# April 21, 2026
## HockeyStack Revenue Agents: Now Live!
Your CRM, call recordings, and engagement data contain the complete blueprint of how your company wins deals. HockeyStack Revenue Agents extracts it and puts it to work.
**Two agents. One system.**
**Prospecting Agent** creates pipeline — breaks into new target accounts and generates expansion opportunities within your existing customer base. Identifies intent signals, finds the right champion, and builds personalized outreach strategies.
**Deal Agent** closes pipeline and protects revenue — moves open deals forward, manages renewals, and monitors customer health. Assesses every deal against your winning patterns, identifies blockers, and tells reps exactly what to do next.
**How it works**
HockeyStack's ML pipeline analyzes every won and lost deal in your history to discover the specific patterns that drive outcomes — which actions, stakeholders, timing, and engagement sequences separate wins from losses. Agents then execute on those patterns across every rep, every deal, automatically.
This isn't generic AI suggestions. Every action is grounded in what your data says actually works.
**What your team gets**
* Reps get a prioritized daily queue with next actions, drafted comms, account research, and meeting prep — ready to go every morning.
* Managers see which deals are drifting from the winning pattern and where coaching will have the highest leverage — without hours of pipeline reviews.
* Scores, signals, and insights write back to Salesforce, embed in your page layouts, and route to Slack.
**Self-improving by design**
Every completed task, dismissed recommendation, and closed deal feeds back into the blueprint. The system gets sharper the longer it runs — no manual tuning needed.
***
HockeyStack Revenue Agents is available now for teams on Salesforce and Gong. Get started at [hockeystack.com](https://www.hockeystack.com/).
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.hockeystack.com/release-notes/april-21-2026.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.