Turn 10 earnings calls into a strategy timeline.

What the AI will do

• Find the strategic question in your internal discussions and confirm the ten calls to examine.
• Track management commitments, analyst challenges and subsequent results across calls, releases and filings; reconcile the chronology and use a separate reviewer where available to check it.

What you can provide

• A company or comparison, an approximate period and the question you want the timeline to answer.
• Relevant strategy material or access to emails, chats and market discussions; the AI will seek the public call record.

Where you'll take part

• Confirm the exact ten-call scope before analysis.
• Clarify consequential ambiguity and review what the timeline means for your decision.

What you'll get

A dated, source-linked strategy timeline across ten calls, separating changes in management’s words from evidenced operating changes; unavailable calls remain explicit gaps.

Activity context

Ten earnings calls can reveal a strategy changing in public: a promise repeated, a metric quietly replaced, an analyst’s question that never quite gets answered. Turn those moments into a timeline you can inspect.

For the user

Start with the company and what you want to understand. The AI will propose the exact ten calls, retrieve the record and ask you to confirm the scope. It will do the comparisons and return the chronology and its strategic meaning. Missing transcripts can leave an incomplete timeline; recollection cannot replace the record.

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

Help me turn ten earnings calls into a strategy timeline. Trace what management promised, sustained, revised or abandoned, and distinguish changes in rhetoric from changes supported by operating evidence.

1. Confirm which ten calls answer the question

Use what I have supplied to identify the company or company comparison and period. Inspect and try connected sources, then search internal strategy documents, market reviews, relevant emails, chats including WhatsApp where available, calendar-linked discussions and meeting transcripts. Look for the competitive question, decisions we are considering and earlier interpretations of this company. Identify the intended readers’ concerns from their actual questions and roles.

Propose an explicit numbered list of ten calls, with company and fiscal period. Explain how that selection serves the question: for example, ten successive quarters for one company or a defined comparison across companies. Ask me to confirm the exact scope and wait before the ten-call analysis, unless I already specified and confirmed it. Resolve questions one at a time. Do not silently choose ten recent calls if a different period matters.

Try access before requesting exports. If internal connections are unavailable, investigate permitted alternatives and ask only for the relevant missing material. Rough context can orient the inquiry. Missing call records are more consequential: explain that a complete chronology requires them, and carry any unavailable calls as gaps rather than reconstructed quotations.

2. Assemble a dated source set

Retrieve transcripts, recordings when available, earnings releases and linked filings from company investor relations and official filing archives. Prefer the company’s transcript; identify the provenance of any third-party transcript and cross-check pivotal wording against official audio or documents where possible. Note unavailable Q&A, incomplete transcripts and paywalled or inaccessible sources.

For every call record its date, fiscal period, speaker identities, source links, transcript completeness and supporting release or filing. Keep call date separate from the period reported and the effective date of a policy or target. If a selected call cannot be obtained, ask whether to proceed with an explicit gap or replace it; wait on that scope change. Do not claim ten inspected calls when fewer were available.

Build a working chronology from oldest to newest. Record restatements, renamed segments, revised metrics and changes in definitions so later comparisons preserve their meaning. A new label or later mention does not alone establish an operating change.

3. Extract commitments and challenges independently

Divide the confirmed corpus into bounded consecutive periods or companies using agents where available. Brief each with exact sources, the common strategic question, extraction fields and assigned coverage. Its deliverable is a dated evidence table with passages, references, unresolved ambiguities and a check that every assigned call’s prepared remarks and Q&A were inspected. Use waves and track omissions centrally. Have adjacent-period assignments inspect their transition boundary where needed.

Extract:

• Strategic priorities and management’s explanation of how they create results.
• Commitments, targets, deadlines, resource decisions and qualifications.
• Analyst challenges, the response actually given and unresolved questions.
• Reported milestones, results and evidence offered for progress.
• New, revised or disappearing themes, without treating silence as proof of abandonment.

Tag statements as commitments, aspirations, descriptions of results or interpretations. Preserve qualifiers and contemporaneous context. If agents are unavailable, use fresh sessions or manageable sequential passes with explicit source, decision and coverage handoffs; identify shared-context checks accurately.

4. Link each development to what preceded it

Reconcile all extracted rows into a single timeline. Assign related statements a common theme so a promise can be followed through later calls. For each apparent change, show the earlier position, later statement, dates, evidence of actual action and what currently stands within the selected period.

Classify developments as reiterated, refined, delayed, reversed, fulfilled, unresolved or no longer mentioned, using evidence rather than an arbitrary requirement to find a dramatic shift. Link amendments explicitly. Test apparent operating changes against releases, filings and results; a management statement alone establishes what management said, not necessarily that implementation occurred.

Separate a changed explanation from changed capital allocation, product availability, customer activity or segment performance. Consider alternative explanations such as market conditions or metric redefinition. Identify where the record cannot resolve them. Ask me a focused question only when our purpose or internal context materially affects interpretation, and pause the dependent conclusion.

5. Review and deliver the timeline

Give an independent reviewer the assembled timeline and original sources, without the author’s rationale. Ask it to check chronology, faithful paraphrase, preserved qualifications, support for change classifications, missing contrary statements and arithmetic. Resolve material findings and retain genuine uncertainty. Use a fresh session if needed and disclose a shared-context fallback.

Deliver a readable timeline with date, theme, management’s position, subsequent evidence, interpretation and source link. Accompany it with a short account of the strategy’s trajectory, the strongest turning points, unresolved promises, implications for our original question and the ten-call coverage register. State clearly whether all ten were examined. End with the actual chronology and findings; do not portray absent evidence, simulated management motives or a designed follow-up inquiry as established history.

Done when

You have a reviewed chronology of the confirmed ten-call scope, or an explicitly agreed incomplete scope, with linked commitments, later evidence and clearly marked changes, continuities and gaps.

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.