KeyChat

Ask questions about your data in plain language and read grounded, cited answers. About 6 minutes.

KeyChat is KeyOne’s conversational analyst. Instead of building a report, you just ask — “What are the top risks this week?” — and get an answer back in plain English, with its sources attached. It’s the fastest way to triage what’s happening across your stores and then jump straight into the work.

KeyChat has two surfaces over one thread store:

The rail — the chat toggle in the topbar slides KeyChat in as a persistent right-hand rail alongside whatever page you are on (⌘K “Ask KeyChat” opens the same rail). Best for quick asks while you work.
There is no separate page — the rail IS the analyst surface. Visiting /app/chat simply opens the rail over whatever you were looking at.

Both read and write the same saved threads, so you can start in the rail and continue on the full page.

What you’re looking at

When KeyChat opens you’ll see:

A header with the thread title, a History button (the thread library) and a New thread button. On the full page the header also carries the thread’s entity anchor.
The conversation area, where the back-and-forth appears — your messages on the right, KeyChat’s replies on the left.
An input box pinned to the bottom for typing your question.

Before you’ve asked anything, the conversation area shows an empty state with a few suggested prompts you can tap to get going.

Threads & investigations

Every conversation is a saved thread: it’s persisted the moment you send your first question, auto-titled from that question, and listed newest-first under History with its title, entity chip, and last-updated time. Select a thread to reload it; New thread starts fresh; hover a row to rename or delete it.

A thread becomes an investigation — the concept that used to live on the separate Explore page — when you:

Name it — rename inline (click the title on the full page, or the pencil in the History list), and
Anchor it — click the anchor dot / crosshair next to the thread title in the rail header and pick a type (store, product/SKU, category, region, rep) plus the entity’s name and optional id.

Same object, no separate surface: the anchor shows as a colored chip on the thread, and it’s passed to the analyst as context so answers stay focused on that entity. Clearing the anchor demotes the investigation back to a plain thread.

Honest note: if the database is unavailable, the thread list shows an honest empty state and your conversation still works — it just isn’t persisted for later.

Asking a question

Type your question in the input box and press Enter to send. Need a second line? Press Shift+Enter for a newline without sending.

Ask the way you’d ask a colleague — full sentences are fine, and you can follow up to refine. KeyChat keeps the thread, so “and which of those is worst?” works as a follow-up to your last question.

The suggested prompts on the empty state are a good starting point:

“What are the top risks this week?”
“Show me the Win List for store KS_00001”
“Why did rate of sale drop at GreenMart?”

(GreenMart is an illustrative store label, used here as an example — substitute your own store, region, or SKU.)

Reading an answer

Answers appear in the conversation, your questions right-aligned and KeyChat’s replies left-aligned. A reply can include:

The answer itself, with light formatting — bold text, bullet lists, and dividers to keep things readable.
Citation chips — small tags showing exactly which tool, which record ID, and a label the figure came from. Each number traces back to a specific source.
Tool badges — showing which underlying tools KeyChat called to assemble the answer.

Those citations are the point: every figure KeyChat gives you is traceable. You’re never asked to take a number on faith — you can see where it came from, down to the record.

Tip: Skim the citation chips before you act on a surprising number. If a figure has a chip, it’s pulled from your data; if a claim has no chip, treat it as framing or interpretation, not a measured fact.

Grounded and honest by design

The scope banner in the header spells out how KeyChat works:

Your questions run under your own token scope — read access plus author:metric. KeyChat can only see and answer within what you’re permitted to see.
Raw-SQL access is reserved for analyst accounts. If you need to run arbitrary SQL, that’s an analyst capability, not something KeyChat does on a standard token.
Answers are grounded and cited, not fabricated. KeyChat answers from your data; it doesn’t invent figures to fill a gap.

If KeyChat can’t ground an answer, it tells you — rather than guessing.

KeyChat can act, not just answer

Beyond answering questions, KeyChat is registered as an MCP (Model Context Protocol) server with KeyOne’s underlying engine. This means it can take actions in the system on your behalf — not just describe what to do, but do it.

