Docently by Datics AI
A support agent for your learners and admins, grounded in your help center.
Answers how-do-I questions from your help center with the article linked, inside your product or in Slack, and hands the rest to support with the context attached. It ships inside your platform, under your name.
Built into your codebase and shipped under your name, on an engine we license to you.
admin.northstarcampus.com / help
In · Employer admin asks
How do I assign the safety course to the new Field Service department? And can I set a different due date for contractors?
Out · Docently
Courses → select the course → Assign › By department → Field Service.
Help · Bulk assignment
Not in the help center: TKT-5509 opened, conversation attached
Same demo, step by step below.
Try it step by stepIllustrative demo on a fictional institution. Not client work.
From question to answer, or to a person
Answers from your help center, and a clean handoff when the docs are silent.
Northstar Workforce Academy (fictional). An employer admin asks how to bulk-assign a course to a new department.
Employer admin · in-product help
Input- Q1How do I assign the safety course to everyone in the new Field Service department?
- Q2Can I set a different due date for contractors?
Two questions in. One answered from the docs, one handed to a person.
- 1Searching 214 help-center articles
- 2Checking the best match is good enough
- 3Writing the answer with its source
- 4Routing what the docs don't cover
Illustrative demo on a fictional institution. Not client work.
AI inside the workflow
Docently inside the product, not a chatbot beside it.
Northstar Learn today: support answers the same how-to tickets by hand every term start.
The assistant runs Docently, branded as Northstar Help, the way it is built to ship under your product's name.
Illustrative demo on a fictional institution. Not client work.
What it does
What Docently can do.
"In the demo" items are shown above; "Sprint-ready" ones are built the same way. We pick the ones that fit your product; you don't need all of them.
Answer users inside your product, help your support team with tickets, and find what your docs are missing.
Answer users
Cited answers
In the demoAnswers from your help center, docs and release notes, linking the article it used.
Answer users
Clean handoff
In the demoSays when the docs don't cover a question and opens a ticket with the conversation attached.
Help the support team
Draft replies
In the demoDrafts answers to open tickets for an agent to approve.
Proof: the work it builds on
Built on a support-agent engine we've delivered.
Our own product
B2B Software · AI support assistant
Support chats answered from each company's own content, with handoff to a person
Bots that answer from the wrong content lose visitors. Each chatbot in our assistant answers from its own knowledge base and hands off to an agent.
NenoBrief by Neno Technologies
Government, Legal & Defense · AI gateway for a live DMS
Archive officers get cited answers inside their live document system, files never copied
Archive records could not reach an outside AI. Now the client's live document system calls our self-hosted gateway for cited answers.
Dental clinical documentation AI
AI engine · Review and approve
AI clinical documentation inside the dentist appointment workflow
Live transcription, patient context and AI-drafted clinical notes with dentist review and approval.
Why it sells
What Docently does for your business.
What your customers get, and what it does for your renewals and pricing.
A reason to renew
Admins and instructors get answers at rollout and term start inside your product, when first impressions are made.
An answer for RFPs
Cited answers and a clean handoff to your support team, under your name, for buyers who ask how AI support works.
Lower support load
Fewer how-do-I tickets; the Build Sprint measures the share of your past tickets it could have answered.
Controls
What Docently touches, and who approves.
Student data isn't used to train models for anyone else and stays in your cloud. Built and tested on synthetic or de-identified data.
Who uses it
Learners, instructors and admins asking how-do-I questions, and your support team.
What it connects to
Your help center, docs and release notes, your help desk, and optionally Slack.
What a person approves
Questions the docs don't cover go to a person with the context attached; draft replies can wait for support approval.
Switch per institution
On or off for each institution, with data settings their admins control.
How to get it
Two steps to a finished Docently.
Start with a three-week Build Sprint. Add more only if you want it.
First · Build Sprint · $10,000 fixed
Users get cited answers inside your product
- Cited answers
- Clean handoff
- Draft replies
- In your staging, behind a feature flag
- Delivered as pull requests
- A test set your team reviews
- Week 1Setup
- Weeks 2–3Build
- You getDocently in your staging and a fixed production quote
- Your time
- About 2–3 hours a week from a product owner
- Data
- Synthetic or de-identified
- The fee
- Counts toward production
Then · Live in production
A finished product, yours to run
- Fixed quote
- Tested before launch
- Switch per institution
- A finished, working Docently in your product
- Runs in your cloud, under your name
- Fixed quote, agreed before we start
Optional · Add more later
Only if you want it
More of Docently:
- Guided walkthrough
- New-customer onboarding
- Slack and Teams
- +3 more
Another module:
- Each one quoted on its own
- Nothing ongoing unless you ask
Already built or tried AI? Get it scored with the AI ScorecardNeed something else? Start with a Planning Sprint
FAQ
Questions about Docently.
What if the docs don't cover a question?
It's designed to say so and open a ticket with the conversation attached, rather than guess.
Does it answer users or help our support team?
Both. It answers in the widget, or drafts replies to open tickets for an agent to approve.
Where does it run?
Inside your product as an embedded widget, and optionally in Slack or Teams for internal teams.
How do we know it's helping?
A weekly top-questions report shows what users ask by role and institution, and the docs gap finder lists what the docs couldn't answer. The Build Sprint measures the share of your past tickets it could have answered.
What does a conversation cost to run?
We measure the cost per conversation in the Build Sprint, on your real help center, so you know it before you decide on production or pricing.
See Docently on your own product.
Bring your product and one workflow. In 30 minutes we look at where Docently fits, what it would cost to serve and what your customers' security review will ask.
Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.