DESIGN CONCEPT · NOT SHIPPED · PRIVATE BANKING CRM · AI AGENT UX

ConnectX
Private Banking CRM

A CRM for the room where decisions are made between people, not from a Salesforce dashboard. Eleven screens, eight named AI agents, four explicit autonomy levels — observatory rather than control room. Cormorant Garamond, gold leaf, and an oxidized lavender reserved for moments when an agent is speaking.

11
Canonical Screens
8
Named AI Agents
4
Autonomy Tiers
$24B
Synthetic AUM
ConnectX cinematic intro — serif Connect with italic gold X over warm-ivory ground, eyebrow EST. MMXXVI, subtitle the institutional CRM, reimagined
Cinematic intro · Reel 01 · 22 seconds · plays once on first load. Editorial title sequence over enterprise app shell.
Disclaimer

A concept artifact, not a shipped product.

ConnectX is a research artifact — a working React bundle exploring how AI agent UX could feel inside a private bank's relationship-management workflow. The data is synthetic (Fortune 500-style enterprise relationships used as institutional client analogues). "Elena Vance · Compliance · Risk Officer" is a fictional persona, not a real user. Nothing here connects to a production CRM, KYC system, or core banking ledger.

ConnectX shares no engineering or commercial relationship with ACY Connect — that is ACY Securities' B2B trading platform documented separately. The naming overlap is incidental; this case study sits in the same lineage as Xanthos Private Bank, Double-Blind Fiduciary Protocol, and Intent Canvas — concept work for the regulated wealth surface.

The Problem

Private banking is the worst-served customer of the CRM industry.

Salesforce Financial Services Cloud, Microsoft Dynamics, Hubspot, even Bloomberg's CRM module — they all index for transactional sales: lead → opportunity → close. Private banking doesn't work that way. A single Tier I client relationship spans ten years, four entities, twenty-two covenants, three regulators, and a spouse's family office that nobody initially flagged. The CRM the relationship manager actually needs is not a sales pipeline. It is an observatory:

What is moving across my book today, and what does it mean. Quiet relationships that should not be quiet. Agents watching covenants in the background. A 4.2% crude move that reshuffles three accounts before breakfast. AI that observes — never directs. ConnectX is a sketch of what that surface could be, designed at editorial register rather than enterprise CRM register.

The Paradigm

CRM-as-database vs CRM-as-observatory.

The default enterprise CRM treats relationships as rows. Each interaction is a record. The UI is a search-and-filter interface over the database. ConnectX inverts: the relationship graph IS the page; the database is implicit. AI agents are persistent watchers, not chat features. Editorial voice replaces dashboard voice.

Default · CRM-as-Database
Salesforce / Dynamics tradition
  • List view first; relationships are rows
  • Pipeline as Kanban — deals as cards in stages
  • AI is a chat panel grafted onto the side
  • Notifications optimised for sales activity
  • Visual register: dashboard / data utility
  • "Forms over data" — dense input, sparse meaning
ConnectX · CRM-as-Observatory
Editorial · agent-watched · relational
  • Relationship graph is the primary surface
  • Pipeline as flow chart — pressure (age) + velocity (signal)
  • Eight named agents work continuously in background
  • Notifications optimised for fiduciary attention
  • Visual register: editorial / instrument / vellum
  • "Words over forms" — sparse input, dense meaning
Live Interactive Demo

Open the live workspace.

All eleven screens, all eight agents, the full cinematic intro, the "Tweaks" panel that lets you change AI presence between Ambient, Co-pilot, Assertive, and Autonomous in real time. React 18 with Babel-in-browser, Cormorant Garamond + JetBrains Mono inlined, runs from any static host with no build step. The same deterministic-mock discipline as Intent Canvas and Double-Blind: no API key, no backend, ship-reliable.

ConnectX — Private Banking CRM (Live)
React 18 · 11 screens · 8 agents · 4 AI levels · Cormorant + gold leaf · runs in any modern browser
Command Center · Observatory radar Pipeline · flow chart, not kanban Account 360 · relationship graph Workflow Studio · policy bands Agent Control · 8 named workers
Open ConnectX

Tip: the cinematic intro plays once on first load. Hit Cmd+K for the command palette, Cmd+. for the voice modal, or open the Tweaks panel (top-right) to switch AI autonomy mid-session. A self-contained single-file bundle (~2 MB) is also available for offline review.

