Patterns

PatternsToggle SidebarNavigateSeller PrepProcess IntelligenceAIOutcomesSecurityTeamExamplesDrivers‑based financial model from CIMBuyer universe with tags & contactsDraft CIM sections from documentsCustomer churn & cohort analysisIC memo with citationsLinksGuidePricingLinkedInXLoginCreate accountToggle SidebarPatternsPrepare CIMs FastDraft banker‑grade CIMs 70% faster—with drivers‑based models and a 200+ buyer universe.Research & analysis: competitive landscape, market sizing, LBO, comps, positioning.CIM draft in 3–4 weeks60–80 slidesDrivers‑based model200+ buyer universeTalk to our teamSeller PrepProcess IntelligenceIntroducing PatternsExamplesExplore common sell‑side tasks. Click to open a live example.Drivers‑based financial model from CIMGenerate buyer universe with tags & contactsDraft CIM sections from source docsCustomer churn & cohort analysisIC memo from CIM with citationsSeller PrepProcess‑ready materials, buyer management, and analytics—tuned for lower mid‑market timelines.Deliverables• Teaser, CIM draft (60–80 slides) with citations• Financial model — drivers‑based revenue; bottoms‑up cost by drivers; sensitivities• Customer & operational analytics and KPIs• Buyer universe (200+ names) with tags & contacts• Dataroom index + diligence request listTalk to our teamTimelineWeek 0Kickoff, data & style intakeWeek 1Discovery, data ingest, early analyticsWeeks 2–3Model build, KPI packs, buyer universeWeek 4CIM draft & process readinessProcess IntelligenceTurn buyer interactions into actionable intelligence—weekly process memos, Q&A triage, and bidder analytics.Deliverables• Outreach waves & IOI tracker, bidder analytics & heatmaps• Take buyer/banker call transcripts → extract insights → weekly process memos• Q&A triage and answers (draft responses, coordinate owners)How it runsInputsOutputsCadenceBuyer/banker call transcripts, email threads, Q&A questionsWeekly memo (sentiment, risks, next actions), FAQ/Q&A log, bidder heatmapWeeklyTalk to our teamHow It Works1IngestConnect XLSX, PPT, PDFs, data rooms, and SQL. Bring your templates.2ExecuteThe agent follows your playbooks to extract, compute, and assemble pages with cited sources.3DeliverOutputs flow back to Excel, PowerPoint, and CRM with diffs and reviewer gates.AIAn agentic research platform built for banker outputs—CIM authoring, buyer tagging, KPI packs—with Excel and PowerPoint write‑back.CIM Authoring & Doc IntelligenceDrag/drop CIMs and source docs; extract, cite, and assemble sectionsWatch demoExcel/PPT Write‑BackBidirectional Excel sync, tracked changes, PowerPoint slide exportWatch demoBuyer Research & TaggingMarket/company research, enrichment, and buyer tagging logicWatch demoPython & Database KPIsDrivers‑based KPIs, cohort/concentration analysis from SQL and filesWatch demoMemo/Notebook ScaffoldsDraft IC or weekly memos with tables, charts, and citationsWatch demoMemory & AutomationAI memory for custom formats, multi-step workflows, autonomous executionWatch demoPatterns platform interfaceOfferingsPick the path that fits your team—done‑for‑you sprints or software you drive.Sell‑Side Sprint$15k• 60–80 slide CIM draft, drivers‑based model, 200+ buyers• Compress 6–8 weeks to 3–4View details →Process Intelligence$5k/mo• Weekly process memos, Q&A triage, bidder analytics• Keep leadership aligned without adding headcountView details →Outcomes & Capacity30+ hrsSaved per deal on average70%Faster CIM creation$200K+Annual analyst cost savingsZeroMissed deadlinesSee how agent assistance changes throughput. Adjust the parameters below to understand capacity gained and extra deals you can run with the same team.Hours per dealTypical range: 10–40hDeals per monthActive or diligence‑stageAssistance level (%)Work handled by agentReset to defaultsMonthly Hours120Baseline analyst hoursHours Saved36Capacity gainedExtra Deals2.6Additional possibleCalculator estimates vary by deal scope, templates, and review processes.Traditional vs Agentic (Sell‑Side)See the difference between traditional deal execution and our agentic approach.OLD vs NEWInfinite scale,expert validation,instant impact. Traditional Deal TeamPatterns: Agentic Deal ExecutionSpeed to deliverablesWeeks to workforce—Manual research and data entry—Slow Excel modeling and formatting—Multiple revision cyclesMinutes to live—Bring your existing templates—Instant process execution with natural language—AI-powered research and analysisQuality & accuracyHuman error prone—Manual data transcription mistakes—Inconsistent formatting and analysis—Limited time for thorough reviewExpert accuracy—AI + human verification loop—Every decision audited with sources—Consistent output quality across dealsScale & capacityCapacity-constrained