See the change firstThe old and proposed values are visible before any AI explanation.
Keep CRM records up to date as conversations change.
Signal suggests CRM changes from customer conversations. Sellers can review the evidence and update records from the tools they already use.
Problem
Customer conversations change before CRM records do.
Sellers learn about deal changes through emails, meetings and notes. Updating the CRM means switching tools and entering those details again. I designed Signal to let sellers review and save changes from the conversation itself.
Problem snapshotWhy the CRM falls behind
Live conversationWhat changed today
✉
Email“The $450K budget has been approved.”
◉
Meeting“We want to start a new rollout.”
✎
Seller note“Sarah is taking over procurement.”
→
Manual handoffContext has to be remembered and re-entered
CRM RecordWhat the system still knows
Budget$400Kout of date
Close dateSep 30out of date
Procurement leadNot setmissing
New opportunityNot createdmissed
Approach
Suggest updates alongside the conversation.
Signal proposes a CRM action when a conversation contains new information. The seller can check a field change, add a stakeholder or review a new record before saving it.
Signal system modelHow source information becomes a CRM suggestion
Connected sourcesSources Signal can use
✉
Emailcustomer conversations
◉
Virtual meetingslive conversation + transcript
in
Sales Navigatorpeople + role changes
⌂
Company websitespublic business signals
✎
Seller notesoffline conversation context
→
✦Signalidentifies new information
and proposes a CRM change
and proposes a CRM change
→
Proposed CRM actionsChanges the seller can review
01Updatekeep known facts current
02Createprepare a new opportunity
03Progresssuggest the next deal stage
04Connectpeople, products and competitors
05Surfaceshow relevant deal information
Design principleThe right CRM update, inside the seller’s existing work.
Solution
Fit the suggestion to the tool the seller is using.
I adapted the same review pattern for email, meetings, notes and CRM. Each version uses the space and interactions available in that tool.
Flow-of-work modelThe same review pattern across tools
The core experience
Sellers review suggestions in the tool they are using.
The CRM update appears inside the surface where the work is already happening.
Seller
Alex
moves through the day
EmailReview a CRM suggestionSignal appears beside the message
Virtual meetingCreate a new opportunitySignal opens in the meeting side pane
CRMSee what changedSignal appears in the deal itself
Notes / voiceCapture offline contextSignal works from the seller's note
1The seller stays in the task
→
2The layout adapts to each tool
→
3Evidence and review stay available
Design decisions
Show the proposed change and its evidence.
Before accepting an update, the seller can see what will change, where the information came from and which record it affects.
Interaction anatomyDetails shown with each suggestion
✦ Signal – Suggested CRM updates
Opportunity: Asteron expansion ↗
4 changes
Budget
Explicitly stated
$400K
→
$450K
⌃
✦Evidence
“The $450K budget has been approved.”
Found in this email from Sarah Chen · 8:41 AM
View in email
Evidence stays attachedOpen the evidence to see the customer’s words, source and time.
Inference is named“Explicitly stated” is different from “Strong signal” or “Needs review.”
The seller decidesThe seller can accept, edit or dismiss each suggestion.
Trust modelSource → Suggested change → Saved update.
Story
Meet Alex, a seller moving through a busy day
The walkthrough follows Alex through a working day. Each conversation tests a different way to capture a deal change and review it in context.
01
Morning
The day starts with an email that changes the deal.
Sarah’s email reveals four updates the CRM does not know yet.
Alex can compare the four suggestions with Sarah’s email, then choose which changes to save.
What Signal found in the email
Four changes, with different levels of certainty.
Try the prototype
Open a suggestion → check the evidence → accept, edit or dismiss.
Email patternMake the decision where the evidence already is.
Afternoon
A coffee before the next customer conversation.
Alex prepares for a customer meeting. This part of the prototype tests how Signal proposes an update during a live conversation.
02
Afternoon
A customer meeting reveals a deal that does not exist yet.
Signal proposes a new opportunity for Alex to review.
During a meeting with Asteron, the conversation shifts from exploration to a real rollout. Signal recognizes that the CRM is missing the deal and proposes a new opportunity while the context is still fresh.
NoticeA buying signal appears in the conversation.
ReviewSignal explains why and prepares the required CRM fields.
CreateAlex reviews once. Signal records the opportunity in CRM.
Try the prototype
Wait for Signal → open the suggestion → review the evidence and fields → create or dismiss.
If you ignore it, leave the meeting to see how Signal keeps the unresolved CRM update available for review.
Meeting pattern
Keep the meeting in view while the seller reviews a new opportunity.
Evening
Later that evening, Alex meets a customer in person.
As he walks out, the conversation is still fresh. Alex records a quick voice note to capture what was agreed. Once the note is saved, Signal recognizes that the deal has moved forward and brings the next CRM update to him.
03
EveningAn in-person meeting ends. The deal keeps moving.
Alex saves a voice note after the meeting.
On a work-managed iPhone, Alex can use Siri to save the meeting note without opening the CRM app. Signal uses the connected work context behind the scenes. When the note contains evidence that the deal has progressed, it brings the relevant CRM update to Alex.
Capture naturallyAlex asks Siri to save the customer outcome while it is still fresh.
Signal recognizesThe saved note becomes another signal in the connected work context — no CRM app required.
Act when it mattersSignal surfaces the evidence and suggested stage change for Alex to review.
Try the prototypeLet Siri finish the note → Save note → tap Signal’s notification → review the evidence → Move to Closing.The CRM app never needs to be opened. Siri handles capture; Signal turns the saved context into a reviewable CRM update.
Mobile review patternThe phone handles voice capture. Signal uses the saved note to propose a stage change for Alex to review.
End of day
Alex finishes where the record lives.
By the time Alex opens the CRM, most of the day is already captured. Signal and the other agents have kept records current; Alex only reviews what still needs judgment.
04
CRMThe system of record becomes the review surface.
The CRM prototype shows how Signal fits into the wider product.
For the CRM prototype, I designed the opportunity workspace and record experience around Signal. Sellers can review agent updates, check their evidence and undo a saved change.
Product layerOpportunity workspace + record experience
Agent layerOne place for Signal and other specialized agents
Trust layerEvidence, confidence, review and reversible updates
123
Design principleThe CRM should show what agents changed and give sellers a way to review or undo it.
Try this prototype
Review what Signal changed — then undo it.
Open Asteron, review an update, accept it, then undo it to see the CRM stay synchronized.
Product outcomes
How I would measure the design.
I would measure Signal on whether it reduces seller admin while improving the freshness and completeness of the system of record.
Across the seller’s day.
Review deal changes across the seller’s day.
The prototypes use the same review pattern across email, meetings, notes and CRM. Each suggestion carries the proposed change and its evidence, so sellers can pick up a review in another tool.
01CRM
02Meeting
03Email
04Notes
✦
Deal context stays with each suggestion.CRM intelligence that stays connected across the surfaces sellers already use.