Build a strategy translator for every audience.

What the AI will do

• Learns your strategy and the actual people it must reach, then develops a plan to inform, inspire and influence each audience.
• Builds a reusable strategy-communication tool and produces the real assets for a first campaign: the chosen decks, memos, emails, long document, short-message sequence, game or video.

What you can provide

• A strategy, leadership notes or a rough account of what is changing and why.
• Access to relevant audience and project records, plus any existing communication channels or brand materials.

Where you'll take part

• Clarify the strategic choices and what you want each audience to understand, feel or do.
• Choose the communication approach where a decision is needed and review the completed assets before any authorized distribution.

What you'll get

A reusable strategy translator plus a coherent first communication campaign with completed assets in the chosen formats, grounded in real audience evidence. Any format or distribution capability that remains unavailable is identified precisely.

Activity context

The board, a plant manager and the team selling your product may all need to understand the same strategy. They are unlikely to need the same explanation. Build a tool that knows what each audience cares about and turns the strategy into communication that can actually move them.

For the user

Begin with the strategy in whatever shape it is in. The AI will investigate the audience context and make a first campaign, then leave you a tool for the next one. You will clarify important strategic ambiguities, choose the approach and review the actual words, slides or experience.

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

Establish the strategy and the change it needs to produce

Build a reusable strategy translator and use it to create a complete first communication campaign. The campaign should inform, inspire and influence distinct actual audiences while preserving the same underlying strategy. Produce the assets in the forms we choose, ready to use after review.

Start with my strategy document, leadership notes or rough account. Search relevant strategy drafts, decision records, leadership and project meeting transcripts, email and chats, including WhatsApp where accessible, plus calendar invitations, project plans and earlier announcements. Use initiative names, decision dates, leaders and distinctive strategic phrases to locate the underlying choices and their history. Establish the current authoritative strategy, what is changing, why now, what remains undecided and what claims are supported. Distinguish an adopted decision from a proposal; find explicit superseding decisions rather than relying on file timestamps.

Ask focused questions about consequential gaps after investigating. Extract the core strategic account: the situation, the choice, the reasoning, the intended benefit, the tradeoffs, what people will experience and what happens next. Confirm interpretations that would otherwise become decisions or promises on my behalf. This core account is the source of truth for every audience version.

Find the actual audiences and what matters to them

Identify the people or defined groups who must receive the communication from attendee lists, organization and project roles, correspondence, customer or partner records and prior communication plans. A label such as “employees” may conceal materially different situations: people whose work will change, managers who must explain the change, and people who simply need to understand its purpose.

Search their relevant emails, messages, questions in meeting transcripts, previous responses, objectives and operational records. Look for expressed concerns, incentives, interests, existing knowledge, vocabulary, relationship history and the decisions or actions each group controls. Use the evidence to establish how the strategy intersects with their work. Record source references and dates, and distinguish actual stated views from plausible inferred reactions.

Create a concise brief for each materially distinct audience: who they are, what they currently understand, why the strategy matters to them, what might be difficult to believe, what we need them to understand or do and which real evidence supports this picture. Ask me about important missing audiences or unsupported assumptions. Preserve unknowns where no evidence exists; simulation cannot establish a person's actual views.

For many audiences or a large record, split evidence collection into bounded audience or source assignments with explicit periods, source references and deliverables. Maintain a coverage record and reconcile shared facts centrally. Use successive waves or separate passes if agents are unavailable.

Choose how the communication should unfold

Develop a campaign recommendation from the strategic account and audience briefs. Specify the desired understanding, feeling and action for each audience, the evidence that could make the message credible, the sender, sequence, channel and timing, and opportunities to hear back. Consider who needs context first and which explanations depend on a prior decision or announcement.

Choose the form for its purpose. Possibilities include a single substantial strategy document people can revisit; a deck for a real meeting with supporting speaker notes; a decision memo; prewritten emails; short messages spaced over days or weeks; a small game that lets people experience a strategic tradeoff; or a video that makes an unfamiliar future concrete. Do not force every audience into a deck, and do not make every possible format. Recommend a coherent combination and, when a meaningful decision remains, show two concrete treatments with a short specimen so I can choose. Use existing decisions without repeating approval requests. Wait on choices that determine production while continuing independent work.