When you ask KeyChat to take an action, it calls the relevant tool, tells you what it did, and what outcome it expects. The 10 tools available are:

Tool	What it does
Read work items	Fetch current risks, decisions, and tasks
Read decision analytics	Pull resolution speed and escalation data
Read OSA signals	Fetch current OOS events and replenishment queue
Create task	Create a new field task in the Work Queue
Bulk create tasks	Create multiple tasks in one step
Assign task	Reassign an existing task to a different owner
Escalate task	Bump a task’s severity level
Launch campaign	Trigger a field campaign across a store set
Create decision	Add a decision to the Work Queue
Create goal	Register a new tracked goal in Orchestration

Example: If you type “Create a replenishment task for SKU 88421 at store KS_00042 and assign it to Sipho,” KeyChat calls create_task and assign_task sequentially, then confirms what it did with citation chips.

Tool calls are always visible in the conversation — you will see which tool was called and what parameters were passed before any action completes.

When the full engine isn’t provisioned

KeyChat’s full conversational, tool-using ability is powered by KeyOne’s embedded engine. If that engine isn’t set up in your environment, KeyChat runs in a limited / offline fallback mode and says so plainly with a banner:

“Chat is not provisioned. Running in offline fallback mode — answers are limited.”

In that mode you can still see the interface and the suggested prompts, but the rich, tool-using, fully cited answers only arrive once the engine is connected. Crucially, even in fallback mode KeyChat does not fabricate figures to fill the gap — a limited state is labelled honestly rather than dressed up as the full experience.

If you’re seeing limited answers and that banner, the fix is on the setup side: the engine needs provisioning. Check the FAQ or ask your administrator.

Writing good questions

KeyChat rewards specificity. The more precise your question, the tighter the answer:

Name the thing. Reference a specific store, region, SKU, or timeframe — “for store KS_00001”, “this week”, “in the North region” — instead of asking in the abstract.
Follow up to drill down. Start broad, then narrow: ask for the top risks, then ask “why?” on the one that matters, then ask “what should I do about it?”
Use it to triage, then act. KeyChat is great for figuring out where to focus. Once you know, jump into the Decision Inbox or your hub’s Work Queue to actually work the items.

Some realistic, illustrative questions an FMCG user might ask:

“Which stores in the East region have the most open risks right now?”
“What’s the rate of sale trend for SKU 88421 over the last 8 weeks?”
“Show me the Win List for store KS_00042 and rank by expected impact.”
“Why is availability down at FreshFields this week?”
“Which three actions would lift sales the most across my territory?”
“Compare on-shelf availability between store KS_00001 and KS_00007.”

(FreshFields and the store/SKU codes above are illustrative — use your own.)

A worked example

Data below is illustrative.

You ask:

“Why did rate of sale drop at GreenMart this week?”

KeyChat replies (left-aligned):

Rate of sale at GreenMart (KS_00013) fell ~18% week-over-week, driven mainly by:

Out-of-stock on SKU 88421 for 3 of the last 7 days [availability · rec_4471 · OOS days]

A price increase of 6% that took effect Monday [pricing · rec_5582 · list price]

The availability gap looks like the larger factor. Tools called: availability, pricing, rate_of_sale.

Notice the citation chips ([tool · record ID · label]) on each figure and the tool badges at the end. You can trust each number because you can see its source.

You follow up:

“What should I do about the out-of-stock?”

KeyChat will point you to the relevant action — and that’s your cue to move into the Work Queue and resolve it.

Common pitfalls

Asking for data outside your scope. KeyChat answers within your access scope. If you ask about a store or region you’re not permitted to see, it can’t return those figures — that’s the permission model working, not a bug.
Expecting raw SQL. Arbitrary SQL queries need an analyst account. KeyChat on a standard token answers through its grounded tools, not free-form SQL.
Expecting it to fabricate. If KeyChat can’t ground an answer in your data, it says so instead of making something up. A “no” or “I can’t ground that” is the honest answer, not a failure.
Mistaking fallback mode for the full experience. If you see the offline-fallback banner, answers are intentionally limited until the embedded engine is connected.

Tip: If an answer seems thin, check for the fallback banner first, then try making the question more specific. Both are common, easy fixes.

Investigations — how named, entity-anchored threads replace the old Explore surface
Using a Hub — where to act on what KeyChat surfaces
Decision Inbox — your queue of decisions to work
Impact Estimates — how expected impact is calculated
FAQ — provisioning, scope, and common questions
Glossary — terms like rate of sale, Win List, and on-shelf availability

Next: KeyLink for Field Reps