Chat Modes
How the floating chat widget changes behavior across deal, portfolio, and prospecting workspaces — including tools, context, web toggles, approvals, and persistence.
The floating chat widget runs in one of three modes depending on where you open it. Each mode has its own backend route, system prompt, tool set, and default web toggles. The widget detects mode automatically from the page you are on; you do not switch it manually.
The Three Modes at a Glance
| Mode | Where it appears | Backend route | Primary purpose |
|---|---|---|---|
| Deal | Inside any deal workspace tab (/deals/[id]/...) | POST /api/assistant/chat | Analyze, draft, and update one deal |
| Portfolio | /deals and other org-level pages | POST /api/assistant/portfolio-chat | Compare and analyze across the pipeline |
| Prospecting | /prospecting and mandate dashboards | POST /api/assistant/prospecting-chat | Triage prospects against active mandates |
If a page does not pass a mode prop, the widget does not render. On deal routes the widget remounts with a fresh state when the dealId changes — there is no cross-deal leakage in conversation history.
Deal Mode
Deal mode is the most capable surface and the only one with write access to deal data. It is bound to the current deal: the system prompt includes the deal name, visible page data, any custom deal-level instructions, and any items you have @-mentioned.
Tools Available
Tools are organized by domain. A broader domain reference lives in Tool reference; below is the high-level coverage.
- Schema, Review, and tenants: read deal data, read the canonical Review queue, act on any Review decision including data conflicts, update fields, add or delete tenants, update property info, mark documents reviewed, and run the evidence-backed queue resolver
- Documents — search documents (
searchDocuments, deal-scoped only), list, reprocess, delete - Valuation — read the model, run sensitivity, update assumptions and OpEx, export to Excel
- Health — read summary and issues, create or resolve issues, run on-demand health analysis
- Research and market data — Gateway web search (when enabled), market reports, papers, narratives, economic conditions, comparable properties (deal mode is the only place comps are available)
- Portfolio comparison from inside a deal —
compareDealMetrics,searchAcrossDeals - Tasks and workflow — deal task CRUD, transaction-graph queries, intake / lease / legal / diligence / debt / closing specialists
- Memory — read the deal memory brief and notebook, search prior notes, compare the deal to reviewed institutional patterns, and propose approval-gated memory entries
- Overview JSON Render (Overview tab only) — list saved custom dashboard widgets, create new widgets from explicit creation prompts or the Overview dashboard button, and edit or rebuild existing widgets by id from explicit edit prompts. Create and edit persist immediately (no Allow / Deny). Lease rollover plus DSCR timeline requests use the deterministic
system-lease-rollover-dscrtemplate.
Governed Writes
The following writes are governed. Base/scenario scalar valuation changes, capital-stack replacement, destructive actions, and other attended tools require explicit Allow / Deny approval. Eligible routine writes can execute under an organization-approved autonomy policy:
actOnReviewItemupdatePropertyInfoupdateFieldaddTenantaddOperatingStatementmarkDocumentsReviewedresolveAllConflictsautoResolveReviewQueueexecuteDealCleanupCommanddeleteDocumentdeleteTenantdeleteSuiteInventoryreprocessDocumentupdateAssumptionupdateScenarioAssumptionupdateTenantAssumptionupdateOpexupdateValuationParamssizeDebtsizeMezzapplyLeaseIntelligencePackageupdateCapitalStack- deal work-queue mutations such as
createDealTask,updateDealTask,completeDealTask,snoozeDealTask, andscheduleTaskReminder recordNotebookEntryproposeInstitutionalMemoryPatternrecordHistoricalDealOutcome
When two or more direct approvals are pending at once, a bulk approval bar appears so you can review and confirm them together. Some decisions are never part of a batch click: attesting a release blocker, accepting diligence risk, a Review action covering more than one item, and anything destructive or externally visible. Those show a count of how many need individual attention, and Confirm all safe skips them so you can confirm each one on its own. Deny all still denies everything. Single approvals always show inline.
Approval Modes for the Review Queue
Deal mode has one setting that changes when the assistant asks. Open Session settings in the chat header, then Approval mode, and choose one of three:
| Mode | What it automates |
|---|---|
| Manual approval | Nothing. Every Review action waits for your Allow click. This is the default. |
| Auto-approve routine Review | Confirming a source-backed value, dismissing an item, answering a clarification, and marking a document reviewed. Corrections, conflicts, source requests, attestations, and risk acceptances still ask. |
| Full review automation | Every Review queue action, bulk conflict resolution, and the evidence-backed queue resolver. Attestations and risk acceptances are included, each recorded with the assistant's written reason on the decision and in the deal's audit trail. |
Two things stay true in every mode:
- A mode is a request, not a permission. Your organization's autonomy policy decides what the assistant may do without asking, and a mode only picks which part of the Review queue that permission covers. If your organization is set below Act & report, the assistant still asks whichever mode you pick. The panel shows your organization's current setting under the picker so you can see why. An org admin changes it in Settings, under Agent autonomy.
- This picker automates only Review queue actions. Organization-approved autonomy can separately permit the eligible routine writes listed above. Release approval, IC decisions, converting a prospect to a deal, sharing externally, destructive cleanup, and sandbox analysis always ask, whatever the mode.
The mode is remembered in your browser and applies to the chat widget on every deal, not just the one you set it on. The full-page assistant at /deals/[id]/assistant has no approval mode and is always manual.