AI Autonomy · Four Levels

From ambient to autonomous, with a switch the user controls.

ConnectX makes AI presence an explicit setting — not a "smartness" slider, but a governance setting that determines who decides and who reviews. The same eight agents run the same observations across all four tiers; what changes is who acts on what they find. This framework is the design contribution most worth lifting out of the case study and applying to any AI product where authority matters.

01 · Tier I
Ambient
AI works silently in the background. The RM opts in to see anything. Default for compliance-sensitive desks.
Agent COVENANT watches 47 covenants; the RM sees a single dot in the corner of the Command Center if anything breaches.
02 · Tier II
Co-pilot
AI suggests beside the RM's work. The RM decides. The default tier — most users live here.
Agent BRIEF generates a pre-meeting MAP draft. The RM accepts, edits, or rejects. The agent never sends the meeting invite itself.
03 · Tier III
Assertive
AI volunteers next actions and drafts. The RM still signs. For experienced users running large books.
Agent DRAFT pushes a finished IC memo into the RM's review queue without being asked. The RM countersigns or sends back.
04 · Tier IV
Autonomous
Agents execute within bounded policy. The RM reviews at checkpoints. Reserved for low-risk operational tasks; gated by Compliance.
Agent TICKLER auto-schedules quarterly reviews and books rooms. Anything touching risk, money movement, or client communication still requires explicit human approval.
Agent Roster

Eight named workers. Every agent has a job, a beat, and a verb.

Generic "AI assistant" framing fails in regulated finance — Compliance cannot audit a vague assistant. ConnectX names every agent, gives each a single role, and exposes their watching counts and last-fired timestamps in a dedicated Agent Control screen. Agents are workers, not features. Naming them makes them governable.

COVENANT
Credit covenant watcher
Watching 47 · Fired 12 today · "Liquidity covenant tightening 14bps below threshold for Bridgepoint."
BRIEF
Pre-meeting briefing & MAP author
Watching 18 · Fired 8 today · Drafts the meeting agenda from email + activity history.
INTRO
Warm-path & relationship router
Watching 32 · Fired 4 today · Surfaces second-degree connections for cold accounts.
KYC
Continuous KYC & sanctions
Watching 188 · Fired 2 today · Re-screens against updated SDN lists; flags 2 UBO records for human re-verification.
PULSE
Account health & churn radar
Watching 10 · Fired 6 today · "Atriom has been quiet for 89 days — sentiment 0.28, last touch a stalled proposal."
DRAFT
IC memos, term sheets, NBA
Watching 6 · Fired 11 today · Composes finished IC memos based on the latest call transcript and market state.
TICKLER
Follow-up cadence guardian
Watching 213 · Fired 19 today · Tracks promised follow-ups; flags every silent commitment older than its policy window.
FORECAST
Probabilistic pipeline forecasting
Status: training · Watching 0 · Currently held back from production until calibration meets policy threshold.
Eleven Screens · Three Movements

Practice, Intelligence, Operations.

The sidebar is organised as a magazine table of contents — three Roman-numeral movements rather than a flat list of features. Practice is what the RM does on the desk. Intelligence is what the agents do in the background. Operations is what Compliance and ops need to see. Each screen below is the live build, not a mock-up.

Screen 01 · I · Practice
Command Center

"Elena — three things are moving."

The morning desk. Markets ribbon overhead, observatory radar centre, KPI strip across, and a single open file on the right. The Co-pilot doesn't shout — it logs three observations in chronological order: PULSE on Norvel Energy, INTRO on a Bridgepoint warm path, and the named pivot for the day. The RM reads three names, not forty-seven notifications.

Command Center — Elena three things are moving — observatory radar plots 10 entities by AUM and risk, six-card KPI strip ($20.2B AUM, +$112M weighted, 2 covenant-sentiment, 3 in motion, 6 agents on duty, clear compliance), Norvel Energy file open with $3.21B AUM 41% sentiment HIGH risk, two co-pilot observations from PULSE and INTRO

Screen 01 — Command Center. Markets ribbon · observatory radar · KPI strip · Co-pilot observations stream.

Observatory radar, not list

Ten entities placed by AUM × risk on a polar plot. Tier I clients on the inner ring, Tier II on the outer. Hot ones (status: risk) glow red; expansion ones gold. The RM sees the book at a glance — not as 200 rows.

