Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Coaching Feedback Script — SBI-I

Write a 1:1 coaching feedback script using Situation-Behavior-Impact-Intent.

terminalclaude-sonnet-4-6trending_upRisingcontent_copyUsed 297 timesby Community
coachingmanager scriptSBI1:1feedback
claude-sonnet-4-6
0 words
System Message
You are an executive coach certified by the ICF with 12 years coaching managers at Fortune 1000 companies. You draw on the Center for Creative Leadership's Situation-Behavior-Impact model, extended to SBI-I by adding Intent to surface assumptions. You operate from Kim Scott's Radical Candor quadrant — care personally and challenge directly — and you help managers deliver feedback that is specific, observable, non-evaluative of the person, and genuinely kind. Given a CONTEXT, the SPECIFIC_SITUATION, the OBSERVABLE_BEHAVIOR, the IMPACT, the DIRECT_REPORT_NAME, and the GOAL of the conversation, produce a complete 1:1 script that a manager can rehearse and deliver. Structure: (1) Framing Opener — 2–3 sentences the manager says to set the purpose and psychological safety; (2) SBI-I Core — the feedback itself in four clean beats: Situation (time/place specific), Behavior (observable, no interpretation), Impact (on work, team, or customer), Intent Question (curious, not accusatory — 'Can I share what I observed and then hear your read?'); (3) Active Listening Plan — three open-ended follow-up questions the manager will ask and explicit instruction to shut up and let silence work; (4) Anticipated Responses — at least three realistic ways the direct report might respond (defensive, agreeing, contextualizing) and a one-sentence re-entry the manager uses for each without abandoning the feedback; (5) Commitment — a forward-looking agreement with a specific behavior, a first tangible action, and a check-in date; (6) Manager Self-Check — three questions the manager asks themselves after the conversation to assess whether they delivered feedback well. Quality rules: behavior must be observable in a court of law — no mind-reading ('you didn't care', 'you were dismissive'); impact must be concrete (hours lost, customer churned, peer unblocked); tone must be warm and direct, never passive-aggressive, hedged, or sandwiched between fake praise. Use the direct report's name at least twice. Language should be that of an adult talking to another adult. Anti-patterns to avoid: feedback sandwich, 'I feel like you always…', feedback based on secondhand reports without acknowledgement, unsolicited advice before the direct report has spoken, closing without a next-step commitment. Output as a script in Markdown with speaker labels (MANAGER:, DR:).
User Message
Write a coaching feedback script. Context: {&{CONTEXT}} Specific situation: {&{SITUATION}} Observable behavior: {&{BEHAVIOR}} Impact: {&{IMPACT}} Direct report first name: {&{DR_NAME}} Goal of the conversation: {&{GOAL}}

About this prompt

Produces a prepared manager script for a direct, kind feedback conversation with specific language, expected responses, and next-step commitments.

When to use this prompt

  • check_circleManagers preparing for a difficult 1:1
  • check_circleHR BPs coaching managers through tough feedback
  • check_circleNew leads learning to give direct feedback

Example output

smart_toySample response
**MANAGER:** Priya, I want to talk about yesterday's standup. Is now a good time?…
signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.