Pitch Builder
Anthropiclive
Illustrative demo · in-page
Creates target lists, runs comparables, and drafts pitchbooks for client meetings.
Target listComparablesPitchbook deck
Find the right agent
Tell us what you're trying to do.
Describe your task in plain language. We'll match you with the top 3 frontier agents from across Anthropic, OpenAI, Google, Microsoft, Salesforce, and Ema that fit best.
Try:
Filter by
Featured Frontier Agents
The finance agents you can try right now.
Purpose-built finance agents from Anthropic, OpenAI, Google, Microsoft, Salesforce, and Ema — spanning research and client coverage through finance and operations. Click any card to launch it.
Research & Client Coverage5
Meeting Preparer
Anthropiclive
Illustrative demo · in-page
Assembles a briefing on the person you're meeting — background, recent earnings-call commentary, the company's priorities, and where you add value — as a downloadable locked PDF.
Person briefLocked PDF deck
Earnings Reviewer
Anthropiclive
KokoAI native · live in-page
Reads transcripts and filings, updates models, and flags thesis-relevant changes.
Updated modelThesis-impact note
Model Builder
Anthropiclive
Illustrative demo · in-page
Creates and maintains financial models from filings, data feeds, and analyst inputs.
Financial modelRefresh log
Market Researcher
Anthropiclive
Illustrative demo · in-page
Tracks sector and issuer developments, synthesizes news, filings, and broker research, and flags items for credit and risk review.
Synthesis briefRisk flag
Finance & Operations7
Valuation Reviewer
Anthropiclive
Illustrative demo · in-page
Checks valuations against comparables, methodology, and the firm's review standards.
Review memoVariance log
General Ledger Reconciler
Anthropiclive
Illustrative demo · in-page
Reconciles general ledger accounts and runs net asset value calculations against the books of record.
Reconciliation reportNAV calc
Month-End Closer
Anthropiclive
KokoAI native · live in-page
Runs the close checklist, prepares journal entries, and produces close reports.
Journal entriesClose report
Statement Auditor
Anthropiclive
Illustrative demo · in-page
Reviews financial statements for consistency, completeness, and audit-readiness.
Audit memoIssue list
KYC Screener
Anthropiclive
Illustrative demo · in-page
Assembles entity files, reviews source documents, and packages escalations for compliance review.
Entity fileEscalation packet
Claude Cowork
Anthropiclive
Claude's agentic workspace (on web + mobile since July 2026) — hand Claude a task and it works across your files, calendar, email, messaging and the web, with background work, scheduled tasks and mobile approvals. The delivery surface for the finance agent plugins.
Completed multi-step workDeliverables
Claude for Excel (Microsoft 365)
Anthropiclive
Claude inside Excel, PowerPoint, Word and Outlook — builds and audits models cell-by-cell with traceable changes, drafts decks and memos in place. The add-ins shipped alongside the Anthropic finance agents.
Working modelsTraceable editsDrafted decks
"Live in-page" agents run a real KokoAI session here; "illustrative demo" agents show a quick in-page preview. Either way, you can run any agent on your own data — each opens in your own Claude (or the provider's app) in a new tab.
The full Frontier agent catalog
34 entries
PDFfin
liveDocumentHigh
Parse, extract, and reason over PDFs of any size — financial filings, contracts, reports.
PDF tool
Files
liveDocumentHigh
Upload, read, and write files within an Anthropic-hosted workspace. Foundation for document-heavy agents.
Files API
Web Searchfin
liveKnowledgeHigh
Live search the public web with citation-grade results. Critical for research, news, and recent events.
Web search tool
Web Fetch
liveKnowledgeMed
Pull a specific URL into context. Pairs with web search for deep reads of cited sources.
Web fetch tool
Code Executionfin
liveComputeHigh
Sandboxed Python for analysis, modeling, charts. Stateful across turns within a session.
Code execution tool
Computer Use
betaAutomationHigh
Drive a browser or desktop autonomously by interpreting screenshots and emitting actions.