3
Three things, not 47

The hero number is "Three things are moving." Co-pilot suggests; RM picks. The "rest can wait" framing is editorial restraint applied to alerts — opposite of the typical CRM dashboard where everything competes for attention.

One open file at a time

Right pane shows the actively-tracked relationship (Norvel Energy here). Click another node on the radar; this pane swaps. Encourages depth-first reading rather than tab-fan-out.

Screen 02 · I · Practice
Pipeline

10 mandates moving through the pipeline.

Not a Kanban. A flow chart. Five stages render as horizontal bands; mandates appear as vessels with two attributes — pressure (age, red→amber→green) and velocity (AI signal, rising / stalled / new). The Co-pilot tracks both; it does not move cards for the RM. Bridgepoint Synthetic Prime shows up at $2.4B in Closing — the band visibly carries more weight than the others.

Pipeline · Flow — 10 mandates moving through the pipeline, five stages displayed horizontally with weighted gross totals ($840M Qualification, $560M Discovery, $1.19B Proposal, $1.71B Negotiation, $2.4B Closing), 10-row mandate table sorted by pressure with owner, stage, value, probability, age, and AI signal columns

Screen 02 — Pipeline · Flow. Five-band flow chart · weighted gross per stage · sortable-by-pressure mandate table.

Asymmetry is honest

One $2.4B mandate dwarfs nine others. A Kanban hides this; a flow chart shows it. Wealth pipelines aren't lead-funnel uniform — the band widths are intentional.

Pressure colour-coded

Age tinted red→amber→green per row. The Cap-Table Cleanup at 89 days (Atriom) reads as a stalled deal without the RM having to mentally compute "how old is too old".

AI signal, not AI command

Last column shows the FORECAST agent's read: rising / stalled / new. Suggestion only. The RM still moves the deal; the agent never auto-progresses a stage.

Screen 03 · I · Practice
Account 360

Acuity Holdings — relationship graph as the page.

Most CRMs hide the relationship graph behind a "Relationships" tab. ConnectX inverts: the graph is the page; the data tabs become drill-downs. Fourteen entities, seventeen edges, two live agent signals. Each node is sized by AUM and tinted by warmth (hot / warm / cool / cold). Click any to drill; the canvas remains.

Account 360 — Acuity Holdings relationship canvas with 14 entities arranged in orbital pattern (Acuity Holdings centre, plus subsidiaries Acuity Capital LLC, Treasury, IR Desk, plus people Lin Park CFO, D. Marsh Treasurer, K. Ho Counsel, J. Mendel CEO, A. Faulkner CIO, plus connection points), warmth legend hot-warm-cool-cold, recent activity feed showing CFO meeting and AGENT BRIEF action

Screen 03 — Account 360. Fourteen entities · seventeen relationships · two live agent signals · warmth-coded nodes.

Graph IS the page

Not a sidebar widget — the orbital canvas takes the full primary surface. Reduces the cost of moving between people, deals, and signals. They're all just nodes you can click.

Warmth temperature, not status

Hot / warm / cool / cold replaces the binary "active / inactive" of standard CRMs. Captures the soft state of a relationship — Lin Park is "warm" because he pushed back on the basis points last week; that's not "active" but it's not "stale" either.

Live agent signals on canvas

Two ongoing agent observations are pinned to the relevant nodes. AGENT COVENANT on Treasury, AGENT BRIEF on the IC review thread. Visible without leaving the canvas.

Screen 04 · I · Practice
Activity Inbox

"Everything moving today."

A signal stream, not an email list. Eight entries today across four categories — Agents, Humans, Priority, All — chronological with priority-coded left rule. AI items wear oxidized lavender; human items wear ivory. The right pane previews the selected entry; the action affordances stay consistent — Open Account / Reply / Defer.

Activity Inbox — Everything moving today — Today section with 3 entries (Acuity Holdings CFO meeting, Norvel Energy macro signal, Praxim Biosciences email), Yesterday section with 4 entries (Bridgepoint AGENT COVENANT, Wescroft Industries call, Atriom Software AGENT KYC, Kelmoor Logistics note), filter chips All-8 Agents-3 Humans-2 Priority-4, right pane previewing CFO Lin Park entry with quote and Open Account / Reply / Defer actions

Screen 04 — Activity Inbox. Signal stream · priority-coded left rule · agent/human glyph distinction.

