MARKET RESEARCH
On-Demand Earnings Theme Deep-Dive Agent
Ask in chat about any competitor's earnings narrative; an agent fetches recent transcripts, traces a theme across quarters with cited quotes.
How it runs
The automated pipeline, trigger to output.
- TriggerChat question about a company's theme over time
- ActionRetrieve the relevant quarterly transcriptsFirecrawl
- ActionExtract theme mentions and quotes per quarterOpenAI
- LogicAssemble trajectory and flag missing quarters
- OutputReply in chat with sourced multi-quarter analysis
What it does
Gives analysts a conversational way to interrogate earnings narratives. You ask something like 'How has Competitor X talked about pricing power over the last four calls?' and the agent gathers the relevant transcripts, finds where that theme appears, and answers with a quarter-by-quarter trajectory backed by direct quotes and call dates — instead of you grepping transcripts manually.
When to use it
Use it for ad-hoc research mid-analysis, when prepping for a meeting, or when a structured tracker doesn't yet cover the exact angle you need. Best when questions are exploratory and a fixed schedule wouldn't anticipate them.
How it works
- 1A chat message starts the agent with a question about a company and a theme.
- 2The agent decides which quarters it needs and uses Firecrawl to retrieve the relevant transcripts.
- 3It reasons over the text to locate the theme and pull representative quotes per quarter, calling OpenAI for nuanced extraction where needed.
- 4It assembles a sourced, quarter-by-quarter trajectory and flags any gaps in available transcripts.
- 5The answer is returned in the chat thread with quotes, dates, and links for verification.
Set it up
What you configure once, before turning it on.
- 1Connect FirecrawlCrawl, scrape, structured extract.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Market Research workflows
Hiring Surge Detector with Slack Alert
Detects when a target account's open-role count jumps above its recent baseline and posts a ranked Slack alert to the GTM channel so reps can act on a company that is clearly…
Tech-Stack Shift Inference from Job Descriptions
Reads new job descriptions for target accounts, uses an LLM to extract named technologies and infer stack changes.
Enrich Inbound Accounts with BigQuery Firmographics and Score Fit
When a new account row lands in Airtable, joins it against BigQuery public business datasets to attach firmographic attributes.
Blend BigQuery TAM with Live Competitor Signals into a Notion Brief
On demand, sizes a chosen segment from BigQuery public data, gathers current competitor signals via Brave Search, and synthesizes a one-page market brief into Notion.
Allocate Sales Territory TAM from BigQuery Geo Data to HubSpot
When triggered by a webhook, queries BigQuery public ZIP-level business data to compute TAM per sales territory.
Discover Adjacent Segments from BigQuery and Rank Expansion Bets
On a schedule, scans BigQuery public industry data for fast-growing NAICS sectors adjacent to your core segments, scores them as expansion bets.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.