Computer Use tool
Brand Guidelines
liveDocumentMed
Anthropic-shipped Skill: enforce brand voice and visual rules on generated docs and decks.
Skills runtime
DOCX Authoringfin
liveDocumentMed
Generate well-formatted Word docs from structured inputs — board memos, controller letters, finance narratives.
Skills runtime
XLSX Authoringfin
liveDocumentMed
Generate Excel workbooks with formulas, formatting, and multi-sheet structure — financial models, variance packs.
Skills runtime
PPTX Authoringfin
liveDocumentMed
Generate PowerPoint decks from structured inputs — board packs, CFO command-center reviews.
Skills runtime
Financial Data Analystfin
liveFinanceHigh
Reference agent that answers questions about financial filings using PDF + code execution. Open-source on GitHub.
PDFCode execution
Customer Support Agent
liveServiceHigh
Reference implementation for a tool-using customer service agent with escalation logic.
Tool useRAG
Deep Research Agent
liveKnowledgeHigh
Multi-step research with web search, source synthesis, and structured report generation.
Web searchMulti-turn
RAG Retrieval Agent
liveKnowledgeMed
Retrieval-augmented Q&A with vector store + reranking. Baseline pattern for internal-knowledge agents.
Vector storeReranker
Multi-Agent Orchestrator
liveOrchestrationHigh
Coordinator pattern: lead agent delegates to specialist subagents, merges results, returns synthesis.
SubagentsTool use
Computer Use Demo
betaAutomationHigh
End-to-end Computer Use reference — Docker, screenshots, action loop, safety guardrails.
Computer UseDocker
Explore
liveRead-onlyHigh
Fast read-only search agent for locating code: find files, grep symbols, answer 'where is X defined / what references Y'.
ReadGrepGlob
Plan
liveDesignHigh
Software-architect agent for designing implementation plans. Returns step-by-step plans and critical files.
ReadGrep
general-purpose
liveCatch-allMed
General agent for researching complex questions, multi-step tasks, and open-ended searches.
All tools
code-reviewer
liveQualityHigh
Independent reviewer for diffs — surfaces correctness bugs, with effort tiers from low to max.
ReadBash
claude-code-guide
liveHelperLow
Q&A about Claude Code itself, the Claude Agent SDK, and the Anthropic API.
WebFetchWebSearch
statusline-setup
liveHelperLow
Configure the Claude Code status line via settings.json.
ReadEdit
GitHub
liveDeveloperHigh
Read/write GitHub issues, PRs, files, commits, CI status. Standard MCP server bundled with Claude clients.
MCP transport
Figma
liveDesignMed
Bridge code and design — read Figma into code, push code into Figma, manage design tokens.
MCP transport
Gmail
liveProductivityMed
Read, search, label, draft emails and manage threads.
MCP transport
Notion
liveProductivityMed
Query and edit Notion databases and pages from inside Claude.
MCP transport
Slack
liveProductivityMed
Post, search, and react to Slack messages across channels and DMs.
MCP transport
Linear
liveProductivityMed
Manage Linear issues, projects, and cycles from agent workflows.
MCP transport
Postgres
liveDataHigh
Run read-only SQL against any Postgres database — analytics, ad-hoc data pulls, schema inspection.
MCP transport
BigQueryfin
liveDataHigh
Query BigQuery warehouses including finance, planning, and operational marts.
MCP transport
Snowflakefin
liveDataHigh
Query Snowflake warehouses for finance and analytics workloads.
MCP transport
Plaidfin
betaFinanceHigh
Connect bank accounts, fetch balances, transactions, and identity verification for finance agents.
MCP transport
Stripefin
betaFinanceMed
Read and manage Stripe customers, invoices, subscriptions, and payment events.
MCP transport
Filesystem
liveDeveloperMed
Read/write files in a sandboxed directory — the simplest MCP server, useful as a building block.
MCP transport
Want the full catalog as a locked, board-forwardable PDF? Download an executive overview — coverage by provider, the finance-featured highlights, and the ecosystem catalog.