Inspect actual access to the source records, asset-production tools, destination formats and intended communication channels. Consult current official documentation for tool-specific capabilities when needed. Test the formats you propose to produce; a promise to create a video is not a rendering capability. Investigate available setup and permitted alternatives before asking for a specific user or administrator action. With supplied excerpts alone, build a first campaign and label the audience-evidence limit; do not imply a connected reusable system is operating.

Produce the first campaign and the reusable tool

Build the tool in the available environment. Give it a clear way to accept a new or revised strategy, retrieve or ingest supporting records, refresh dated audience briefs, record confirmed strategic choices and produce audience-specific assets. Retain the common source account, source references, chosen campaign approach, completed assets and version history so the next run can identify what changed. Keep unconfirmed strategic changes visible for decision. Provide a simple usable interface or supported workflow rather than a prompt collection the user must assemble.

Create the complete first campaign through this tool. Write the actual opening, explanation, evidence, examples, transitions and requested action for each selected asset. Keep strategic commitments, numbers and tradeoffs consistent while changing the depth, language and relevance for each audience. Draw on evidenced audience concerns; do not flatter an invented persona. Inspiration should come from a credible possibility and its significance, with the practical implications made clear.

For each chosen form, finish the deliverable:

• A deck needs actual slides, readable design and speaker notes appropriate to its meeting, not slide titles alone. A memo or long strategy document needs the complete argument, necessary evidence, decisions and usable navigation.
• An email campaign needs full subject lines and bodies. A spaced short-message campaign needs the exact messages, intended recipients or groups, sender, cadence and sequence logic. Each message must contribute something while the sequence builds understanding.
• A game needs playable rules, decisions, feedback and a working experience demonstrating the intended tradeoff. Review what players actually learn, including whether scoring or winning implies a strategic claim we did not intend.
• A video needs the completed rendered video when the available tools support it, with a script, visuals, narration or captions as appropriate. Inspect the final playback. If rendering is unavailable, investigate a usable production path and agree an achievable alternative; a script and storyboard alone must be labeled unfinished video production.

Use bounded creative or audience agents where available. Give each the established core account, its evidence-backed audience brief, the actual selected format and clear deliverable. Complete independent audience treatments before reconciling them. The lead owns cross-campaign consistency and production; do not hand the main drafting burden back to me or a colleague.

Test understanding and repair the assets

Give fresh reviewers the completed assets, necessary strategy evidence and their respective audience briefs without the author's explanation of what the communication was intended to achieve. Ask them to state what they understand, what feels unsupported, what they would ask next and what action they think is expected. These are simulated audience responses, not proof of real audience reaction. Keep each audience pass independent until synthesis. If independent agents are unavailable, use separate bounded review passes and disclose shared context.

Compare the recovered meaning with the intended strategic account. Repair misleading simplifications, inconsistent promises, unexplained terminology and misplaced calls to action. Render and inspect documents and slides, play the game and video where selected, and check links, sequencing and readability in the actual delivery formats. Recheck the affected assets after corrections.

Demonstrate reuse by changing a controlled input or confirmed audience need and regenerating the affected asset. Verify that it changes for the right reason, retains the authoritative strategic commitments and preserves the prior version. Return the real first-campaign assets for my review alongside the plan, tool location and brief operating instructions. Incorporate my material corrections.

Deliver the campaign and its use

Deliver the reusable tool, evidence-backed audience briefs, common strategic account, communication plan and completed assets with a clear next action for each intended audience. State which capabilities were demonstrated and which remain partial. A strategy template, outline, script awaiting production or access request is not the promised completed campaign in that format.

Treat publishing or sending as a separate action within whatever authority I have actually given. If distribution is authorized, show the exact assets, destinations and timing covered by that authority, execute the agreed distribution and verify its outcome. Otherwise leave the completed campaign ready for use. Identify simple feedback to collect from real audiences—such as the questions they ask and their understanding of the next action—so a subsequent tool run can improve the communication from evidence rather than simulated approval.

Done when

You have a reusable tool demonstrated on your strategy, a communication plan for the actual audiences and the completed first campaign in the chosen formats. The assets preserve the strategy, have been reviewed and repaired, and are ready for use; any uncompleted production or distribution is named explicitly.

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.