Purpose
Inbound demand can outgrow a form-to-BDR-to-AE process: buyers wait days for simple answers that are
already in the docs. This skill turns Anthropic's buying-agent case study into a repeatable design and
iteration procedure. In the source, the agent holds thousands of conversations a day; escalated leads
convert to opportunities more than twice as often as old form leads and close about five days faster.
When to use
- Inbound requests far exceed what the BDR team can answer, and most questions are simple
(price, seat minimums, compliance terms such as HIPAA contract requirements).
- You want buyers answered at any hour and in any language, and able to buy without a rep if they prefer.
- You are drafting or tuning the system prompt, tools, or knowledge base of a sales-facing agent.
Instructions
- Define the job like a rep's job. The agent should do what a good rep does: understand what the
customer is trying to solve, what their current usage looks like, and how best to help them.
- Deploy where buyers already ask. Contact-sales page, pricing page, inside the product, and email.
Keep it opt-in: at the start the buyer chooses an agent or a sales rep.
- Design the conversation flow. The buyer describes needs, the agent asks a few follow-ups, answers
pricing, security, and data questions, then recommends a plan and seat count. Every conversation
ends in one of three outcomes - see references/conversation-outcomes.md.
- Keep the architecture small. A prompt, a handful of tools, and Claude, on a managed runtime
(Claude Managed Agents handles hosting, sessions, and tool orchestration). Spend your effort on the
three selling-specific parts: the prompt, the tools, and the knowledge base.
- Write a goal-first, short prompt. State the goal instead of a rules flowchart, and supply the
knowledge Claude needs (what seat-based pricing covers, when billing cycles run). Start from
templates/goal-first-system-prompt.md.
- Optimize for the right plan, not the biggest. Pointing a small team to a smaller plan is a
feature: correctly placed buyers stay longer and have a better experience.
- Put SMEs in the loop. Engineering owns the code; sales and content leads review and edit the
system prompt directly (in the Console in the source). Changes go to a staging agent first.
- Version every change. Each prompt change is a version (the source reached v7 about a week into
internal testing and kept shipping weekly after launch). Roll new sessions back to a prior version
when needed.
- Treat escalations as feedback. Require the agent to state why it hands off. Log reasons with
templates/escalation-feedback-log.md, cluster them, and fix
the self-serve gaps they reveal (the source roughly halved the share needing a human).
- Measure. Track conversations/day, outcome mix, lead-to-opportunity rate vs. the old form,
time to close, and rep effort per deal. See references/lessons-and-results.md.
Examples
Example 1 - prompt rewrite.
Input: a 3-page prompt that lists every qualification rule as a flowchart.
Output: a short prompt opening with "Your goal is to understand customer requirements, qualify
prospects, and recommend the best plan," followed by pricing/billing knowledge and the three outcomes;
the rule list is dropped.
Example 2 - small team asks about Enterprise.
Input: "We're 8 people, should we get Enterprise?"
Output: the agent asks about needs, and if a smaller plan fits, recommends it with a seat count and a
checkout link instead of upselling.
Example 3 - escalation review.
Input: a week of hand-offs where most reasons are "customer needs X that self-serve can't do yet."
Output: a ranked list of self-serve gaps fed into the product/experience backlog; re-measure the
hand-off share next cycle.
Bundled resources
- references/conversation-outcomes.md - the three endings and hand-off payload.
- references/lessons-and-results.md - lessons, platform reasons, reported results.
- templates/goal-first-system-prompt.md - starting prompt skeleton.
- templates/escalation-feedback-log.md - hand-off reason log.