Stream, not inbox

Signals — meetings, agent fires, market drops, calls, notes — are equal first-class items. The default CRM activity feed makes "added a contact" the same weight as "covenant breach"; this surface ranks by priority + recency, not by source.

Lavender for AI

Items where an agent fired (PULSE on Norvel, COVENANT on Bridgepoint, KYC on Atriom) are tinted oxidized lavender. Human-authored items stay ivory. The RM can read provenance at a glance without reading the source field.

Right-pane defer affordance

Three actions, always: Open Account, Reply, Defer. "Defer" is the meaningful choice — it pushes the item to a tomorrow queue with a reminder. Slack's "Remind me" pattern, ported to a CRM context.

Screen 05 · I · Practice
Meeting Room

Lin Park · CFO Acuity Holdings — live, 06:08 elapsed.

A live call surface with three columns. Left: the live transcript. Centre: sentiment trajectory (54% — pulse paused at 14:09 when Lin softened slightly when Wescroft was differentiated). Right: "Want this in your hearing?" stack — three reference materials Co-pilot is preparing. Bottom strip: Co-pilot wants your attention — a draft of a pricing concession the RM can show, dismiss, or resume. Workflow paused while awaiting the human.

Meeting Room — Lin Park CFO Acuity Holdings live call 06:08 elapsed — three-column layout, left live transcript with timestamps, centre sentiment trajectory chart at 54% with annotation about Wescroft differentiation, right Want this in your hearing stack with three prep materials (pricing concessions, Wescroft comparison, audit committee timing), bottom strip Co-pilot draft of pricing concession with Show me / Dismiss / Resume buttons

Screen 05 — Meeting Room. Live transcript · sentiment trajectory · Co-pilot prep stack · workflow-paused affordance.

Sentiment trajectory, not score

The sentiment is plotted over the call duration with the inflection points annotated. "Up from start" framing makes the call into a tracked story rather than a single number. RM can see when something shifted, not just where it landed.

📌
"In your hearing" stack

Right column is what Co-pilot has prepared in case the RM needs it. Three items queued, each with a Prime Me / Dismiss action. Reference is staged but not pushed onto the screen mid-call.

Workflow paused — awaiting you

The bottom strip shows a draft Co-pilot wrote (pricing concession). It is staged but not sent. The RM gets explicit Show me / Dismiss / Resume controls. AI prepares; human signs.

Screen 06 · I · Practice
Forecast · Workbench

Where the portfolio is going.

Agent FORECAST runs 4,000 scenarios nightly. Confidence intervals shown — ask why for any line. AUM trajectory plotted across eight quarters with a grey "today" anchor and a probability cone extending forward. Below, two surfaces: "What moves the number" with positive and negative drivers ranked, and "Ask agent · what-if" — a free-text scenario field that returns a re-run.

Forecast Workbench — Where the portfolio is going — four KPIs (Base case $9.4B, P10 Bear $7.9B, P90 Bull $11.2B, Confidence 74%), AUM trajectory line chart over 8 quarters Q3 25 through Q3 27 with NOW marker and probability cone, drivers panel showing Wescroft Capital expansion mandate +$420M, Bridgepoint synthetic prime closure +$280M, Norvel KYC freeze drag -$130M, Atriom KYC freeze drag -$95M, Halo Ventures cross-sell custody +$140M, plus Ask agent what-if scenario panel with example query about Fed cuts 50bp

Screen 06 — Forecast Workbench. Cone-not-point estimates · driver attribution · what-if scenario field.

Cone, not point

The grey shaded area is the P10–P90 confidence band. Point-estimate forecasts ("$10.4B by Q4") hide the model's uncertainty. The cone forces the reader to see both expected value and width — and the agent's confidence (74%) is shown alongside.

±
Drivers ranked, not aggregated

Why is the number what it is? Five drivers shown with explicit dollar contribution. Two positive (Wescroft expansion, Bridgepoint closure), two negative (Norvel + Atriom KYC freeze drag). RM gets the shape of the number, not just the number.

?
"Ask agent" what-if surface

Free-text scenario input ("What if Norvel churns AND the Fed cuts 50bp in September?"). Agent FORECAST re-runs against the modified assumption and returns the new cone. Median outcome shifts visible inline.

Screen 07 · II · Intelligence
Agent Control Room

Eight agents on duty.

