AI for Sales & revenue teams
Claude for sales work: the official sales plugin, prospect research you can actually source, CRM and deliverability audits, and which tools connect to Claude.
Start here
Read these in order — each one assumes the last.
- 01GuideClaude for Sales Teams: The Surface MapA developer's surface map for sales teams: Anthropic's free sales plugin, claude.ai Projects, Cowork, Claude Code, and the connectors that make them real.
- 02GuideInside Anthropic's Sales Plugin for Claude: All Nine SkillsAnthropic's sales plugin for Claude, skill by skill: what all nine produce, what needs a connector, and why its own README undercounts them at six.
- 03GuideHow to Research a Prospect with Claude (and Verify It Before You Send)Research prospects with Claude step by step: the sales plugin's account-research skill, enrichment connectors, draft-outreach, and a pre-send claim check.
- 04GuideThe Best AI Sales Tools in 2026Ten AI sales tools checked against vendor pages in September 2026: data, CRM, execution, and conversation intelligence, with Claude connectors and AI metering.
- 05GuideWhich Claude Plan Should a Sales Team Pay For?Cowork, Projects, connectors, seats, or Claude Code: match what a sales team needs to a Claude surface, then check the plans page for the current numbers.
Guides20
Tutorials and deep-dives
Claude Free vs Pro vs Max vs Team (2026): Which Plan Unlocks What
Every Claude plan compared as of September 2026: prices, usage tiers, and which plan unlocks Claude Code, Cowork, Design, Excel, Chrome, projects, and models.
What Is Claude Cowork? The Complete Guide for Non-Developers
Claude Cowork explained for non-developers: what the desktop agent does with your files and apps, how it differs from chat and Claude Code, plans, and safety.
What Are Claude Skills? The Complete Guide
Claude Skills explained: what a SKILL.md is, how progressive disclosure keeps skills cheap, where they run, and how to install or write your own.
Getting Web Data into AI Agents: Search & Scraping APIs Compared
The agent web-data layer — Exa for semantic search, Firecrawl for extraction at scale, Tavily for all-in-one, Jina Reader for zero-setup — and how they compose.
AI Meeting Notes: Turn Transcripts into Decisions and Action Items
Use AI to turn a meeting transcript into clear minutes, with evidence for decisions, confirmed owners, unresolved questions, and a reviewable action list.
ChatGPT Projects vs Claude Projects for Teams
Compare shared AI project context in ChatGPT and Claude, then build a team brief with clear instructions, source ownership, and a review process.
Create an AI Presentation from a Report: A Reviewable Workflow
Turn a business report into an AI-assisted presentation with a claim-to-slide map, source checks, speaker notes, and a finished-deck review.
How to Research Documents with AI and Verify Citations
Turn a set of documents into a defensible AI research brief with a source register, conflict table, citation checks, and clear unanswered questions.
How to Summarize an Email Thread with AI and Draft a Reply
Use AI to reconstruct a long email thread, distinguish current decisions from old requests, identify open questions, and draft a reply for review.
Microsoft 365 Copilot vs ChatGPT for Work
Compare Microsoft 365 Copilot and ChatGPT for workplace tasks by source access, app context, deliverables, and a practical team pilot.
Build an AI Customer Support Answer Library You Can Check
Build an AI support answer library with source-backed answer cards, eligibility limits, escalation rules, and checked customer-question test cases.
Build an RFP Compliance Matrix with AI and Evidence
Build an RFP compliance matrix with AI that maps every requirement to source text, approved evidence, response locations, owners, and unresolved gaps.
Anthropic's Knowledge-Work Plugins: Every Role Plugin, Explained
Every Anthropic knowledge-work plugin for Claude Cowork and Claude Code cataloged: what each role plugin bundles, the install commands, and how to fork one.
Claude Code for Revenue Ops: Connectors, CRM Audits, and the Fine Print
Running Anthropic's sales plugin in Claude Code: wiring MCP connectors, auditing a CRM export, and the vendor terms that decide what you may connect.
Claude Skills for Sales: The Set Worth Installing
The Claude skills a sales team should install: Anthropic's nine official ones, plus four of ours that verify and audit what the official set writes.
