Product
One connected operating workspace, not a chat box over a database.
The Import Intel operations platform gives employees a place to ask for real work, and gives the business explicit control over what agents can read, run, and prepare. Inside the product, the agentic command surface is called Ask Sawyer.
Read-only by default. Source-grounded. Human-approved where actions matter.
Primary surfaces
Where the work happens
Conversations
Ask once. The platform finds the right systems, evidence, and workflow.
Related workflows
- Ask operational questions in plain language
- Query governed plant data and attach files
- See agent tool activity, sources, and returned rows
- Receive artifacts such as reports and PDFs
- Delegate work to a specialized agent and continue later
Dashboarding
The chart, answer, rows, query, source, and time scope stay connected.
Related workflows
- Create one chart or a full dashboard from a normal request
- Edit a selected chart conversationally
- Inspect the governed query and the rows it returned
- Keep time scope and source freshness visible
- Surface no-data and query errors honestly
- Pin results from a conversation and save reusable views
Agents
Build a repeatable role, not another one-off prompt.
Related workflows
- Define the job, tools, sources, and permissions for a role
- Attach files, knowledge, and skills
- Set instructions and approval rules
- Reuse the role across shifts, sites, and teams
Integrations and tools
Governed access to the systems that already run the plant and the office.
- Operational database context and read-only queries
- Production, downtime, and dashboard metrics
- Document classification, extraction, and report comparison
- Maintenance parts, inventory, order, and invoice workflows
- Market research with explicit sources
- Connected-system tools that run with the signed-in user's permissions
Supporting surfaces
What keeps answers consistent between people, dashboards, and agents
Knowledge and modeling
Model the operation once. Reuse the meaning across questions, dashboards, and agents.
- Governed datasets, views, columns, and calculations
- Explicit relationships instead of guesses from matching column names
- Saved analytical examples, approved queries, and revisions
- Owner and tenant scope respected at answer time
Ontology
Import Intel learns the structure of the operation, not just the names of its database columns.
- Sites, process areas, machines, lines, and sources
- Metrics, units, shifts, products, and grades
- Events, operator responses, work orders, parts, and stock
- Customers, orders, invoices, documents, and workflows
- Evidence and lineage from answer back to source
Organizations and permissions
One company's plant data is not pooled into another company's operating context.
- Company and site tenancy
- Users, roles, invitations, and administrative controls
- Tenant-scoped data, dashboard sessions, and artifacts
- Delegated user access for connected systems and audit attribution
Files and artifacts
Agent work produces things people can use, not only text.
- Analyze uploaded documents and extract structured fields
- Preserve source-line references
- Generate reports, spreadsheet-ready data, and PDFs
- Attach artifacts to the conversation that produced them
- Retain artifact identity, provenance, and expiration metadata
Skills and prompts
Digital standard operating procedures, not a prompt library
Differentiation
How this differs from what you have already been sold
Versus generic AI chat
Them
- Knows general language, not your data model or process
- May have no permissioned tools
- May not preserve source evidence
- Can produce plausible but ungrounded answers
Import Intel
- Receives plant-specific context
- Maps language to governed operational concepts
- Reads approved systems and validates queries and outputs
- Preserves evidence and time scope, and stops at approval boundaries
Versus traditional BI
Them
- Answers questions someone modeled in advance
- Needs a developer or analyst for new views
- Separates the dashboard from the next action
Import Intel
- Creates and edits views from normal language
- Keeps answer, chart, rows, and source connected
- Turns analysis into a report, event workflow, or draft action
Versus point solutions
Them
- Cover one machine, system, report, or department
- Preserve the silos between production, maintenance, purchasing, and the office
Import Intel
- Connect plant and office evidence in one operational model
- Coordinate work across systems without replacing them all
Versus automation and RPA
Them
- Follows a fixed sequence
- Breaks when the context changes
- Hides why a step was selected
Import Intel
- Agents reason within defined tools and policies
- Can ask for clarification
- Preserve agent activity and keep consequential changes review-gated
See it against a workflow you already run.
Bring one question your plant answers too slowly. We will show what an agent can complete with your sources and your approval rules.