Source
1---2name: inbound-buying-agent-design3description: Design, build, and iterate an inbound "buying agent" that takes a prospect from "I want this for my company" to a purchase, a hand-off to a sales rep, or a quick answer - modeled on how Anthropic's sales team rebuilt inbound with Claude Managed Agents (beta) in September 2026. Covers where to deploy the agent (contact-sales and pricing pages, in-product, email), the three conversation outcomes, keeping the experience opt-in, a goal-first and short system prompt, a small tool set plus knowledge base, versioned prompt iteration with a staging agent and subject-matter experts in the loop, recommending the right (not the biggest) plan, and treating every agent-to-rep escalation as feedback. Use when a sales or go-to-market team cannot keep up with inbound demand, wants an always-on self-serve buying path, or is writing and tuning the prompt for such an agent.4metadata:5 source: https://skillmd.com/skills/uygnoey/inbound-buying-agent-design6---78## Purpose9Inbound demand can outgrow a form-to-BDR-to-AE process: buyers wait days for simple answers that are10already in the docs. This skill turns Anthropic's buying-agent case study into a repeatable design and11iteration procedure. In the source, the agent holds thousands of conversations a day; escalated leads12convert to opportunities more than twice as often as old form leads and close about five days faster.1314## When to use15- Inbound requests far exceed what the BDR team can answer, and most questions are simple16 (price, seat minimums, compliance terms such as HIPAA contract requirements).17- You want buyers answered at any hour and in any language, and able to buy without a rep if they prefer.18- You are drafting or tuning the system prompt, tools, or knowledge base of a sales-facing agent.1920## Instructions21221. **Define the job like a rep's job.** The agent should do what a good rep does: understand what the23 customer is trying to solve, what their current usage looks like, and how best to help them.242. **Deploy where buyers already ask.** Contact-sales page, pricing page, inside the product, and email.25 Keep it **opt-in**: at the start the buyer chooses an agent or a sales rep.263. **Design the conversation flow.** The buyer describes needs, the agent asks a few follow-ups, answers27 pricing, security, and data questions, then recommends a plan and seat count. Every conversation28 ends in one of three outcomes - see [references/conversation-outcomes.md](references/conversation-outcomes.md).294. **Keep the architecture small.** A prompt, a handful of tools, and Claude, on a managed runtime30 (Claude Managed Agents handles hosting, sessions, and tool orchestration). Spend your effort on the31 three selling-specific parts: the prompt, the tools, and the knowledge base.325. **Write a goal-first, short prompt.** State the goal instead of a rules flowchart, and supply the33 knowledge Claude needs (what seat-based pricing covers, when billing cycles run). Start from34 [templates/goal-first-system-prompt.md](templates/goal-first-system-prompt.md).356. **Optimize for the right plan, not the biggest.** Pointing a small team to a smaller plan is a36 feature: correctly placed buyers stay longer and have a better experience.377. **Put SMEs in the loop.** Engineering owns the code; sales and content leads review and edit the38 system prompt directly (in the Console in the source). Changes go to a **staging agent** first.398. **Version every change.** Each prompt change is a version (the source reached v7 about a week into40 internal testing and kept shipping weekly after launch). Roll new sessions back to a prior version41 when needed.429. **Treat escalations as feedback.** Require the agent to state *why* it hands off. Log reasons with43 [templates/escalation-feedback-log.md](templates/escalation-feedback-log.md), cluster them, and fix44 the self-serve gaps they reveal (the source roughly halved the share needing a human).4510. **Measure.** Track conversations/day, outcome mix, lead-to-opportunity rate vs. the old form,46 time to close, and rep effort per deal. See [references/lessons-and-results.md](references/lessons-and-results.md).4748## Examples4950**Example 1 - prompt rewrite.**51Input: a 3-page prompt that lists every qualification rule as a flowchart.52Output: a short prompt opening with "Your goal is to understand customer requirements, qualify53prospects, and recommend the best plan," followed by pricing/billing knowledge and the three outcomes;54the rule list is dropped.5556**Example 2 - small team asks about Enterprise.**57Input: "We're 8 people, should we get Enterprise?"58Output: the agent asks about needs, and if a smaller plan fits, recommends it with a seat count and a59checkout link instead of upselling.6061**Example 3 - escalation review.**62Input: a week of hand-offs where most reasons are "customer needs X that self-serve can't do yet."63Output: a ranked list of self-serve gaps fed into the product/experience backlog; re-measure the64hand-off share next cycle.6566## Bundled resources67- [references/conversation-outcomes.md](references/conversation-outcomes.md) - the three endings and hand-off payload.68- [references/lessons-and-results.md](references/lessons-and-results.md) - lessons, platform reasons, reported results.69- [templates/goal-first-system-prompt.md](templates/goal-first-system-prompt.md) - starting prompt skeleton.70- [templates/escalation-feedback-log.md](templates/escalation-feedback-log.md) - hand-off reason log.7172## Source73- https://claude.com/resources/articles/how-anthropics-sales-team-rebuilt-inbound-with-claude-managed-agents