looking things up.
- Routine policy emails to HR
- Count leave, expense and conduct questions in the HR inbox for four weeks before launch and four weeks after.
- Clause accuracy
- Each quarter, check a sample of answers against the current policy and record whether the quoted clause was correct.
- Correct routing of personal cases
- Review cases the chatbot sent to the HR inbox each month and note how many were genuinely personal.
Before you start: Log a month of routine policy questions reaching HR, grouped by topic. Note which policies come up most often.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
You pay for the build once. Running it costs roughly $30 to $150 a month in your own accounts, covering AI model usage and hosting, and moves with how many employees ask questions each month.
AI usage during the build and testing is billed to your own accounts too, so the AI model relationship stays in your name.
Ask about running costsCustom requirements
If you need more than 100 policy documents, a second channel, or more than 5 intents, add a note at checkout for a written Change Quote. Your order still runs on its normal timeline. Larger or bespoke projects go through the Custom AI request form.
Request a custom versionKeep it running
Optional monthly maintenance covers monitoring, fixes, model and platform updates, a monthly health report and monthly change hours for a policy update or a new FAQ. It starts after the 30 days of support and can be cancelled any month.
$249/mo (the minimum fee, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | An HR helpdesk tool charges per employee seat every month | A custom agency quotes after a discovery call | Ours is one fixed price, shown before you buy |
| Scope | An HR helpdesk tool leaves you to write and tag every policy answer | An agency agrees scope as the project runs | Ours is written on the Scope Card before purchase: your policy set, up to 100 documents |
| Accuracy | An HR helpdesk tool answers from whatever was typed in, right or outdated | An agency build depends on what was scoped and tested | Ours quotes the exact clause and is tested on 40 documented questions before launch |
| Delivery | An HR helpdesk tool is instant to sign up but slow to populate correctly | An agency build usually takes several weeks | Ours has a fixed delivery time shown before you buy, with faster options |
Questions about this product
How is AI Policy Q&A different from AI Document Q&A?
AI Document Q&A answers from any single document set you choose, such as a product manual. This bot is built specifically for HR and operational policy, quoting the exact clause behind every answer and routing personal cases to your HR inbox. Choose Policy Q&A when the questions are about leave, expenses, conduct or similar policy.
Does AI Policy Q&A quote the actual policy wording or paraphrase it?
It quotes the clause itself, attributed to the document it came from, rather than paraphrasing. That matters for policy, where the exact wording of a leave or expense rule can change the answer. If a clause is ambiguous, the bot says so and hands the question to your HR inbox instead of interpreting it.
Can it handle a personal HR situation, not just general policy?
No, and it is not meant to. It answers general policy questions from documents you approve, and hands anything personal, sensitive or outside written policy to your HR inbox. You set that boundary during intake, and the 40-question test before launch confirms it behaves the way you expect.
How much does AI Policy Q&A cost to run each month?
Roughly $30 to $150 a month in your own accounts, covering AI model usage and hosting, moving with how many employees ask questions. The build itself is paid once and covers indexing your policy set, building the FAQ answers, and the 40-question test before launch.
How long does AI Policy Q&A take to launch?
Delivery runs on a fixed schedule from a complete intake, and the delivery panel shows that date plus express and rush options before you buy. Most of the time goes into indexing your policy documents, building the approved FAQ answers with HR, and running the 40-question test before your review.
What happens when a policy changes after AI Policy Q&A launches?
Update the source document and ask us to re-index it. That fits inside the monthly change hours included with maintenance. Without maintenance, a policy update can still be quoted as a small Change Quote, agreed before the work starts. Maintenance also covers monitoring, fixes, a monthly health report and new FAQs, and can be cancelled any month.
Policy questions answered in the policy's own words.
Order AI Policy Q&A and it goes live on a fixed delivery date, quoting the exact clause behind every answer your employees get.
Works well with
Knowledge Assistants
AI Knowledge Agent for Google Workspace
Answers staff questions from your documents with citations, connected natively to Google Workspace so it reads and cites Drive files, shared drives…
Knowledge Assistants
AI Knowledge Agent for Confluence
Answers staff questions from your documents with citations, connected natively to Confluence so it reads and cites spaces and pages your users…