MARKET RESEARCH
Quarterly Competitive Analyst Agent
Each quarter, an agent autonomously researches the full competitive set, gathers and cross-checks evidence from multiple sources.
How it runs
The automated pipeline, trigger to output.
- TriggerSchedule: quarterly kickoff
- ActionRead tracked list + prior memoConfluence
- ActionPlan and run multi-source researchExa
- ActionCross-check and scrape evidenceFirecrawl
- ActionDraft narrative strategy memoOpenAI
- OutputPublish cited memo to ConfluenceConfluence
What it does
Acts as a standing competitive analyst. Once a quarter it works through your competitive set, decides which sources to pull for each company, cross-checks claims, and writes a narrative strategy memo — trends, threats, and recommended responses — rather than a flat data dump. Every claim carries a citation.
When to use it
Use it for the quarterly strategy ritual where leadership needs synthesis and a point of view, not just raw signals. The agent handles the judgment calls (which competitor moved most, what it means) that a fixed pipeline can't.
How it works
- 1A quarterly schedule starts the analyst agent.
- 2The agent reads the tracked competitor list and prior memo from Confluence for continuity.
- 3It plans and runs research per competitor, drawing on Perplexity, Exa, and Firecrawl as each question demands, and reconciles disagreements between sources.
- 4OpenAI drafts the narrative memo with an executive summary, per-competitor movement, and recommended actions.
- 5The agent publishes the cited memo as a new Confluence page under the strategy space and links it from the prior quarter's.
Set it up
What you configure once, before turning it on.
- 1Connect PerplexitySearch-grounded answers with citations.
- 2Connect ExaNeural search across the web.
- 3Connect FirecrawlCrawl, scrape, structured extract.
- 4Connect OpenAIModels, embeddings, files.
- 5Connect ConfluenceSpaces, pages, blueprints.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Market Research workflows
Weekly Materiality-Ranked Filing Digest by Email
Each Friday, aggregates the week's regulatory filings across the coverage universe, ranks them by materiality.
Earnings Keyword-Spike Alert into Linear
Scans new earnings-call transcripts for a set of strategic keywords you care about, and when a competitor's mention frequency spikes above its historical baseline.
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.
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.
Cross-Competitor Theme-Shift Analyst
An agent that gathers the latest earnings transcripts across all tracked competitors, compares this quarter's themes against the prior quarter stored in Coda.
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.