ResearchNeeds scheduled runs, not available yet

Competitor tech and product changes

Lists new technologies on competitor sites and diffs their release notes pages week over week. Your agent does the diff.

ResearchNeeds scheduled runs, not available yet

Competitor tech and product changes

Lists new technologies on competitor sites and diffs their release notes pages week over week. Your agent does the diff.

4 providers

Cost per 1,000 competitor runs

reading live price

1 competitor
one run: 6 calls
per competitor: your Supabase
memory

The prompt

Copy one prompt, give it to your agent.

Edit the names and numbers, paste it, and the agent runs the job and shows the cost.

One run is one competitor.
2 steps across 4 providers.
Needs scheduled runs, not available yet. Run it by hand whenever you want.

Prompt: Competitor tech and product changes

Use looot to list the technologies these ten competitors started using since last Monday and read their release notes and changelog pages, then keep last week's text and report only what was added or removed. 1. Set up https://looot.ai/skill.md. 2. Connect my Supabase and create the table competitor_changes. 3. Upsert on a natural key and never overwrite my edits. 4. Store source, endpoint, cost and fetched_at on every row. 5. Show any price over one cent first and stop at my daily budget. 6. On a re-run, write only what changed. 7. Report rows added, rows changed and total cost.

Give this to your agent

Setup command

set up looot for the Competitor tech and product changes recipe - https://looot.ai/recipes/competitor-tech-and-product-change-watch/skill.md

Set up once

Then paste any recipe.

Paste one prompt into your agent

Set up looot

Done, looot is connected.

Copy one prompt from /connect into Claude Code, Cursor, or any MCP agent. No SDK, no dashboard click-through first.

Your agent finds the right operation

Hunter$0.0265

Exa$0.0090

Diffbot$0.0032

The agent finds the operation it needs and sees the price first. It calls nothing blind.

You watch what it cost

Hunter$0.0265

Exa$0.0090

Diffbot$0.0032

Total$0.0387

Every call settles for its quoted price and lands in the ledger. You always know what ran and what it cost.

Steps

The calls behind this recipe

Your agent picks each endpoint. Prices are the cheapest live endpoint for the step.

01
List new technologies
PredictLeads
BuiltWith
Cheapest$0.0100 / lookup
company.technographics, 1 lookup per competitor
02

Every run lands in your Supabase

The prompt tells your agent to write one row per result to your own Supabase and skip rows it already has. looot does not store them. See the build kit.

Keep going

Pricing page monitor
Reads competitor pricing pages and reports when a plan name, price or limit changes. Your agent needs another tool for alerts.
Landing page teardown
Reads a landing page and lists its tech stack, headline, offer, proof and call to action, then suggests what to test.

FAQ

Questions about this recipe

Yes. The agent runs 2 steps through looot: list new technologies, then read release and changelog pages. You give it the prompt on this page and the inputs.

Paste the prompt on this page into your coding agent. It sets up looot, finds the endpoint for each step, checks the price and runs the cheapest one that fits. Edit the names and numbers first.

You pay per call, and the price depends on the provider the agent picks. The web version of this page reads the cheapest price for each step live from the catalog and shows the cost per 1,000 competitors when every step is priced.

The providers behind this recipe are predictleads, builtwith, jina, firecrawl. The catalog shows each endpoint's price before you run it.

This recipe is a watch and needs scheduled runs, which are not available yet. You can run it by hand whenever you want, and the agent will report what changed.

The prompt tells your agent to write one row per result to your own Supabase project, with the source, the endpoint, the cost and the time. looot returns the data and bills the call. It does not store your rows.

looot returns data and does not do page diffs. Your agent needs another tool for that part.

For agents

recipe: Competitor tech and product changes
category: Research
run: competitor
memory: your Supabase
schedule: needs scheduled runs, not available yet
step: List new technologies: predictleads builtwith
step: Read release and changelog pages: jina firecrawl
setup: https://looot.ai/recipes/competitor-tech-and-product-change-watch/skill.md
llms.txt: https://looot.ai/llms.txt
updated: 2026-10-19

markdown /recipes/competitor-tech-and-product-change-watch.md

Try this recipe with your own agent.

Start your workspace, top up, and paste the prompt into the agent you already use.

Start your workspace See other recipes