Clay vs Apollo: Which GTM Data Tool in 2026?
Clay vs Apollo compared on what each actually is, the two-meter versus one-seat pricing shape, the MCP surface Claude can drive, and the fine print on credits.
Claude's Document Skills: Excel, PowerPoint, Word, and PDF
How Anthropic's pre-built document skills let Claude produce real .xlsx, .pptx, .docx, and PDF files — on claude.ai, the API, and in Claude Code.
How to Install Claude Skills
Every way to install Claude skills: manual copy, the agentscamp CLI, GitHub repos, plugins, team distribution, and uploading to claude.ai.
Human-in-the-Loop AI Workflows: Approval Gates That Keep Agents Safe and Trusted
How to design human-in-the-loop into agent workflows — when to require approval, gate patterns, confidence escalation, review UX, and feedback loops.
Few-Shot vs Chain-of-Thought vs Structured Prompting: What to Use When (2026)
When to reach for few-shot examples, chain-of-thought reasoning, or structured/output-constrained prompting — a 2026 decision guide to the core techniques.
Tools22
The AI tooling directory
Apollo
Apollo pairs a 240M+ contact database with outbound sequencing in one seat, and its MCP server is the most agentic thing about it.
Attio
Attio is a developer-extensible CRM with a user-defined data model, agents that research and act on records, and a live MCP endpoint for Claude.
Claude
Anthropic's AI assistant app for web, desktop, and mobile, with Projects, connectors, Artifacts, skills, memory, and code execution.
Claude Cowork
Anthropic's agent for knowledge work that completes multi-step tasks in your folders, connectors, and browser, on desktop, web, and mobile.
Clay
Clay is a GTM data workbench where every table column runs an enrichment step, with Claygent research agents and a Claude connector listing seven tools.
Close
Close is an all-in-one CRM for high-velocity inside sales that bundles calling, SMS and email into the record, plus Chloe, an autonomous voice agent.
Fireflies
Fireflies joins Zoom, Meet and Teams calls, transcribes them, and turns transcripts into searchable notes, action items and CRM records for sales teams.
Gong
Gong records and analyses every customer conversation across an org, deriving deal risk, forecast and coaching signals, and publishes three read-only MCP tools.
Hubspot Breeze
HubSpot's built-in AI: Breeze Assistant in every plan, pre-built Breeze agents for content, prospecting, and support, and a plain-language Agent Builder.
Lindy
An AI teammate that lives in Slack, joins your meetings, and runs scheduled routines and reusable skills across 1,000+ tools with approvals.
Nooks
Nooks is an AI sales workspace for outbound teams: a parallel dialer with answer detection, AI sequencing, account research, signals and call coaching.
Outreach
Outreach is a sales-execution platform that owns the outbound rep's whole workflow, repackaged around agents including Outreach Omni and Agent Studio.
Unify
Unify turns real-time intent signals into automated, AI-personalised prospecting plays, with a chat agent, 50+ native skills and flat per-seat pricing.
Zapier Agents
Zapier's no-code AI agents that take plain-English instructions and act across 9,000+ apps on a schedule, on app events, or on demand.
Zoominfo
ZoomInfo is a B2B contact and company database with intent signals, now positioned as the grounding data your agent calls through API, MCP or CLI.
Intercom Fin
Fin by Intercom is an AI customer agent with support-content training, guidance, pre-deployment batch testing, and configured human handover workflows.
Loopio
Loopio is an RFP response platform with a reusable answer library, AI-assisted response drafting, project collaboration, and source-scoped generation controls.
Exa
The search engine built for AIs — semantic web search, page contents, Websets, and research APIs, plus a hosted MCP server.
Firecrawl
The API to search, scrape, and crawl the web for AI — clean Markdown out of any site, LLM-powered extraction, and a first-class MCP server.
N8n
Fair-code workflow automation with native AI: a visual canvas plus code, 400+ integrations, and LangChain agent nodes; self-host free or cloud per-run.
Notion MCP
Notion's hosted MCP server — search the workspace, fetch and create pages and databases, and manage comments through Markdown-optimized agent tools.
