What it does
Fetches and parses the most recent earnings call transcript to extract management’s forward-looking guidance on revenue and operating margins. When guidance is available, it provides a better starting point for DCF assumptions than extrapolating historical trends. This skill runs as Phase 5.5 — after cost of capital and before growth & profitability. It is optional: if no transcript is found or no usable guidance is extracted, the pipeline proceeds with LTM-derived defaults.Why earnings guidance matters
Historical financials tell you where a company has been. Earnings guidance tells you where management expects it to go. For companies undergoing rapid change — high-growth tech, turnarounds, recent IPOs — the gap between past performance and forward expectations can be enormous. When management provides explicit guidance, the plugin uses the conservative end of any range as the default starting point, which the user can then adjust.What it extracts
The skill looks for guidance on four forecast variables:| Variable | Example guidance | How it’s used |
|---|---|---|
| Revenue — Year 1 | ”We expect FY2026 revenue of $12–13B” | Overrides the Year 1 revenue growth rate in the DCF |
| Revenue — Long-term | ”Exit run-rate of $17–19B” | Informs year 10 revenue growth target |
| Operating margin — Year 1 | ”Adjusted operating income of $900M–1.1B” | Overrides Year 1 margin assumption |
| Operating margin — Long-term | ”25–30% long-term margin target” | Overrides the Year 10 target margin |
- Sales-to-capital — CapEx guidance, useful for cross-checking reinvestment assumptions
- Cost of capital — refinancing commentary, interest rate improvements
How it works
Determine the expected earnings call
From
statements_required, identify the most recent filing by fiscal period end and map it to the corresponding earnings call quarter (e.g., 10-K with FY end 12/31/2025 → Q4-2025).Check the cache
Look for an existing
guidance-Q{N}-{YYYY}.json in the ticker cache. If found, load and return it — no fetch needed.Fetch the transcript
Search for the transcript using a priority cascade: company IR website, Motley Fool, Investing.com, SEC 8-K exhibit. Fetches and filters the transcript to the most relevant 5,000–8,000 tokens (prepared remarks + forward-looking Q&A).
Extract structured guidance
An LLM prompt extracts guidance for each variable, including raw quotes, inferred numerical values, inference method, and confidence rating.
Inference methods
Management rarely says “our revenue will be exactly X.” The skill handles several patterns of guidance:| Pattern | Example | Method |
|---|---|---|
| Direct annual guidance | ”Revenue of $12–13B for FY2026” | direct_guidance |
| Growth rate applied | ”Approximately 140% growth” | growth_rate_applied |
| Exit run-rate | ”Exit run-rate of $17–19B” + Q1 guidance | exit_run_rate_interpolation |
| Quarterly sum | Per-quarter guidance that sums to annual | quarterly_sum |
| Derived from adjusted OI | ”Adj. operating income $900M–1.1B” ÷ revenue guidance | derived_from_adj_oi_guidance |
| Direct margin percentage | ”25–30% long-term margin target” | direct_guidance |
Mode behavior
| Mode | Behavior |
|---|---|
| Expert | Presents extracted guidance alongside industry benchmarks. User can accept, modify, or reject each value. |
| Novice | Presents guidance with explanations of what it means and how it was derived. |
| Feeling Lucky | Runs silently — applies guidance automatically with no user interaction. |
Output
Two files are saved per extraction to the ticker cache:guidance-Q{N}-{YYYY}.json— structured data consumed by growth-and-profitability and the lucky pipelineguidance-Q{N}-{YYYY}.md— annotated markdown with raw management quotes, inference reasoning, and confidence ratings
Edge cases
| Scenario | Behavior |
|---|---|
| No transcript found | Logs a warning and returns None. Pipeline proceeds with LTM-only defaults. |
| Transcript found but no revenue guidance | Saves JSON with null revenue values. LTM default is used. |
| Guidance is adjusted (excludes SBC) | Flags the adjustment type. User can decide whether to use GAAP or adjusted figures. |
| Low confidence extraction | Flagged in output. In Expert mode, user is asked to confirm. In Lucky mode, used but caveated in the transcript. |