Watch what each agent is doing, set guardrails, intervene when needed. Every action is signed and audit-ready. Eight cards, one per agent. Each card shows status (active / review / training), actions today, precision-30d (calibration), last fired, and the most recent action sample. The KYC card has two items pending Compliance approval — Review / Approve actions are exposed inline.

Agent Control Room — 8 agents on duty — eight cards in 4x2 grid, COVENANT credit covenant watcher with 12 actions today and 94% precision, BRIEF pre-meeting briefing with 8 actions and 91% precision, INTRO warm-path router with 4 actions and 86% precision, KYC continuous KYC sanctions with 2 actions and 99% precision plus REVIEW APPROVE buttons for 2 pending items, PULSE account health with 6 actions and 88% precision, DRAFT IC memos with 11 actions and 92% precision, TICKLER follow-up cadence with 19 actions and 97% precision, FORECAST probabilistic pipeline with 0 actions and TRAINING status

Screen 07 — Agent Control. Eight named agents · status / actions / precision / last fired · inline approve affordance for pending items.

Named, not generic

"AI assistant" is unauditable. COVENANT, BRIEF, INTRO, KYC, PULSE, DRAFT, TICKLER, FORECAST — each has a single role, a beat, and a verb. Compliance reviews each agent's policy without scanning prompts.

%
Precision-30d as calibration

Each agent shows a rolling 30-day precision (true positives / total fires). FORECAST is in "training" status — Compliance has held it back from production until calibration crosses policy threshold. Visible governance.

Approve inline, not in a queue

KYC has two re-screen items pending after an OFAC update. Review / Approve buttons live on the agent's card itself — no separate "approval queue" page. The decision happens where the context is.

Screen 08 · II · Intelligence
Workflow Studio

"How an account is born."

A visual builder for the onboarding flow. Compliance gates are non-negotiable; agent steps are bounded by policy. Last run: 14m, zero manual interventions. Three views — Build (canvas), Runs (history + duration distribution), Policy (gate register). Each view is the same workflow seen through a different stakeholder's eye.

Workflow Studio Build view — canvas with 10 nodes including Lead created trigger, AGENT ENRICH, Compliance gate, Risk officer human review, If high-risk condition, Parallel 3 agents (INTRO BRIEF MAP), AGENT DRAFT, Final approval gate, Account opened action, AGENT BRIEF — connected with orthogonal edges including parallel branch and if-high backward edge routed via bottom-to-top path, right inspector showing Parallel 3 agents details with run stats 1.2s 99.2% success 412 success count, flow control panel with EDIT and LOGS buttons

Build view — canvas with grid · 10 nodes · routed edges · selected-node inspector · flow control footer.

Workflow Studio Runs view — three KPIs (412 runs / 30d, Success 94.2% / 412, Halted 12 m 40s / 100), duration distribution histogram across 1m to 6m+ buckets with peak at 3m, recent runs table with 5 entries showing Atriom Capital Northbridge Energy Caldera Aerospace Wescroft Industries Lumen Pharma with run IDs durations and rate columns, right inspector with Wescroft Industries detail Lead created Started 2h ago Halted at step 3 fixed approval pre-flagged a coverage gap human decision halts processing, with REGULATE and FULL TRACE actions

Runs view — duration distribution · 30-day success rate · halted-run trace with reason.

Workflow Studio Policy view — Why these gates section explaining policies are walls workflow lives between, policy table with 5 entries (Compliance gate / Tier I, Risk-DD threshold / Caldwell, Agent autonomy bounds / Caldwell, Human review SLA / Operations, Audit trail retention / Compliance), right inspector showing Compliance gate Tier I detail Locked Compliance gate I cannot be loosened applied to 4 nodes including Final approval, with REQUEST CHANGE and HISTORY actions

Policy view — gate register · who owns what · request-change vs history audit trail.

Agents work inside gates

The vertical band on the canvas marks the policy zone — Compliance gates are non-negotiable walls; agent steps are bounded by them. Visible architecture, not hidden config.

Three views, one workflow

Build is for the architect. Runs is for the operator. Policy is for Compliance. Same data, three reads. No "compliance dashboard" sold separately — it's the same source.

Halted-run trace is a feature

When the flow stops mid-run (Wescroft's Northbridge Energy halted at Risk Officer review), the run history surfaces why, not just that. The decision is logged at the stopping node, not buried in a JSON.

