Next Best Action
Recommend the one or two moves most likely to advance a deal, grounded in the current conversation state and account context.
Overview
Next Best Action reads the current state of a deal and recommends the one or two moves most likely to advance it. It runs conversation_intelligence over the recent engagements for open threads, stated next steps, blockers, buying signals, and unanswered questions, then pulls account_research for deal stage and stakeholder context. Every recommendation ties back to specific evidence from the conversations.
The skill is built for sellers who want a grounded call on what to do next, aimed at a goal they set (get to a technical eval, close this quarter, re-engage a stalled deal). It ranks up to three concrete moves. For each one it states the move, the why-now evidence behind it, and the effect it should produce.
Point it at an account, a contact, or a specific engagement, by ZoomInfo ID or by a name to resolve. When the evidence does not support a confident recommendation, the skill says what is missing and what to find out next. If conversation data is unavailable, it gives the best account-research-based suggestion and flags that the read is limited.
What It Does
- Conversation state read: Runs conversation_intelligence over the recent engagements for open threads, stated next steps, blockers, and buying signals.
- Deal context pull: Adds account_research for stage and stakeholder picture, so the move fits where the deal actually sits.
- Ranked recommendations: Proposes one to three moves in priority order, each aimed at the goal you set.
- Evidence and effect: Pairs every move with the specific conversation that justifies it and the outcome it should produce.
- Open-question callout: Names the one thing you do not yet know that would most change the recommendation, plus how to get it.
Use Cases
Decide the Next Move on a Stalled Deal
A deal has gone quiet after a strong demo. The skill reads the recent calls and emails, finds the pricing question that was never answered and the champion who stopped replying, and recommends a specific re-engagement move tied to that evidence. It also flags what you would need to confirm before treating the deal as dead.
Advance Toward a Technical Evaluation
Your goal is a paid technical eval. The skill reasons over the conversation state, sees that the technical buyer raised an integration concern, and recommends leading the next touch with a scoped proof point that addresses it. The recommendation states why that move fits now and what it should open up.
Get a Grounded Read Before a Call
Before a check-in, you want a fast, evidence-based sense of the best next step. The skill returns a short state-of-play, a ranked move or two, and the open question worth resolving on the call, so you walk in with a plan rather than a generic agenda.
Skill Definition
The raw markdown Claude uses when this skill is invoked.
--- name: next-best-action description: Recommend the next best action on a deal or relationship, grounded in the current conversation state. Uses conversation_intelligence as the primary source, with account_research for deal context. Identify the account or contact by ZoomInfo ID (preferred) or name (triggers a lookup), or point it at a specific engagement. Use when someone asks "what should I do next with Acme", "what's my next move here", "how do I advance this deal", or wants an evidence-based recommendation rather than a generic playbook. Reasons over the last few engagements only. --- # Next-Best-Action Read the current state of the conversation and recommend the one or two moves most likely to advance it. ## Prerequisites `conversation_intelligence` requires at least one connected email or meeting source; `conversation_intelligence` and `account_research` consume AI credits. If no conversation data exists, base the recommendation on `account_research` and say the read is limited, pointing the user to their ZoomInfo admin. ## Input Provided via `$ARGUMENTS`: - **Scope** (required) — an account, a contact, or a specific engagement (ID, or a name to resolve). - **Goal** (optional) — e.g. "get to a technical eval", "close this quarter", "re-engage a stalled deal". Sharpens the recommendation. ## Workflow 1. **Resolve scope.** Use a ZoomInfo ID directly, or resolve via `search_companies` / `search_contacts` and confirm an ambiguous match before spending credits (`conversation_intelligence` and `account_research` both cost AI credits, so a wrong resolution burns them). For a specific call not named, offer a `browse_engagements` shortlist first. 2. **Read the state.** Run `conversation_intelligence` scoped to the account/contact/engagement for where things stand: open threads, stated next steps, blockers, buying signals, and unanswered questions. Pull `account_research` for deal stage and stakeholder context. Keep CI scoped to one ID; it sees only the last few engagements and cannot search by topic or count, so reason from what it returns. 3. **Recommend.** Propose one to three concrete next actions, ranked, each tied to specific evidence from the conversations and aimed at the stated goal. For each, give the move, why now (the evidence), and the expected effect. Skip generic advice — if the evidence does not support a confident recommendation, say what is missing and what to find out next instead. ## Output Format ### Next best action — [Account / Contact] **State of play** — 2-3 lines on where things stand right now, from the conversations. **Recommended moves** (ranked, 1-3): 1. **[The move]** — *Why now:* [evidence from a specific conversation]. *Expected effect:* [what it unlocks]. **What we don't yet know** — the open question(s) that would most change the recommendation, and how to get the answer. ### When there is no data If conversation data is unavailable, give the best `account_research`-based suggestion and flag that it is not grounded in recent conversations.
Created by
Rowan Bailey
Senior Director, Product
Provided by
ZoomInfo ↗Capabilities
- Reads the current conversation state with conversation_intelligence
- Pulls deal stage and stakeholder context via account_research
- Ranks one to three concrete moves, each tied to specific evidence
- Names the why-now and the expected effect for every move
- Surfaces the open question that would most change the recommendation