Knowledge Base
Knowledge Base
Connect your databases, upload documents, and define business terms in one place — so your team and the AI Assistant always have the right context.
Mithrilis
Overview#
In logistics, data lives everywhere — your TMS, carrier portals, ERPs, warehouse systems, spreadsheets, email. The Knowledge Base brings it all together into one place where your team can browse, query, and make sense of your data without switching between tools.
It also powers Mithrilis's AI Assistant. When you ask a question, the AI draws from your connected databases, uploaded documents, and business definitions to give you an accurate, grounded answer — not a guess.
Connect Your Data Sources#
Connect your existing databases directly to Mithrilis. If you've already configured integrations with your carrier or TMS systems, the Knowledge Base detects those credentials automatically — no need to re-enter connection details.
Once connected, Mithrilis maps out your database structure so you can browse tables, see what data is available, and understand how everything is related. This works with any standard database, with support for additional types as demand grows.
Automatic credential detection
If a database is already configured in your integrations, the Knowledge Base recognizes it automatically and offers it as a data source. Otherwise, it walks you through setting up the connection.
Definitions Library#
A searchable library of business definitions that gives your entire organization a shared vocabulary.
Why This Matters#
In logistics, the same term can mean different things to different teams. "On-time delivery" might be measured from pickup to final delivery by one team, and from warehouse departure to customer receipt by another. When teams and systems define terms differently, you get conflicting reports, miscommunication, and bad decisions.
The Definitions Library creates a single, authoritative source for what terms mean in your organization. Define "on-time delivery," "exception," "SLA breach," "proof of delivery," and any other terms your team uses — and the AI Assistant will use those same definitions when answering questions.
How to Use It#
- Create definitions for key business terms your team uses every day
- Scope definitions to specific business units, so different teams can maintain their own vocabulary where needed
- Search and browse from the library interface
- Definitions are automatically used by the AI when answering questions about your data
Start with your most ambiguous terms
Begin with the terms that cause the most confusion across teams. These are the ones where having a single, authoritative definition delivers the most value.
Query Playground#
An interactive tool for querying your connected data sources directly inside Mithrilis — no need for a separate database client.
Features#
- Write and run queries against any connected data source
- Results table — Sortable, scrollable results with the ability to download as CSV
- Saved queries — Bookmark frequently used queries for quick access. Saved queries are visible to your team.
- Read-only by default — Prevents accidental changes when exploring data
- Query feedback — Rate results to help improve future AI-generated suggestions
Large result sets
Results over 10,000 rows are automatically paginated. Use the download button for full exports.
Documents#
Upload documents that your team and the AI Assistant can reference. PDFs, Word documents, plain text, and markdown files are all supported.
Once uploaded, documents are processed and made searchable across the platform. When you ask the AI a question, it can find relevant information from your uploaded documents and include it in its answer.
Use Cases#
- Upload carrier rate sheets so the AI can answer questions about pricing
- Store SOPs and procedures for team reference
- Add contracts and service agreements for compliance lookups
Workflow Integration#
The Knowledge Base connects directly to the Workflow Builder. Add a data lookup step to any workflow, and your automations can pull live information from your connected systems to make decisions.
Example: A workflow receives a carrier update, looks up that carrier's SLA terms from your database, and checks whether the event is an SLA breach — all automatically.
Data-driven automations
Combined with AI steps, you can build workflows that look up your data, have the AI analyze it, and take action based on the results — all in a single automation.
Getting Started#
Connect a data source
Navigate to Knowledge Base from the sidebar, then click Add Data Source. If your credentials are already configured, the system detects them automatically. Otherwise, enter the connection details manually.
Browse your data
Click on a data source to see its tables, fields, and relationships. This helps you understand what's available before running queries.
Add business definitions
Go to the Definitions tab and start adding terms. Each definition should include a plain-language explanation that your whole team can understand.
Run your first query
Open the Query Playground, select a data source, and write a query. Click Run to see results. Save useful queries for your team to reuse.
Topics
Related updates
Knowledge Base
Data Unification
One source of truth for every shipment — Mithrilis merges data from all your systems, shows you which sources it trusts and why, and flags conflicts for your team to resolve.
AI
AI Query & Assistant
Ask questions about your logistics data in plain English and get trustworthy answers — backed by your actual data, with sources shown so you can verify every result.
Workflows
Workflow Builder
Build visual automations for your logistics operations — drag-and-drop design, 50+ integrations, AI-powered steps, branching logic, version history, and pre-built templates.