- Home
- Skills
- Finance & Accounting
- Earnings Call Evidence Extractor
Works with the AI Agents you already use
Earnings Call Evidence Extractor
Extracts structured evidence, guidance changes, and management commitments from earnings call transcripts.
$16.99
Earnings Call Evidence Extractor
Example session with this skill installed
Analyze the attached Q3 transcript for TechCorp. Focus on margins and AI infrastructure spend. Compare against the Q2 guidance I provided earlier.
- Read your context and instructions
- Compiled the earnings call evidence
I have analyzed the TechCorp Q3 Earnings Call transcript (Full) and compared it against the supplied Q2 guidance notes.
Earnings Call Evidence Brief: TechCorp Q3
Source Scope: Full transcript provided; Speaker labels and section headings present.
Executive Summary: Management reported record infrastructure spend driven by AI demand. Gross margins compressed by 120bps due to hardware ramp-up. CFO confirmed a shift in full-year capex guidance to the high end of the previous range.
Evidence-Linked Statements
| ID | Topic | Speaker | Classification | Statement / Paraphrase | Locator | Research Significance |
|---|---|---|---|---|---|---|
| 001 | AI Capex | Jane Doe (CFO) | Guidance | Raising FY infrastructure spend to $4.2B-$4.5B. | Remarks, p. 4 | Direct impact on FCF |
| 002 | Margins | John Smith (CEO) | Management interpretation | Margin dip is "transitory" during H1 2024 ramp. | Q&A, 14:20 | Execution risk indicator |
| 003 | Demand | Jane Doe (CFO) | Reported fact | Backlog for AI servers grew 40% QoQ. | Remarks, p. 2 | Revenue visibility |
Guidance Changes and Outlook
- Metric: Total Capital Expenditure
- Prior Guidance: $3.8B - $4.2B
- New Guidance: $4.2B - $4.5B
- Direction: Increase
- Reason: Accelerated procurement of H100 clusters.
- Source Location: CFO Remarks, Page 4.
Management Commitment Tracker
- Commitment: Achieve 55% Gross Margin floor.
- Timeframe: By end of Q4 2024.
- Status: Aspirational (CFO noted "dependent on supply chain stability").
- Owner: Jane Doe (CFO).
Risks, Caveats, and Unresolved Questions
- Risk: Supply chain bottlenecks for liquid cooling components (CEO mentioned at 22:15).
- Analyst Challenge: Question regarding the ROI timeframe for current AI spend remained partially unanswered.
- Unresolved Question: Exact breakdown of "Other Operating Expenses" which spiked 15% this quarter.
Next steps
- Review the Q4 supply chain report for liquid cooling vendors.
- Cross-reference the $4.5B capex target with competitor H100 deployment schedules.
- Prepare follow-up regarding the specific margin recovery levers for Q1.
Connects securely to your tools. The creator never sees your data.
About this skill
Manually parsing earnings transcripts for material changes, guidance shifts, and management commitments is slow and prone to oversight. This skill automates the extraction of evidence from earnings call transcripts, organizing data into structured research briefs with precise source attribution. It eliminates the need to cross-reference speaker labels and timestamps manually, ensuring every claim is linked back to its specific location in the text.
What it does
- Extract material statements captures performance data, demand signals, and operational updates.
- Classify evidence categorizes items as reported facts, management interpretations, or forward-looking claims.
- Track guidance changes identifies shifts in outlook by comparing current statements against supplied prior-period data.
- Monitor commitments builds a tracker for explicit promises, targets, and milestones with stated timeframes.
- Identify risks and caveats flags management-cited uncertainties and unanswered analyst questions.
- Generate follow-up questions creates research prompts tied directly to specific evidence items or contradictions.
How it works
- Source ingestion analyzes the transcript to establish boundaries, reporting periods, and available locators like timestamps or page numbers.
- Attribution mapping separates prepared remarks and management answers from analyst questions to prevent misattribution.
- Structured extraction populates an evidence-linked statement table using eight distinct classification labels.
- Research synthesis produces a brief containing the commitment tracker, guidance log, and risk analysis.
Frameworks & tools
This skill is designed for equity research, financial analysis, and investor relations workflows. It works with raw transcripts, call notes, or excerpts in Markdown or text formats.
Why this beats prompting it yourself
Generic prompts often hallucinate speaker attributions or miss subtle guidance changes. This skill uses a rigorous classification system and mandatory locator linking to ensure every point in the research brief is anchored to the source text.
Use cases
- Quarterly earnings analysis to quickly isolate guidance shifts and new management targets.
- Competitor benchmarking by extracting specific operational metrics and product roadmaps from peer calls.
- Preparation for 1-on-1s by generating evidence-backed follow-up questions for management.
- Due diligence to audit historic management commitments against current results.
Known limitations
Does not independently verify company claims or provide investment recommendations. Guidance comparisons require the user to supply prior-period data.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
Requires user-supplied transcript text. Cannot independently verify the truth of management statements or provide buy/sell recommendations. Guidance comparison requires prior-period input.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 27 days ago
Permissions
No special permissions declared or detected