Why your reps need an always-on coach

Sales leaders and RevOps pros all hit the same brick wall: once your team’s calendar explodes with 30, 50, or 100+ calls per day, individual coaching becomes impossible. Yet CSO Insights research shows sales teams that operate under a structured coaching program see win-rates rise by 28% compared to teams without one.

Hypermode Agents let you embed a sales coach in every call, automatically reviewing transcripts and DM’ing actionable feedback to the rep within minutes. Below is the exact blueprint we use internally—feel free to copy-paste it into your own workspace and start coaching at scale today.

The anatomy of a sales coach agent

1. Key components

• A trigger: the moment a call ends, your “conversation intelligence platform” (Gong, Chorus, Claap, etc.) finalizes the transcript.
• Evaluation engine: custom rubric tied to your methodology—MEDDPICC, SPICED, Force Management, you name it.
• Workspace where reps receive notifications (Slack, Teams, email, etc.)
• Optional: CRM API key (Salesforce, HubSpot, Attio) to log scorecards

2. High-Level Flow

1. Call ends → transcript finalized in Gong.
2. Gong fires a Webhook → Hypermode Agents connection.
3. Sales coach agent in Hypermode ingests transcript + metadata.
4. Agent applies your coaching rubric (system prompt).
5. Agent posts a threaded DM to the rep (and logs a coaching object in CRM).

The whole thing runs in ~60 seconds, costs pennies, and never sleeps.

Agent template

Copy the block below into a new agent in Hypermode threads. Simply adjust the scoring criteria whenever your priorities change (new product launch, SPICED methodology rollout, etc.). Here is an example MEDDPICC implementation.

## Description
Coaches AE's on the application of MEDDPICC

## Instructions

Identity: Hypermode MEDDPICC Sales Enablement Workflow

System Prompt: 

You are a sales enablement AI assistant for {Company}, a {breif description of your company}. Your primary role is to help Account Executives (AEs) qualify, advance, and close opportunities using the MEDDPICC methodology, tailored to {Company's} value proposition.

Your Workflow:

1. MEDDPICC Framework Reference
    - Always use this Notion/Google doc to understand our MEDDPICC methodology, grading rubric, and other company initiatives: {link to doc}
2. Call Transcript Analysis
    - When provided with a call transcript, analyze the conversation and:
        - Score each MEDDPICC element (1–5) with a brief rationale.
        - Identify at least five specific areas of improvement for the AE, referencing the framework.
        - For each area of improvement, provide a concrete alternative question, talk track, or action for future calls.
3. Slack-Optimized Feedback
    - Summarize the scoring and feedback in a Slack-friendly format:
        - Use clear section headers, bullet points, and relevant emojis for each MEDDPICC element.
        - Use the star emoji to indicate a score (1-5)
        - Clearly separate “Misses” and “Alternatives” for easy reading.
        - End with a summary and actionable next steps.
        - Offer to provide custom call plans, email templates, or checklists if requested.

4. Message Delivery
    - Always send the formatted feedback to every participant from {company}. Dont send to any other channels,
    - If the message fails, try four more times


Tone & Style:

- Be concise, actionable, and supportive.
- Use {Company}-specific language and value props.
- Always focus on helping the AE improve MEDDPICC rigor and move deals forward.

Example Output Structure:

📋 MEDDPICC Call Review – Hypermode Framework 📋 📊 Metrics: 2 > [Rationale] 💸 Economic Buyer: 2 > [Rationale] ... 🚨 Where We Missed the Mark & How to Improve 1️⃣ [Miss] 💡_Try next time:_ [Alternative] ... 🌟 Summary & Next Steps 🌟 - [Actionable bullet points] ...

Always ask if the user wants a custom call plan, email template, or checklist for their next meeting.

Wiring it up in Hypermode

1. Create the agent.
2. Add an HTTP trigger.
3. Connect Notion and Slack.
4. (Optional) Sync to CRM.
5. Deploy.

Total setup time: ~35 minutes, including coffee refill.

Operational tips and tricks

• Iterate monthly: Update the “Scoring Rubric” section to match evolving GTM priorities (e.g., new product line, multi-threading push).
• Leaderboards: Pull the data into your BI tool; rank reps by average score and improvement delta.
• Drill-down channels: Route low-scoring calls to #needs-help so frontline managers can jump in.
• A/B methodologies: Clone the agent, change prompts, and randomly split calls to measure which framework drives higher win-rates.

Objections you’ll hear (and how to nuke them)

“AI can’t capture nuance.”

We feed the full transcript plus CRM context. Scores correlate with win-rates. Nuance, delivered.

“Reps will ignore bots.”

Reps will ignore useless, unhelpful bots. It’s incumbent on YOU to deploy agents that deliver timely, context-rich insights and relevant feedback, and they’ll pay attention.

“I’ll never get engineering support for all the things I want to do with Agents.”

Fear not! The entire process listed above can be done in natural language with zero code.

“It’s a black box—we can’t tweak logic.”

Launching a new product or emphasizing new discovery questions? Simply update your agent’s system prompt. In minutes, you can align feedback with current product priorities, team goals, or company initiatives—no retraining or redeploying required.

“Finance won’t sign off on runaway token spend.”

Token costs are roughly $2.00 per hour. Assuming one min of agent time per call, thats $0.03 per piece of coaching feedback. Your CFO will think thats money well spent.

Ready to put a coach on every call?

You can keep manually reviewing 1% of your pipeline—or you can spin up an agent that scales the best version of you across 100% of customer conversations.

Start with Hypermode’s Hobby plan, fork the template, and give your reps their first AI coach before the next deal review.

Happy scaling—and may every call make quota.