Slack MCP Server
The community-canonical Slack MCP server — smart history fetch, message search, channels, reactions, and opt-in posting, after the official server was archived.
Glossary11
AI terms, defined precisely
Ticket Deflection
Ticket deflection means helping a customer find an answer through self-service before they submit a support ticket or need a human support queue.
AI SDR
An AI SDR is software that runs sales development work such as prospecting, outreach, and follow-up, with autonomy that varies enormously between vendors.
Conversation Intelligence
Conversation intelligence is recording sales calls and meetings, transcribing them, and turning transcripts into searchable notes, actions, and CRM records.
Lead Enrichment
Lead enrichment is filling the missing fields on a lead or account record, such as title, headcount, or tech stack, from data sources outside your own system.
Revenue Intelligence
Revenue intelligence is deriving deal risk, forecast accuracy, and coaching signals from captured customer conversations rather than from CRM fields.
Sales Engagement Platform
A sales engagement platform is the system reps work out of: it sequences emails, calls, and tasks across channels and logs every touch back into the CRM.
Compliance Matrix
An RFP compliance matrix maps each buyer requirement to its source, response location, evidence, owner, and reviewed status throughout a proposal.
Grounding
Grounding ties a model's output to verifiable sources — retrieved documents, tool results, citations — instead of training-data memory.
AI Agent
An AI agent is an LLM-driven system that pursues a goal in a loop — calling tools, observing results, iterating — instead of returning one answer.
Hallucination
A hallucination is fluent, confident output that is factually wrong or fabricated — plausible text unsupported by any source, the signature LLM failure mode.
MCP (Model Context Protocol)
MCP is the open standard for connecting AI models to external tools and data: write one server, and any MCP client — Claude Code, IDEs, agents — can use it.
Agents4
Specialized subagents for focused work
RFP Completeness Reviewer
Review a prepared RFP submission against supplied requirements, addenda and attachment rules: find unanswered subparts, omitted documents, unproven exceptions, contradictory IDs and submission-rule gaps. Return an evidence-linked completeness review without drafting sales claims or submitting a bid.
Support Answer Auditor
Review prepared customer-support answer cards against supplied policy versions and applicability rules: flag unsupported promises, omitted eligibility conditions, contradictory answers, and missing escalation boundaries before the library is approved.
Sales Engineer
Use this agent to review the technical asks a prospect has put in front of a deal — security questionnaires, integration and API requirements, SSO and provisioning, SLA and uptime demands, data residency and retention terms, custom feature requests — and separate what the product does today from what needs engineering, with evidence for each verdict from the product's own docs and code. It writes the answer language a rep can safely send, and flags the commitments nobody should make without Engineering, Security, Legal, or Finance signing off. Examples — 'they want SSO, SCIM and EU data residency, what can we say yes to', 'review this integration requirements doc before Thursday's technical call', 'they are asking for a 99.99% SLA and two-hour breach notification, tell me what we cannot commit to'.
Contract Obligation Reviewer
Compare a prepared vendor-contract obligation register with supplied agreement and amendment text: flag missing qualifying language, unsupported dates or parties, unresolved cross-references, and unproven supersession. Return a source-linked review packet for qualified counsel; do not give legal conclusions or approve terms.
Skills9
Reusable capabilities Claude loads on demand
Contract Obligation Register
Extract a draft vendor-contract obligation register from supplied agreement text with parties, duties, triggers, timing wording, conditions, exceptions, cross-references and exact section evidence. Use to prepare a qualified reviewer’s packet; do not interpret enforceability, choose controlling terms, or invent deadlines.
Cold Email Deliverability Auditor
Audit a cold email program's sending setup and message body against the things that decide whether mail reaches an inbox: SPF, DKIM and DMARC records with their alignment and policy, the DNS lookup limit, a separate sending domain versus the primary corporate one, domain age and warmup state, list hygiene with bounce and complaint exposure, spam-trigger language, link and image ratio, unsubscribe presence, and the volume ramp per mailbox. Findings come back by severity with the concrete fix and the order to apply them. Use when a sending domain is new, replies have collapsed, or nobody has checked the DNS records, the list, and the copy in the same sitting.