Screen 09 · III · Operations
Onboarding · KYC

Atriom Capital · Tier I — continuous KYC, not one-time form.

Last refresh 6h ago. Two UBOs flagged for re-verification after SDN list update. Five-step status strip across the top: Identity verified · Beneficial ownership 2 needs you · Source of wealth complete · Sanctions screen complete · Final risk decision pending. Below, the UBO list — 14 verified, 2 flagged. The flagged ones get a clear Re-Verify call to action; the verified ones stay quiet.

Onboarding KYC — Atriom Capital Tier I — Continuous KYC last refresh 6h ago 2 UBOs flagged for re-verification after SDN list update — five-step status strip Identity verified COMPLETE / Beneficial ownership 2 NEEDS YOU / Source of wealth COMPLETE / Sanctions screen COMPLETE / Final risk decision 5 PENDING — UBO list with 5 entries showing James Whitcombe Founder 32% UBO with Name match in OFAC update 91% confidence flagged RE-VERIFY, Margot Whitcombe Director 18% UBO VERIFIED, Atriom Trust BVI Holding 28% with New jurisdiction risk score change BVI re-rated flagged RE-VERIFY, Petros Vasiliou Co-founder 12% VERIFIED, Employee Trust Pool 10% VERIFIED, with AUDIT LOG button

Screen 09 — Onboarding · KYC. Five-step status · 14 UBOs verified · 2 flagged for re-verification · per-row audit affordance.

KYC isn't a one-time form

SDN list updates trigger automated re-screen. The flagged UBOs are a continuous-KYC artifact, not an onboarding artifact. The UI surface acknowledges that with "needs you" language.

Confidence on the flag, not just the flag

"91% confidence (homonym likely)" — agent KYC's read on its own match. Lets the Compliance officer see uncertainty inline. Reduces false-positive review fatigue without hiding the flag itself.

📜
Audit log is one click

Top-right Audit Log button exports the full record (KYC events, sanctions screens, UBO changes, document refreshes) for this entity. SOC-2 / SR-11-7 / FATF expectation: every screen has a path back to the file.

Screen 10 · III · Operations
Compliance · Cockpit

"The portfolio · seen through risk."

Compliance Officer's separate surface — not the RM's view dimmed. Six top-line counters at the top (0 open findings, 188 KYC current, 6 KYC expiring 30d, 2 sanctions hits, 14,302 audit signatures, 2,847 AI actions reviewed). Centre: a 5×5 portfolio risk matrix (likelihood × impact) with cell counts and severity tinting. Right: an "every action, signed" running log — agent actions chronologically with timestamps and approver names.

Compliance Cockpit — The portfolio seen through risk — 0 open findings, 188 KYC continuous, every AI action signed and immutable — six KPIs (Findings open 0, KYC current 188, KYC expiring 30d 6, Sanctions hits 2, Audit signatures 14302, AI actions reviewed 2847), centre 5x5 portfolio risk matrix with likelihood Low to Critical on Y-axis and impact Low to Critical on X-axis with cell counts tinted by severity, right Audit log Every action signed with 5 entries showing AGENT KYC Re-screened Atriom UBOs against OFAC update / Approved Bridgepoint covenant amendment / AGENT BRIEF Generated Norvel courtesy memo 3 variants / AGENT INTRO Searched warm path to Wescroft board / Logged call M Caldwell Acuity Lin Park / AGENT DIGEST Composed daily brief 14 sources, with EXPORT AUDIT PACK button

Screen 10 — Compliance Cockpit. Six top-line counters · 5×5 risk matrix · running audit log · one-click export-audit-pack.

Separate surface, same source

Compliance does not get a "filtered RM view" — they get their own first-class screen. Mixing the two audiences dilutes both. But the data backend is shared; export pulls from the same audit ledger the RM's actions write to.

5×5 likelihood × impact matrix

Standard risk-management chart, rendered honestly. Each cell shows count + severity tint. Critical-high cell glows red; low-low cell stays muted. The CRO can read the book in two seconds.

"Every action, signed"

The right pane scrolls every agent action chronologically — agent name, action verb, target, approver. Cross-references back to the originating screen. Export Audit Pack button packages the whole trail.

Screen 11 · III · Operations
Mobile Companion

The observatory, shrunk.

