BotCurrent↗
← Back to examples

Official recipe · Research across apps

Update an earnings model and briefing slide

Source-backed example. Practical decision guidance is proposed and untested; this is not a full implementation guide.

The problem

Earnings updates must be reflected consistently in both a financial model and the presentation used to explain it.

Attributed source action

Retrieve earnings information, revise the financial model, and carry its context into a summary presentation.

Proposed review output

Proposed review artifact: Update-plan candidate with source-to-cell mapping, assumption changes and corresponding slide revisions.

Where this framing comes from
  • Core problem: Editorial purpose framing
  • Agent job: Attributed source documentation or report
  • Expected output: Original proposed guidance; not a source-reported result
  • Relevant job roles: Editorial purpose framing
  • Benefit type: Editorial purpose framing
Editorial framing and outcome limits

Describes the task’s purpose and intended output; measured benefit, safe unsupervised operation and successful delivery are not established by this framing.

Editorial synthesis based on the linked source. This framing does not add evidence of successful delivery or results.

Case-specific decision guidance · untested

Case-specific decision guidance and first checks are original proposals. The linked source supports the attributed task; this added guidance has not been executed.

Read the attributed source evidence and original caveats below ↓

Why use this

  1. An analyst updating an earnings model may need to carry new reported figures into both calculations and a briefing slide. A presentation can remain stale even when the workbook changes, or a model can accidentally blend reported results with new assumptions.

  2. This job could prepare a traceable update package linking source figures, affected cells and slide messages. Clear separation of actuals, estimates and unresolved definitions helps qualified reviewers assess the update before using it in an investment discussion.

Why an agent / simpler alternative

Useful judgment

Map earnings disclosures to model fields, identify changed definitions and keep presentation claims aligned with approved calculations.

Simpler alternative

Update manually when only a few well-defined cells and one existing slide are affected.

Unsuitable when

The workflow would recommend investments, publish unsupported forecasts or change authoritative models without review.

Proposed inputs

  1. Name

    Earnings evidence

    Owner

    Authorized analyst

    Minimum scope

    Relevant official figures, periods and explanatory notes

    Quality check

    Check amendments, units and reported versus adjusted measures

  2. Name

    Model/slide snapshot

    Owner

    Owner

    Minimum scope

    Affected workbook cells, formulas and briefing references

    Quality check

    Preserve baseline version and distinguish hardcoded values

Access and setup — proposed or unknown

Proposed minimum
  1. Use fictional disclosure excerpts and model/slide maps; no live data retrieval, spreadsheet recalculation or file edits.

Compatibility unknowns
  1. Current financial-data access, workbook formulas, slide linkage and runtime compatibility are unknown.

External actions requiring approval
  1. Financial-data sharing, authoritative model changes, briefing distribution and transactions require appropriate approval.

Expected deliverable and review checks

Proposed artifact

Update-plan candidate with source-to-cell mapping, assumption changes and corresponding slide revisions.

Critical checks
  1. Align periods/currencies; preserve formula lineage; keep reported and forecast values distinct; trace each headline to reviewed evidence.

Missing output evidence

This overlay adds no new output inspection, execution or validation; consult the referenced canonical source outcome limits.

Failure signals and proposed responses

  1. Signal

    A metric definition changes between periods

    Why it matters

    The model creates a misleading trend

    Proposed response

    Record the change and request a comparable basis.

  2. Signal

    The slide retains an old headline after a cell update

    Why it matters

    The briefing contradicts the model

    Proposed response

    List dependent slide claims and reconcile them explicitly.

Effort and cost — unknown

Setup work
  1. Define authoritative figures and update dependencies.

Ongoing review
  1. Qualified analysts review calculations and messaging before use.

Unknowns
  1. Disclosure completeness, model validity, export fidelity and review costs are unknown.

First check — proposed, unexecuted

Status

proposed_unexecuted

Synthetic fixture

Invent an earnings excerpt, two model cells and a slide headline with a changed metric definition; draft an update map only.

Acceptance checks
  1. Flag definition mismatch; separate actual/forecast; calculate no valuation and claim no updated result.

Stop conditions
  1. Stop if authoritative figures or approved model assumptions are unresolved.

Limits

  1. An update plan cannot establish financial accuracy, forecast reliability or investment suitability.

Tasks: Money & accountingDocuments & filesData & analysis

Useful for: Finance professional

Editorial relevance from the title and source-supported actions; not evidence of the operator’s occupation.
Claude CoworkIndependent testing: No

Editorial candidate. This is source-backed reporting or a documented workflow. BotCurrent has not independently tested this task. A proposed Canadian adaptation is not evidence of a Canadian deployment or compliance certification.

Original source

https://claude.com/resources/articles/cowork-plugins-finance ↗

Attributed to: Anthropic

Official recipe

Read the attributed source action above ↑

Original action type
cross_app_investigation
Source outcome limits
This official recipe describes a procedure; it does not prove successful execution or independently reproduced results.
Evidence attribution caveat
This official recipe describes a procedure; it does not prove successful execution or independently reproduced results.
Source approval description
Not specified.
Named tools
Claude Cowork; Excel; PowerPoint; equity research plugin
Model or version
Unknown
Publication date
2026-02-24
Source last checked
2026-10-14
Demonstrated in Canada
Unknown
Canadian availability
Unknown
Proposed Canadian adaptation
Use CAD consistently, identify Canadian reporting standards and have a qualified Canadian professional review assumptions; this is an adaptation proposal.
Recommended approval boundaries
Review outputs and source evidence; approve external messages, shared updates, access changes and consequential decisions before execution.