Crm Export Auditor
Audit a CRM CSV export for the data faults that make every report built on it wrong: exact and near-duplicate accounts and contacts, close dates already in the past on open deals, deals with no activity in the last N days, blank required fields by stage, single-threaded deals carrying one contact, records with no owner or a departed one, stage and amount combinations that contradict each other, and currency, date and country formats that drift between rows. Returns a fix list ordered by how much each fault distorts a reported number, with the record IDs to correct and which fixes are safe to apply in bulk. Use when a pipeline number is disputed, when a migration or a dedupe is being planned, or when nobody has checked the export the forecast is built on.
Outreach Claim Checker
Check every factual and personalization claim in a drafted outreach email, or a batch of them, against the research the draft was written from: funding rounds, job titles and recent moves, tech stack, headcount, product launches and press, and named mutual connections. Each claim is marked sourced with the line that supports it, unsourced, contradicted, or stale, then unsupported specifics are cut or narrowed to what the research actually says, and every email leaves with a send, fix, or hold verdict. A source is never invented and never inferred. Use when outreach was personalized from AI or analyst research and nobody has verified the details before it reaches a prospect.
Security Questionnaire Responder
Draft answers to a prospect's security questionnaire — a SIG, a CAIQ, a VSA, or a custom spreadsheet — strictly from the documents the company supplies: the SOC 2 report, the DPA, the subprocessor list, a penetration test summary, architecture and access-control notes. Every answer is tagged sourced with the document and section it came from, needs-review, or not-applicable with the reason, and a control that appears in no document is left unanswered rather than asserted. Anything touching contractual terms, breach-notification windows, data residency, roadmap dates, or an exception is routed to Legal or Security by name. Use when a deal is blocked on a questionnaire and every answer has to survive an auditor reading it back.
RFP Requirement Mapper
Turn supplied RFP instructions and explicit addenda into a draft atomic compliance matrix: preserve requirement IDs and wording, split subparts visibly, map response/evidence locators, and flag missing mandatory or exception authority. Use before assembling a bid; do not write persuasive answers or invent compliance claims.
Support Answer Card Builder
Draft one reusable customer-support answer card per supplied policy question, with approved source locators, applicability, required facts, concise answer wording, exclusions, and an escalation boundary. Use when turning documented policies into an answer library; do not invent policy or send replies.
Web Research Pipeline
Run a structured web-research pass on a question: plan the searches, find sources via search APIs, fetch and read the best ones, cross-check claims, and synthesize a cited answer — with source quality and disagreements surfaced honestly. Use for 'research X and tell me what's actually true' tasks that need more than one search and less than a day.
Prompt Optimizer
Diagnose why a prompt underperforms and rewrite it with the technique that fixes it — clearer structure, few-shot examples, an explicit output contract, or reasoning scaffolding — returning an optimized prompt, the rationale for every change, and what to measure to confirm the lift. Use when a prompt is flaky, verbose, drifting in format, or just not good enough.
Commands5
Slash commands for Claude Code
Audit CRM
Audit a CRM CSV export for duplicates, past close dates, stale deals, missing required fields, single-threaded deals, owner gaps and format drift, and write a ranked fix list with the record IDs.
Check Outreach
Fact-check a drafted outreach email, or a folder of them, against the research files it was written from and write an annotated report with a claims table, without editing the draft.
Check Obligation Dates
Check a human-reviewed obligation CSV against an explicit as-of date with Python: validate calendar dates and status fields, list overdue or due-today open rows, missing owners/dates, and recorded late/future completions. Never infer legal deadlines, breach, or contract status from clauses.
Check RFP Coverage
Check human-reviewed RFP requirement and response-matrix CSVs with Python: validate unique IDs and explicit flags, count supplied statuses including absent rows, and list mandatory attention items or ready rows missing required references. Does not prove claim accuracy or submit a bid.
Check Support Cases
Validate a local JSONL support-answer testset with Python: unique case IDs, exact fields, answer/clarify/escalate expectations, required answer-card references and sources, and explicit escalation reasons; report counts without running a support bot.