AI Knowledge and Support Agent
Cloud Storage Software · Support Agent / Knowledge Retrieval
An AI agent that answers from knowledge spread across cloud storage, inside Slack and Teams
A cloud file-management company runs a desktop and web product across several cloud-storage providers. Datics built its AI layer: ingestion and vectorization of documents and pages across those providers, and an agent that answers questions inside Slack and Microsoft Teams, checking approved answers first and falling back when nothing relevant is found.
- Status
- Delivered
- Engagement
- 2023, after an earlier QA engagement on the desktop app
Support Agent / Knowledge Retrieval
Answer
Where questions are matched to FAQs or answered from the knowledge base.
- Cross-cloud ingestion
- FAQ-first answers
- Answers in Slack and Teams
- Knows its limits
The company's own content and workspace.
The starting point
An established desktop and web product that manages files across multiple cloud-storage providers. Product knowledge and customer content were spread across those sources, and questions were answered by hand.
What had to change
People needed fast, consistent answers from knowledge held in different clouds and formats, where they already work, not another search box.
What couldn't break
Answers had to come from the company's own content first, and the agent had to say when it did not know rather than guess.
Why this was hard
Each cloud provider has its own access model and data shape, so ingestion has to normalize them before retrieval can be reliable, and the fallback has to be predictable.
What Datics changed
Datics built ingestion and vectorization of documents and URLs across cloud providers, a knowledge-base chat that checks a curated FAQ set first, then the indexed knowledge and model fallback, with answers stored for reuse, delivered as a Slack bot with structured replies and extended to Microsoft Teams, alongside provider comparison and workflow automation.
Datics first tested the desktop app and cloud services, then designed and built the AI layer, starting with a proof of concept across three storage providers.
Cross-cloud ingestion
Documents and pages ingested and vectorized across storage providers.
FAQ-first answers
Approved answers checked before anything is generated, and good answers stored for reuse.
Answers in Slack and Teams
Structured replies where people already work.
Knows its limits
Falls back predictably when nothing relevant is found.
How it works
Connects to: Cloud-storage providers, Slack and Microsoft Teams.
- 1
Ingest
Where content from each cloud provider is collected and vectorized.
- 2
Answer
Where questions are matched to FAQs or answered from the knowledge base.
- 3
Deliver
Where answers reach people in Slack or Teams.
Runs within: The company's own content and workspace.
Engagement at a glance
Questions get consistent answers from the company's own knowledge, across clouds, where people already work.
- Sources
- Several cloud-storage providers
- Answer order
- Approved FAQs first, then the knowledge base
- Surfaces
- Slack and Microsoft Teams
Under the hood
- Datics role
- QA engineering, then AI product design and engineering.
- Integrations
- Cloud-storage providers, Slack and Microsoft Teams.
- Deployment
- AWS.
- Production boundary
- The company's own content and workspace.
Technology
What this unlocked
The same ingestion and support-agent pattern powers Docently for LMS, student-services and EdTech help centers.
Related work
Learning-agency directory
EdTech · Directory / Marketplace
A vetted, subscription directory that helps education buyers find and compare learning agencies
A members-only directory of vetted education agencies with search, filters, shortlists, moderated comments and Stripe subscriptions, built end to end in six milestones.
Leadership-development practice app
EdTech · Learning App / Mobile & Desktop
A leadership-development practice app taken from the web to iOS, Android and desktop
A daily leadership practice built on seven inner archetypes, taken from a web app to native iOS, Android, Windows, macOS and Linux apps from one codebase.
Voice Roleplay Trainer
Insurance Sales Training · Skills Practice / Voice AI
AI voice roleplay that makes skills practice measurable
Agents pick a scenario, a prospect personality and a difficulty, hold a live voice call with an AI prospect, and get a scorecard, transcript and coaching against the firm's own method.
Have a product with the same kind of constraints?
Tell us what already exists and what you want it to do. We will tell you what it takes.