delays—Slow turnarounds during peak periods—Seasonal resource bottlenecks—Limited parallel processingInstant speed at infinite scale—Operate 24/7 without breaks—Handle unlimited complex tasks in parallel—No capacity constraints during deal flow peaksCost structureFixed labor overhead—Expensive idle capacity during slow periods—Inflexible cost structure—High hiring and training costsPerformance pricing—Pay only for results delivered—Scale without adding headcount—Predictable per-deliverable pricingSpeed to deliverablesWeeks to workforce—Manual research and data entry—Slow Excel modeling and formatting—Multiple revision cyclesMinutes to live—Bring your existing templates—Instant process execution with natural language—AI-powered research and analysisQuality & accuracyHuman error prone—Manual data transcription mistakes—Inconsistent formatting and analysis—Limited time for thorough reviewExpert accuracy—AI + human verification loop—Every decision audited with sources—Consistent output quality across dealsScale & capacityCapacity-constrained delays—Slow turnarounds during peak periods—Seasonal resource bottlenecks—Limited parallel processingInstant speed at infinite scale—Operate 24/7 without breaks—Handle unlimited complex tasks in parallel—No capacity constraints during deal flow peaksCost structureFixed labor overhead—Expensive idle capacity during slow periods—Inflexible cost structure—High hiring and training costsPerformance pricing—Pay only for results delivered—Scale without adding headcount—Predictable per-deliverable pricingAccess & SecurityWhere it runsCloud, private cloud (VPC), or fully air‑gapped on‑prem. Pick the environment that matches your firm’s requirements.Which modelsUse leading cloud models (GPT‑4, Claude, Gemini), dedicated private endpoints, or open‑source models for maximum control.Controls & complianceSOC 2 Type II and ISO 27001 programsEncryption in transit and at restSSO/SAML/SCIM, RBAC, least‑privilegeCustomer‑managed keys (Enterprise), data residency optionsAudit logs and environment isolationNo data retained beyond processing; standard 90‑day retention, configurable on EnterpriseTeamEvery M&A deal generates the same grunt work: comp tables, buyer lists, LBO models, IC memos. Junior analysts spend 60-80% of their time on repetitive tasks that could be automated.We're building the execution agent that eliminates this bottleneck. Patterns handles the heavy lifting so your team can focus on judgment, relationships, and deal-making—the work that actually drives value.Led by operators who've lived through the late nights building models and know exactly where AI can transform deal execution.Ex-Investment BankerWhat you'll do: Shape our product roadmap by translating real deal execution pain points into AI-powered solutions. Own client relationships with PE/IB teams, design workflows that eliminate grunt work, and ensure our automations actually work in practice.What we're looking for: 3-7 years at a top-tier bank or PE shop. You've built countless models, know every Excel shortcut, and can spot a bad comp table from across the room. Bonus points if you've automated parts of your workflow or wished you could.Why you'll love this: Finally build the tools you always wished existed. Work with cutting-edge AI while solving problems you've lived through. Help other analysts escape the 3am model-building grind.AI EngineerWhat you'll do: Build production AI systems that handle real financial data and generate analyst-grade deliverables. Design LLM workflows for document extraction, financial modeling, and research automation. Own the technical architecture that makes AI reliable for high-stakes decisions.What we're looking for: Strong Python/ML background with production LLM experience. You understand both the power and limitations of current AI models. Experience with financial data, Excel automation, or document processing is a huge plus.Why you'll love this: Work on AI applications that actually matter—helping smart people escape tedious work. Build systems that handle billions in deal value. Shape the future of how finance teams operate.Ready to Join?We're looking for people who've felt the pain of manual deal execution and want to build the solution. If you've ever thought "there has to be a better way," let's talk.Apply to Join Our TeamHelp us eliminate the grunt work that's holding back every deal team.FAQHow is this different from adding more analysts to the team?What sources do you support?Who reviews outputs?Can we use our templates?Is data used to train models? --- PatternsToggle SidebarPricingValue PropositionSell-Side ServicesSoftware PlansACU ModelOnboardingSupport & TermsNavigation← Back to HomeLinksLinkedInXSign