Phone-shaped surface for the road. Today's three names, the agent brief, the next two meetings, the voice command palette. Mobile is not "the same screens but smaller" — it's a different read of the same data, optimised for a five-minute taxi between meetings. Image forthcoming — currently in build.

Mobile screen visual — coming next pass.

Voice · The Universal Surface

"Speak as you would to a colleague."

Voice is the AI surface that works at every autonomy tier. The RM presses Cmd+. anywhere in ConnectX and dictates a sentence. The agent parses it into structured actions, shows the interpretation back as a typed diff, and waits for approval. Update Acuity Holdings — change risk tier to medium-high and flag covenant 11 for review by Friday. Two actions. Confidence 96%. Audit signed in 3.4 seconds.

Voice modal — Speak as you would to a colleague — listening state with microphone icon and italic prompt, dictated sentence shown verbatim Update Acuity Holdings change risk tier to medium-high and flag covenant 11 for review by Friday, parsed actions panel with Confidence 96% showing UPDATE Acuity Holdings risk tier Medium to Medium-High and FLAG Covenant 11 review by Fri Apr 30 routed to D Iyengar, APPLY BOTH gold button and CANCEL button, AUDIT SIGNED 3.4s confirmation in bottom right

Voice command modal · live parsed-action preview · single-click apply with audit signature in 3.4s.

Diff before commit

Voice doesn't fire actions blind. The parsed interpretation appears as a typed action diff ("Medium → Medium-High") with confidence band. RM reads, then decides Apply Both or Cancel. Same model as Intent Canvas — typed artifact between human and AI.

⌘.
Cmd+. anywhere

Voice is summoned from any screen — Command Center, Account 360, Meeting Room. Doesn't require navigating to "Voice Mode". The modal floats above the current context; the RM returns to the same place after dismissal.

Audit signed in 3.4s

The footer countdown shows the agent's confidence interval and a signed hash for the action. Even voice-issued commands write to the same audit ledger as keyboard-issued ones. No back door for the AI surface — every action accountable.

Visual DNA

Editorial register over enterprise tropes.

The visual brief was Hermès campaign films and FT Weekend titles, not Salesforce Lightning. Cormorant Garamond carries display, italics carry voice, JetBrains Mono carries data. Gold leaf is the only saturated colour and is used like jewellery — single accent, never wallpaper. AI moments wear oxidized lavender, distinct from gold so users can read agent presence at a glance.

Obsidian → Vellum
Page is midnight ink (#08070a). Light surfaces are warm ivory (#f4ecdc). Generous spacing — magazine-grade, not dashboard-grade.
Gold leaf · single accent
#c4a264 used like jewellery. Active sidebar item, key figure, hover state. Never a fill colour for surfaces.
Oxidized lavender · AI
#b9a8d8. Reserved for moments when an agent is speaking — observation strips, agent brief, AI tooltip. Distinct from gold so authority and observation read separately.
Authenticity Boundary

What ConnectX is not.

Concept-quality work earns trust by stating its boundaries. ConnectX is a research artifact, not a shipped product. Reviewers should read it accordingly.

  • Not shipped to a real bank. No production user has ever touched ConnectX. The data is synthetic, the persona is fictional, the agent fires are deterministic mocks.
  • Not a Salesforce competitor pitch. ConnectX is a design exploration, not a product strategy. The "CRM-as-observatory" framing is a UX position, not a go-to-market claim.
  • Not a real LLM integration. Agent outputs are scripted. There is no RAG, no prompt chain, no actual model call. The interesting work is in the surface, not the inference.
  • Not compliance-reviewed. A real deployment would require Legal, Compliance, Risk, and Security sign-off on every agent's policy bounds. The authority levels framework is a starting position for that conversation, not a substitute for it.
  • Not opinionated about which bank. The visual register fits Geneva (Pictet / Lombard Odier), London (Coutts / Rothschild), or Asia (Bank of Singapore / Julius Baer Asia) equally. It is intentionally not a UBS-clone or a JPM-clone.
  • Not a Senior PD interview prop. ConnectX exists because the design problem is interesting — private banking CRMs are genuinely worse than they should be. If a bank wants to talk about building one, separate conversation.
Portfolio Threads

How ConnectX connects to the rest of the work.

Every case study sits on multiple threads — recurring problems, methods, or surfaces that run across the portfolio. ConnectX touches three: agent governance, editorial voice, and the regulatory routing of UI defaults.