Turn 360 feedback into a daily plan.

What the AI will do

• Read your 360 feedback and search relevant accessible work exchanges and calendar events for concrete examples and opportunities to practice.
• Help choose one or two behaviors, then turn them into small daily actions and a simple reflection plan.

What you can provide

• Your feedback report or comments in whatever usable form you have.
• Relevant work context and calendar access, if available; you can also describe upcoming situations.

Where you'll take part

• Correct the AI’s interpretation and choose or confirm the behaviors you want to practice.
• Review the daily actions and try a short rehearsal. Daily practice and reflection remain yours.

What you'll get

A practical plan for the next working week, tied to real situations where possible, with observable actions and a lightweight reflection record. It does not automatically schedule coaching or establish that your behavior has changed.

Activity context

“Be more strategic” or “listen better” is hard to do on Tuesday. A useful plan turns feedback into a small action you can recognize at the moment it matters.

For the user

Give the AI your feedback report or comments. It will investigate the relevant context, discuss the patterns with you, and build a short plan around behaviors you choose. You can correct its reading before any interpretation becomes a development goal.

Guidance for the AI

These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.

Start with the activity and the user's context

Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.

Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.

Check the capabilities needed for this work

Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.

When useful access is missing:

• Explain what you cannot reach and how that material would help.
• Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
• If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
• Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.

Ask focused questions and respect the answers

Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.

Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.

Keep evidence and independent contributions distinct

Distinguish evidence, inference, and missing information. Check your work against the source material.

Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:

• Give each agent a bounded brief and the context appropriate to its role.
• Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
• Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.

Produce, check, and revise the result

Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.

Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.

Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.

Your AI prompt

Turn my 360 feedback into a daily behavior plan I can actually use. Ground the plan in the feedback and real opportunities to practice, preserve what I already do well, and help me choose one or two changes. This activity produces a plan and a rehearsal; ongoing coaching, calendar changes and proven improvement are separate outcomes.

1. Read the feedback and investigate relevant situations

Start with the supplied feedback. Identify the review period, questions, rating scales, respondent groups and any examples that explain the comments. Preserve anonymity where the report uses it. Do not search for the identities of anonymous respondents.

Use the report's projects, situations and dates to search relevant accessible meeting transcripts, emails, chats, project documents and my calendar. Look for concrete exchanges that illuminate a theme and upcoming events where a different behavior could matter. For example, a comment about interrupting might connect to how I respond to proposals in a recurring meeting. Keep the observed exchange distinct from an interpretation of why it happened.

Try connections and useful source reads before requesting more material. If access is unavailable, investigate exports or another permitted route, then ask for the specific missing item. Welcome pasted feedback, rough notes or a described situation. Explain when the plan rests on recollection or generic opportunities rather than observed work and a current calendar.

Ask necessary questions one at a time. If a consequential point is unclear, state what the sources establish and ask the question that resolves it; continue independent reading while waiting. Establish what I hope will become easier or more effective through this work.

2. Separate recurring patterns from isolated observations

Create a working evidence map for a few candidate themes. Include supporting comments, contrasting evidence, respondent group where available, examples, dates and uncertainties. Repeated wording copied into a summary is not multiple independent observations. Account for the rating scale and missing responses before comparing scores. Do not average unlike measures into a false ranking.

Distinguish:

• A repeated behavior with several concrete examples.
• A concern specific to one setting or relationship.
• A broad label that still needs a behavioral example.
• A strength worth retaining while changing how it shows up.

Translate abstract feedback into observable actions without claiming motives or diagnosing personality. “Create room for disagreement” might become inviting a contrary view before expressing my own preference. Explain the link to the original feedback and where the translation is your proposal.

For a large feedback set, assign bounded respondent groups or themes to agents with the exact source excerpts, anonymization constraints, required evidence map and completion criteria. Track source coverage, run waves where necessary and reconcile overlap centrally. Without agents, use manageable passes or fresh-session handoffs containing anonymized sources, decisions and remaining coverage. Describe shared-context review accurately.

3. Agree the behavior before making it my plan

Show a concise synthesis, including strengths and material contradictions. Invite my correction and wait. Recommend one or two behaviors with a clear practical benefit and a plausible opportunity to try them. Where two choices differ meaningfully, explain the tradeoff through a concrete example instead of presenting a generic menu.

Ask which behavior I want to work on, or confirm a choice I already made. Do not turn your interpretation into my commitment without my agreement. For each selected behavior, write a plain statement of what I will do, in which situation, and what someone could observe. Keep goals within my control; another person's approval is not an action I can perform.

4. Build a small daily plan around actual opportunities

Use upcoming calendar events and relevant work to write a plan for the next working week, unless we agree another short horizon. For each working day include:

• The real event or recognizable trigger, with date and time where verified.
• One small action linked to a chosen behavior.
• A phrase, question or preparation note I can use in the moment.
• A brief alternative if the meeting changes or the opportunity does not arise.
• A reflection prompt asking what I did, what I observed and what to adjust.

Make the actions specific enough to rehearse. For listening, this could be summarizing a colleague's proposal and asking whether I have it right before offering my assessment. Fit the amount of practice to my actual workload. If no calendar is accessible, use triggers I confirm, clearly labeled as an adaptable plan rather than scheduled events.

Create a simple daily record I can reuse: opportunity, action attempted, observable result and next adjustment. Include a short end-of-week review that compares examples rather than inventing numerical improvement from a handful of attempts. Write the actual plan and record in a usable document or table. Do not silently create reminders, contact colleagues or enroll me in recurring coaching.

5. Check the plan, rehearse and deliver

Give a fresh reviewer the original feedback, relevant work evidence and completed plan, without the drafting rationale. Ask whether the selected actions follow the feedback, fit the situations, preserve useful strengths and avoid invented motives. Resolve findings before delivery. If independent review is unavailable, perform a separate pass and identify its limit.

Show me the plan and invite one brief rehearsal of a high-value situation. Wait for my response, give behavior-specific feedback, and adjust the action if it feels unnatural or misses the goal. Do not treat rehearsal as evidence of workplace change.

Deliver the revised plan, daily reflection record and evidence-linked explanation of the chosen behaviors. Identify any unverified dates or missing context. State whether I completed the rehearsal. The result is a practical week of actions and a way to learn from trying them, with ongoing practice left in my hands.

Done when

You have chosen one or two behaviors and have concrete daily actions, useful words to try and a simple reflection record. The plan distinguishes confirmed opportunities from adaptable suggestions and makes no claim that workplace improvement has already occurred.

These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.