inTalk to our teamToggle SidebarPatternsSell‑Side M&A Execution PlatformSeller prep and process intelligence for banker‑grade outputs—CIMs, drivers‑based models, and buyer analytics—delivered fast.CIM draft in 3–4 weeks60–80 slidesDrivers‑based model200+ buyer universeTalk to our teamSeller PrepProcess IntelligenceTwo Ways to 10x Your Deal Execution SpeedChoose how you want to accelerate your M&A workflow—we handle the work for you, or you use our AI tools directly.IMMEDIATE ROIDone-For-You ServicesOur research analysts use AI to generate your outputsTasks that take 24 hours → completed in 1 hourTasks that take a week → completed in 1 dayYou review and approve, we handle executionBank-grade quality with experienced analyst reviewNo training required—immediate productivityPopular Services:• Sell-side sprint (CIM + model + buyers): $15K• Process intelligence: $5K/monthTalk to our teamDo-It-Yourself AIYour team uses our AI platform directly$800 per user (20 ACUs per user)Full control over your workflow and data100 Agent Compute Units (ACUs) includedScalable per-user pricing, unlimited viewersRequires some training and onboardingPer User (20 ACUs):• ~8 complete CIMs per month• ~5 buyer universes per month• ~20 comps refreshes per monthTalk to our team30+ hrsSaved per deal on average70%Faster CIM creation$200K+Annual analyst cost savingsZeroMissed deadlinesWhat Our Clients Say"We cut seller prep from 6–8 weeks to 3–4. We had a 60–80 slide CIM draft, drivers‑based model, and a 200+ buyer universe ready to go—our team focused on strategy instead of grunt work."— Managing Director, Mid‑Market Investment Bank"The buyer universe generation alone saves us 40 hours per deal. Our analysts can focus on relationship building instead of research."— VP, Bulge Bracket M&A"ROI was immediate. We're closing 50% more deals per quarter because we're not bottlenecked by manual work anymore."— Partner, Boutique Advisory FirmServices — Sell-Side PackagesProcess-ready materials, buyer management, and analytics—tuned for lower mid-market timelines.1) Sell-Side Prep Sprint$15,000~3–4 weeksDeliverables• Teaser, CIM draft (60–80 slides) with citations• Financial model — detailed revenue build with key drivers; bottoms‑up cost model by drivers• Customer & operational analytics and KPIs• Buyer universe (200+ names) with tags & contacts• Dataroom index + diligence request listTimelineWeek 0Kickoff, data & style intakeWeek 1Discovery, data ingest, early analyticsWeeks 2–3Model build, KPI packs, buyer universeWeek 4CIM draft & process readiness2) Process Intelligence$5,000/monthDeliverables• Outreach waves & IOI tracker, bidder analytics & heatmaps• Take banker/buyer call transcripts → extract insights → weekly process memos• Q&A triage and answers (draft responses, coordinate owners)How it runsInputsOutputsCadenceBuyer/banker call transcripts, email threads, Q&A questionsWeekly memo (sentiment, risks, next actions), FAQ/Q&A log, bidder heatmapWeeklyAdd-ons (custom): QoE-lite red-flag review; fairness/solvency opinion coordination; RWI broker introductions; post-deal integration playbooks.Software PlansChoose the deployment model that fits your firm's requirements and scale.TRY FREECloud$800/userSimple per-user pricing. Each user gets 20 ACUs. Designed for bankers running sell‑side workflows.20 Agent Compute Units (ACUs) per userPer-user pricing (analysts to managing directors). Unlimited viewers100 GB secure file storage (encrypted at rest)Data warehouse connectors: BigQuery, Snowflake, PostgresExcel integration (bidirectional sync), PowerPoint export, Python accessDocument intelligence and database connections for researchSupport: Email, Slack, Teams + dedicated support analystBaseline onboarding includedExample: 5 users = $4,000/month (5×$800) + 100 ACUs totalOverage: $25 per additional ACU (billed monthly)Contracts: Monthly or discounted annual with 3-month grace periodEnterpriseCustomFor banks that need scale, custom security, or private deployments.Custom cloud / VPC / on-premise deploymentsVolume ACU pricing (unmetered options available)Expanded storage & retention policiesSSO/SCIM, customer-managed keys, advanced auditPrivate model routing & custom tools/agents; banker‑friendly workflows (CIM authoring, buyer tagging, KPI templates)Dedicated CSM, priority SLAs, quarterly reviewsCustom integrations (CRM, VDR, data vendors; Outlook/Gmail, Slack/Teams)About ACUs (Agent Compute Units)We meter by sessions, not tokens—so banker workflows stay predictable regardless of model mix.What is an ACU?1 ACU = one max-context agent working session (up to 1M tokens across model calls, retrieval/orchestration, networking, and transient storage).Why this model?Predictable: budget by sessions, not raw tokensFlexible: we blend models/tools behind the scenesFair: heavy sessions consume more ACUsMetering rationaleWe meter ACUs because the real cost includes more than tokens—compute, memory, network, vector search, monitoring—and varies by context length.Typical ACU usage (guidance, not a guarantee)TaskTypical ACUsRefresh public/precedent comps~1 ACUDraft a complete CIM (60–80 slides)~2–3 ACUsGenerate buyer universe (200+ names w/ tags & contacts)~3–4 ACUsBuild a financial model (drivers-based revenue & costs + sensitivities)~5 ACUsSummarize diligence/QoE redlines (≤100 changes)~1 ACUWhat 100 ACUs/month typically yieldsExample mix: ~12 CIM drafts (60–80 slides), ~8 buyer universes, ~6 financial models, ~25 comps refreshes, plus weekly memos. Adjust mix to fit your pipeline.OnboardingGet up and running quickly with our baseline onboarding, or add specialized services.IncludedBaseline OnboardingIncluded with any software plan1 agent setup (trained on your data/style)Team training (live session or recorded)Email/Slack/Teams access to your dedicated support analystKickoff checklist• Data intake: historicals, exports, customer cohorts, KPI definitions• Style: brand guide, slide templates, voice/tone examples• Access: storage/warehouse, CRM/VDR, email/calendar (optional)• Samples: prior CIMs/teasers, buyer lists, diligence templatesOnboarding Add-Ons (optional)ServiceTimePriceExtra Agent Setup3–5 days$3,500/agentData Loading & DB Integration5–7 days$5,000Advanced Team Training1 day$2,500Custom Style & Templates~1 week$4,000Premium Data AccessZoomInfo • Crunchbase • PitchBookOngoingCustomConfigure additional agents (e.g., Buy-Side, Diligence), connect data warehouses, or access proprietary datasets (ZoomInfo, Crunchbase, PitchBook).Support, Security & TermsEnterprise-grade support and security with flexible terms.Support• Email/Slack/Teams access• Dedicated support analyst• Enterprise: priority SLAs & named CSMSecurity• No customer data used to train models• Least-privilege access; audit logs• SSO/SCIM; customer‑managed keys (Enterprise)• Data residency options available• DPA on request• Standard retention: 90 days (configurable on Enterprise)Terms• Contracts: Monthly or discounted annual• Grace period: 3 months on all plans• ACU overages billed at month-end• Unused ACUs roll 1 month (50%)Quick FAQHow does Cloud pricing work?Can ACUs be converted to services?How do ACUs relate to tokens?What's included in Enterprise?Do services come with guarantees?Ready to Get Started?Join leading finance firms who are already using Patterns to eliminate grunt work and focus on what matters—deals, relationships, and value creation.Talk to our team --- PatternsToggle SidebarUser GuideOverviewAgentsChat SessionsFilesExcelPythonNotebooksDatabasesWeb ResearchMemory & AutomationsCitationsBest PracticesNavigation← Back to HomePricingUse CasesLinksLinkedInXSign inGet SupportToggle SidebarPatternsPatterns AI for Deal Teams — User GuideThis guide explains how to use the application to produce analyst-grade deliverables across the deal process (comps, buyer lists, models, memos) with an agentic workflow designed for investment bankers. For context on value proposition and pricing, see: Patterns and Patterns Pricing.Try PlatformView PricingKey ConceptsAgents — Workspaces for teams with their own data, memory, and chats.Chats — Task-oriented conversations where the AI executes your playbooks.Files — PDFs, Excel, CSVs; system indexes content for retrieval.Excel — Bi-directional sync via add-in; create/read/write from chats or notebooks.Python — Persistent runtime with pandas/Altair for analysis and visualization.Notebooks — Reproducible Python/Markdown cells; assets and charts render in-app.Databases — Connect Snowflake, BigQuery, Postgres; query from Python or tools.Web Research — Agentic research via Exa for market/industry/company sources.Memory/Projects/Todos — Save templates, manage work, and track progress.Automations — Scheduled or manual tasks to run playbooks autonomously.AgentsWhat agents areAgents are team workspaces with their own data sources, knowledge base, and chat history. Each user gets a default personal agent; you can create additional agents for deals, sectors, or clients.Creating agentsNavigate to lower left menu in the sidebar and select New Agent. Name and optionally describe the agent; it initializes with a clean knowledge base.Agent membersAdd members by email from the agent's Members page. Roles: Admin can manage members and settings; members can use all analysis tools and shared resources. Runtime capabilities are the same; admin adds/removes users and manages integrations.Data, memory, session historyEach agent