Web Toggles
Deal mode is the only mode where all four web-tool categories are available:
- Web search — Vercel AI Gateway Parallel Search (general web search when the toggle is on)
- Market data — metro economic and commercial-market metrics (cap rates, occupancy, rents, demographics, employment) plus national macro, across ~1,000 US metros
- Research — academic papers and structured research sources
- Comps — comparable-property discovery (deal mode only)
The four standard categories above are on by default in deal mode. Turn one off and the assistant suspends those tools for the rest of the session — the model is informed in the system prompt that the category is unavailable.
Two Corbis categories are separate: Economic Insight (FRED) is on by default in deal mode and sends series names or IDs through Corbis to query public FRED data; Deep Research (Corbis) is off by default and sends your query text to Corbis for multi-engine research. Both require an available Corbis connector; if the deployment has not configured it, the switch stays disabled.
@-Mentions
Type @ to autocomplete:
- Documents in the current deal (by name)
- Team members in the deal team (by name and role)
The mention text appears in your message for readability, but the structured reference is sent separately to the backend so the assistant can ground its response on the correct artifact without parsing the chat string.
Persistence
Deal-mode conversations are saved per deal in your browser (equire-chat:v1:{dealId}). Server-side persistence is per-session — when you start a new conversation, a new session ID is generated. Switching deals unmounts the widget and resets state.
Portfolio Mode
Portfolio mode is analysis-first. It is for cross-deal analysis: comparing pipeline metrics, finding deals that match a query, surfacing aggregate analytics, and asking what the organization has learned across prior deals. It has no document-chunk search and no direct deal-field write tools.
Tools Available
- Portfolio —
listAllDeals,getDealSummary,compareDealMetrics,searchAcrossDeals,getPipelineAnalytics - Search and market — web search, market data, market trends, papers, metric definitions
- Memory — read institutional patterns, compare a deal profile to reviewed memory, retrieve deal notebooks when a deal id is known, and propose approval-gated memory entries
Approval Gates
Memory write tools such as recordNotebookEntry, proposeInstitutionalMemoryPattern, and recordHistoricalDealOutcome require Allow / Deny approval before they run. Portfolio mode does not expose direct field, tenant, document, or valuation mutation tools.
Web Toggles
Web search, market data, and research are on by default. Comps is hidden — it is a property-level concept and only useful in a deal context.
@-Mentions
Not supported. Portfolio mode has no per-deal documents or team to mention.
Persistence
A single global portfolio conversation is saved to your browser (equire-chat:v1:portfolio). Unlike deal mode, there is no per-session split.
Prospecting Mode
Prospecting mode is for triaging the prospect inbox against your active mandates. It can read mandate state and prospect sources, generate briefs, and queue up snooze / tag actions for your approval.
Tools Available
- Prospecting reads —
listMandates,searchProspects,getProspectBrief,listProspectSources,compareProspects,searchMandateMarkets,getMandateHealth,getProspectOwnerPath,listSnoozedProspects,getDigestPreview,prepareScreeningMemoExport - Prospecting writes (approval-gated) —
snoozeProspect,addProspectTag,dismissProspect,attachProspectSourceUrl,updateProspectSource,runProspectResearchAction,convertProspectToDeal,runSourcingProfile,launchScoutReview,dispatchBackgroundJob - Search and market — web search, market data, papers, market trends, metric definitions
Approval Gates
Prospecting write tools require Allow / Deny. As with deal mode, the bulk approval bar appears at two or more pending.
Web Toggles
Web search, market data, and research are on by default. Comps is hidden by design — even if a stale client sends a comps flag in the request, the prospecting backend drops it before it reaches the model.
Context the Assistant Sees
In addition to the standard prompt, prospecting mode appends the current view filters: how many active mandates you have, how many prospects are in the ready state, and any readiness / source / tag filters in effect. This lets the assistant ask clarifying questions like "Do you want me to skip the dismissed prospects?" without you having to restate the filter.
Persistence
A single global prospecting conversation is saved to your browser (equire-chat:v1:prospecting). Server-side persistence is org-scoped and not split per session.
Cross-Mode Behaviors
These behaviors are the same in every mode.
Mobile Gestures
- Pull down to close — drag the panel down by 80px from normal size, or 120px from expanded size
- Pull up to expand — drag the panel up by 70px to switch to the larger preset
Gestures are touch-only; on desktop, use the resize handle or the close button.
Resize Handle
Desktop only. The handle in the top-left corner is keyboard-accessible (Tab to focus, then Enter or Space to reset to the default size). Drag to resize within the size presets — the widget does not allow arbitrary widths so it can stay readable on every viewport.
Empty State
Each mode shows a contextual empty state with four suggested prompts. The suggestions reflect that mode's strengths — deal mode suggests deal analysis, portfolio mode suggests pipeline comparisons, prospecting mode suggests readiness and ownership questions.
Bulk Approval Bar
When two or more approval-gated actions are pending, a bar appears above the input. You can clear them all in one action after reviewing. With a single pending approval, only the per-tool Allow / Deny is shown.
Where to Go Next
- For the full list of tools available in each mode, see Tool reference.
- For how the assistant routes complex requests to specialist agents, see Agents.
- For which model handles which mode and what data-handling guarantees apply, see Models and routing.
Last updated on