AI Competitor Intelligence Report — Automatically Monitor What Your Competitors Are Shipping, Saying and Winning Every Week
Built by CortexMatrix ·
About this build
A Claude and Perplexity powered workflow that monitors up to 5 competitors every week across their product updates, pricing changes, content output, job postings, customer reviews and social activity — then synthesises everything into a structured weekly intelligence report that tells you what they are doing, why it ma
What was built
Built this after spending 3 hours on a Sunday manually researching 3 competitors before a board meeting and realising I had been doing this exact same work every quarter without ever building a system around it. The information was useful. The process was completely unsustainable. The workflow runs every Monday at 6am so the report is ready before the week starts. Step 1 — Competitor profile setup in Airtable Each competitor gets a row in a simple Airtable base with their company name, website, product URLs to monitor, pricing page URL, LinkedIn company page, Twitter/X handle, G2 or Trustpilot review page and any specific things to watch — for example a competitor who is known for aggressive pricing changes gets flagged for extra attention on the pricing dimension. Step 2 — Weekly research sweep via Perplexity Every Monday morning n8n triggers a structured research sweep for each competitor across 6 intelligence categories. Product updates — any new features, product announcements, changelog updates, beta launches or deprecated features from the last 7 days. Sourced from their blog, changelog, product hunt listings and tech press. Pricing changes — any changes to pricing pages, plan structures, trial lengths or promotional offers. The workflow compares against the previously logged pricing data to flag changes rather than just reporting the current price. Content and messaging — what topics are they publishing about, what keywords are they targeting, what narratives are they pushing in their marketing. Sourced from their blog, social posts and any press coverage. Customer sentiment — new reviews on G2, Trustpilot or Capterra from the last 7 days. Specifically flagged if there is a cluster of reviews mentioning the same problem or the same praise — clusters are signal, individual reviews are noise. Job postings — what roles are they currently hiring for and what skills are they requiring. Job postings are one of the most underrated competitive intelligence signals because they reveal strategic priorities before any announcement is made. A competitor suddenly hiring 5 ML engineers tells you something their blog will not say for another 6 months. Social and press mentions — any significant social content, interview mentions, podcast appearances or press coverage featuring the competitor or their leadership team from the last 7 days. Step 3 — Intelligence synthesis via Claude All 6 research categories across all competitors get passed to Claude with a structured prompt that does four things. Significance scoring — for each piece of intelligence Claude rates it Low, Medium or High significance based on how likely it is to affect the competitive landscape or require a response. Pattern identification — Claude looks across all competitor activity in the week to identify whether multiple competitors are moving in the same direction simultaneously, which often signals a market shift rather than just individual company decisions. Implication analysis — for each High significance item Claude writes one paragraph on what this means for the business being monitored — not just what the competitor did but what it suggests about their strategy and what the appropriate response might be. Strategic summary — one page overview of the most important competitive developments of the week, written for a founder or product leader who has 5 minutes not 2 hours. Step 4 — Report delivery to Notion The full intelligence report gets written to a dedicated Notion page automatically. Each report is dated and archived so over time there is a searchable history of competitor activity. The Notion page structure is consistent every week so the leadership team knows exactly where to look for each type of intelligence. Step 5 — Slack summary A condensed 5 bullet point summary of the week's most significant competitive developments gets posted to a dedicated Slack channel Monday morning. This is the version most people actually read — the Notion report is there for anyone who wants to go deeper on a specific item. Step 6 — Airtable trend logging Key metrics get logged to Airtable weekly — pricing changes, new product features, review sentiment scores and job posting counts. After 8 to 12 weeks this data starts revealing patterns that are invisible week to week — a competitor whose review sentiment has been declining for 6 weeks, a competitor who has been quietly building out an enterprise sales team through job postings without any public announcement. What took the longest to get right: The significance scoring was inconsistent early on. Claude would rate minor blog posts as High significance and genuinely important pricing changes as Medium. Fixed by giving Claude explicit criteria for each significance level — High means this requires a response or changes our roadmap, Medium means this is worth monitoring but no action needed this week, Low means log it and move on. The job posting analysis was the most valuable thing I added after the initial build but it was also the hardest to implement. Perplexity does not always surface job postings reliably for smaller companies. Fixed by searching directly for the company name plus site:linkedin.com/jobs in the search query which significantly improved job posting detection. The report was too long in early versions. Nobody was reading past page 2. Cut it to a maximum of one page per competitor and moved supporting detail to expandable sections in Notion. The constraint of one page per competitor forces better prioritisation in the synthesis step. Results after 10 weeks: Caught a competitor repricing their mid-tier plan by 23 percent in the same week it happened rather than 6 weeks later when a customer mentioned it. Was able to prepare a response messaging document before the first customer asked about it. The job posting analysis flagged a competitor hiring aggressively for enterprise sales roles 3 months before they publicly announced an enterprise product tier. Had 3 months to prepare rather than being caught off guard. The customer sentiment tracking identified a cluster of negative reviews on a competitor's platform around their mobile app — 7 reviews in 2 weeks all mentioning the same crashes. Informed a product decision to prioritise our own mobile experience before we had even seen customer demand for it. What I would build next: An automated alert that fires immediately rather than waiting for the Monday report when a High significance competitor event is detected — a competitor pricing change, a viral negative review cluster or a major product launch announcement. The weekly rhythm is great for strategic planning but some things warrant same-day awareness. Will share the full n8n workflow JSON and Claude synthesis prompt in the comments for anyone who wants to deploy this.