keeps its own files, memories, and chat sessions. Sharing is scoped to the agent unless explicitly made public (see Sharing).Agents list and Members modalChat SessionsContext and intentThe AI is instructed to act as a PE analyst focused on execution with your data and tools. Be explicit about data sources and expected outputs (e.g., "Refresh public comps for vertical SaaS, output table in Excel and write back formulas"). The AI will ask clarifying questions when needed.AI models and context limitsChoose a model in Settings; the app remembers your selection for future chats. Long chats may hit a model's context limit. Use Session Bridging to continue.Using @mentions to add contextType @ in the message box to search your resources and insert mentions. Supported types commonly include: files, notebooks, databases/tables, knowledge/memories, chats, and tasks. Mentions pin authoritative context to your request so the AI cites and uses the right sources.Your browser does not support the video tag.Chat compose area with @mention functionalitySession bridging (continue when context is full)Use "Summarize & Continue" to roll forward: the app writes a brief summary of the current thread and opens a new chat with that state carried over. Use when context is near limits, you want a clean thread, or after large tool runs.Edit and revert session changesYou can edit your last user message. If tool actions occurred afterward, reverting will roll back subsequent steps in this chat. Reverts will also undo AI-initiated changes tracked in this thread (including Excel writes that were performed via the session). Confirm before proceeding.Prompt tips• Align on a plan first: "Plan the approach to refresh comps and draft IC outline."• Specify sources: "Use Snowflake schema X, PitchBook export, File: 'Q2 KPI.xlsx'"• Specify outputs: "Write results to Excel tab 'Comps', include valuation bands"• If the direction is off: stop, revert to the prior step, and re-prompt.Sharing and embedding chatsUse the Share button in the chat header to copy a view-only link. Public share links render a read-only version without requiring sign-in. For internal distribution, set visibility to your agent and share in Slack/Teams.Chat sharing functionalityFilesSupported file typesPDFs, XLSX, CSV (CSV is converted to XLSX under the hood for consistency). PPT support is on the roadmap. Contact us for additional formats.Loading filesDrag and drop into a chat, or upload via Files. Reference specific files in prompts via @mentions for precise context.Data extraction, indexing, and searchPDFs are indexed for page-level search; Excel sheets are summarized for quick previews. Use @mentions to ensure the AI cites the exact document or sheet.Review extractionsFor PDFs: open the file to preview extracted structure; cite specific pages. For Excel: view sheet list and headers; the AI can read ranges or write results.Your browser does not support the video tag.File management and extraction workflowYour browser does not support the video tag.Document extraction demonstrationExcelCreate / read / writeAsk the AI to create a new workbook, read a range, or write a 2D array to Sheet!A1. The write tool auto-sizes ranges and pads jagged arrays.Formatting basicsYou can request tables with headers, basic number formats, and new worksheets. The system preserves data types and dates when possible.Excel add-in (bi-directional sync)Connect the add-in to sync changes from Excel to the app and vice versa in near-real-time. "Force Sync" will snapshot current sheets to the server and re-index content.Connect the Excel add-inTo connect the add-in, download the manifest and upload it in Excel. Please see the video for details.Your browser does not support the video tag.Excel add-in connection walkthroughSync changesAfter AI writes to Excel, changes appear in your workbook; add-in logs updates. If needed, you can revert chat steps that wrote to Excel from within the chat.Your browser does not support the video tag.Excel bi-directional sync demonstrationPythonRun codeUse the notebook or quick Python execution to run analysis without leaving chat.Libraries availablepandas, numpy, Altair (for charts), statsmodels, openpyxl, and standard libs.Datastorestore.set(key, df) saves a DataFrame (or chart) as a named asset for reuse.store.get(key) retrieves the asset in later Python or Excel steps.Database and files in Pythonquery_database(data_source_id, sql) returns a DataFrame for SELECT/DDL/DML.load_file_by_id(file_id) returns bytes you can pass directly to pandas/openpyxl.Code examples:# Load Excel and preview file_data = load_file_by_id("FILE_ID") import pandas as pd df = pd.read_excel(file_data, sheet_name="Sheet1", nrows=50) store.set("sample", df) # Query