Hire an AI earnings preview, call review and written update

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A preview with what matters, the numbers to watch and what counts as a surprise
• A tone read of the call: confidence, hedges and dodged questions
• A recap against the preview
• A written update: what changed, what did not, what to watch next

How it does the job well

• Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
• Show the calculation, inputs and period for every figure.
• Label actuals, estimates and forecasts clearly.
• Send tax, legal and regulatory questions to a qualified professional.

Mistakes it avoids

• Mixing cash and accrual figures, or different periods, in one comparison.
• Rounding or formula errors that do not tie back to totals.
• Giving personal investment advice.

What a good result looks like

An example, not your task: You write a newsletter or internal note on companies you follow.

• Preview. What matters this quarter, the numbers to watch, what would count as a surprise and questions you hope are asked.
• Tone read. Where management was confident, hedged or dodged questions, and how the tone compares with last quarter.
• Recap. The quarter against the preview, with every number sourced to the release.
• Written update. What changed, what did not and what to watch next quarter, with no buy or sell advice.
• HAND-BACK SUMMARY. Each step's file, any step not run, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Write the preview. Writes what matters this quarter, the numbers to watch and what would count as a surprise.
• The release lands. A pause. Wait for the release and the call. Paste the release and the transcript.
• Read the call's tone. Reads where management was confident, hedged or dodged, with a quote for each. It compares the tone with last quarter when you give it last quarter's transcript.
• Write the recap. Compares the quarter with the preview and names the source of every number, the release first.
• Write the update. Writes the update: what changed, what did not and what to watch next, with no buy or sell advice.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id cover-an-earnings-release-from-preview-to-written-update only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/cover-an-earnings-release-from-preview-to-written-update/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The company and what you already think matters
• After the release: the release and the call transcript
• Last quarter's call transcript (optional, for the tone comparison)
• Your past notes on the company (optional)

Helpful context (optional)

• Last quarter's transcript
• Your past updates
• The company's guidance from the last call

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• The company's investor site: The release, the slides and the transcript live there.
• Claude, ChatGPT or Gemini: Handles a long transcript in one chat and quotes the lines it relies on.

Functions and deliverables

• Earnings preview, call review and written update: Prepare for an earnings release, review the actual results and call, then write a sourced update on what changed.
  • A preview with what matters, the numbers to watch and what counts as a surprise
  • A tone read of the call: confidence, hedges and dodged questions
  • A recap against the preview
  • A written update: what changed, what did not, what to watch next
• Earnings preview writer: Get an earnings preview for any stock ticker: report date, what analysts expect, past beats and misses, and what to watch. Needs code and web access.
  • The expected report date
  • Analyst estimates for earnings and revenue
  • Past surprise history
  • A short list of what to watch
  Source: himself65.
• Earnings call tone analyst: Compare wording in earnings calls across quarters. Get quoted tone shifts, signs of uncertainty and clear limits on what the text can reveal.
  • A tone score from minus 1 to plus 1, with how it was worked out
  • The change in tone against prior quarters
  • Hedging and uncertainty words counted per 100 words
  • Three stress points from the Q&A, each with a quote
  • Places where tone and the reported numbers disagree
  Source: GAJETOso.
• Earnings recap writer: Get an earnings recap for any stock ticker: actual vs expected results, margin trends and the share price reaction, in one short read.
  • Actual versus expected results
  • Beat or miss sizes
  • Margin trends over recent quarters
  • Share price reaction to the report
  Source: himself65.
• Earnings update report writer: Write an earnings update report for a company you already cover. Get an 8 to 12 page note on the beat or miss, new estimates and your thesis.
  • An 8 to 12 page earnings update
  • Summary tables and 8 to 12 charts
  • Updated estimates and thesis check
  • Beat and miss analysis
  Source: nighomni123.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• You write a newsletter or internal note on companies you follow.
• You hold a stock and want a disciplined read of each quarter.
• Your past write-ups repeated the headline and missed the shift in tone.

Limits to check before starting

• You follow a private company or have no release and transcript: write notes by hand or ask your AI for a plain summary of what you do have.
• You only want a note before the release: run the Earnings preview writer skill by itself.
• You want the Company earnings adjustments and reliability reviewer in an annual report: use the workflow Company earnings adjustments and reliability reviewer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the company and what you think matters. It writes the preview before the release.
• After the call, paste the release and the transcript. It reads the tone and writes the recap.
• Read the update, check every number against the release, and publish or file it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/cover-an-earnings-release-from-preview-to-written-update for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.