database my_ds = "ds_XXXXXXXXXX" sql = "SELECT name, revenue FROM finance.customers WHERE region='US' LIMIT 100" df2 = query_database(my_ds, sql) store.set("customers_us", df2) # Chart with Altair (charts render when stored) import altair as alt alt.data_transformers.enable('default', max_rows=None) chart = alt.Chart(df2).mark_bar().encode(x='name:N', y='revenue:Q') store.set('customers_chart', chart)NotebooksWhat they're forStructured, reproducible analysis with Python and Markdown cells. Use notebooks to document research, attach citations, and produce charts/tables.Cells (Python or Markdown)Add, update, or delete cells freely. Python cells can auto-execute; Markdown cells render instantly. Charts render when saved via store.set('key', chart); tables render from stored DataFrames. Console output appears alongside cells for transparency.Your browser does not support the video tag.Notebook interface with Python and Markdown cellsDatabasesSupported systemsSnowflake, BigQuery, Postgres (via configured data sources).Schema indexing and samplingBrowse available tables and columns; the AI can sample data to infer schema usage.Agent data toolsUse tools to list tables, read from a view, or materialize intermediate results.Access via Python VMUse query_database for SQL inside notebook cells; results become DataFrames for downstream analysis and Excel output.Your browser does not support the video tag.Database connections and schema browserFivetranManaged ingestion for common SaaS/data sources. Configure destinations, groups, and connections to route data into your warehouse.Currently supported connectors (examples)Brew (beta), QuickBooks, Gmail. Contact support for additional connectors and enterprise sources.Data connections managementWeb ResearchWhat it doesAgentic multi-step research for market maps, industry analysis, and comps across many websites. Progress streams live; results include a structured summary or JSON if a schema is provided.Typical usesRefresh public/precedent comps, build buyer universes, draft memo sections with citations.NotesLong tasks have a sensible timeout; break very large prompts into smaller chunks if needed.Your browser does not support the video tag.Web research progress and resultsOther Data SourcesCrunchbase, People Data Labs, PitchBook, SourceScrub: bring exports as files, connect via warehouse tables, or leverage web research for public context.Memory & AutomationsMemorySave reusable templates, stylistic guides, and project context as memories.ProjectsMaintain a single "project" memory per effort with goal, scope, and a punch-list of tasks; attach deliverables and files.TodosKeep a lightweight todo memory while working a task; delete it when done.Custom tagsTag memories/files for quick discovery (e.g., tag=project or sector tags) and better @mention filtering.Your browser does not support the video tag.Automation management interfaceAutomations (Tasks)Self-contained runs that execute playbooks on a schedule or on-demand (e.g., weekly comps refresh that writes back to Excel and posts a summary). Create automation → name it → choose recurring or one-time schedule (CRON) or leave unscheduled for manual runs → provide clear instructions and outputs.Memory and project organizationCitationsWhat gets citedThe AI includes citations in outputs so reviewers can validate sources. Common citations reference: PDFs with page numbers, Excel ranges/sheets, and web pages.How to add or ensure citationsIn chats: use @mentions to anchor the exact files/tables; the AI will cite those sources in its response. In notebooks (Markdown cells): include a brief reference at the end of a sentence or immediately after a quote.Examples:Revenue increased 18% YoY in Q3. [PDF: Q3-Report, p. 15]We used the model sheet for calculations. [Excel: Forecast!A1:D50]Industry overview adapted from Gartner. [https://www.gartner.com]Tips:• Place citations right after the sentence they support; quotes should cite immediately after the quote, paraphrases at sentence end.• Prefer specific locations (page numbers or ranges) over broad document mentions.• Use @mentions in chat prompts to make the AI pick the right sources before it writes.Best PracticesBe explicit: State data sources, filters, and expected outputs.Cite and pin: Use @mentions so the AI uses the right files/tables.Iterate: Agree on the plan before heavy execution; summarize between phases.Validate: Use reviewer gates on outputs; leverage revert when needed.Additional ContextFor product positioning, deployment options, security, and pricing models (Agent Compute Units, onboarding, and services for buy/sell-side), see:Visit Patterns.appView PricingGet Support