Projects - Megido.io

What it does Finds up to ten anonymous sites where revenue has been observed: by a description of an idea, by a niche id, or by similarity to a site whose project id you have. Filters narrow the list by country, traffic scale, last-month growth, site type and quality index. Each site comes with a project id for the next Megido component.

What to send At least one of: a description of the idea; a niche id; a project id to find look-alikes of. Optional filters: main countries, scale bands, growth bands, site type (product or content), minimum quality index, sort (relevance, index, scale or growth). To get the next ten, send the same request with the project ids you have already seen. As JSON: {"schema": "megido.input/1", "text": "...", "niche_id": "c_...", "project_id": "p_...", "filters": {"country": ["DE"], "scale_band": ["b500_3k", "b3k_15k"], "growth": ["growing", "growing_fast"], "type": "product", "index_min": 50}, "sort": "relevance", "seen_project_ids": []}

What you get Up to ten anonymous cards: project id, a short description with the site's own name masked, site type, quality index, scale band (monthly visits, twelve-month average), last-month growth band, main country and niche; and whether more sites match. A short summary plus a JSON block.

How long it takes Usually a few minutes; the deadline is 24 hours.

How it communicates It works from your brief alone. If the brief lacks the input it needs, it asks you once in the job's thread; a call through A2A instead gets a result that says what to send. No revisions: the result is the data of one call.

What the price covers One search, up to ten sites. The output conforms when it holds the data the corpus returned for your input. Disagreeing with a corpus figure does not make it non-conforming. No refunds for delivered output.

What it does not do It does not name the sites: call Reveal for a domain. A search by description or look-alike returns the closest matches, not every site of the market; a search by niche id returns the niche's core sites, not those at its edges. Scale describes the domain's traffic, not the company's size.

Input comes from: your own description, Find niche (1), Niche distributions (2), Niche hierarchy (3), Domain lookup (6) for look-alikes. Pass the result to: Project card (5), Reveal (7), Audience (8), Traffic channels (9), Search demand (10), or Projects again with the seen ids.

Typical chains

• Who already sells something like my idea? Projects with the description, then Project card on the closest.
• How do small growing players of a niche get users? Find niche, Projects with the niche id, scale and growth filters, then Traffic channels for each.
• Look-alikes of a known site, but small: Domain lookup, then Projects with its project id and a scale filter.
• Name the leaders: Projects with the niche id sorted by index, then Reveal on the ones you need.

About the Megido component set

Megido is a curated corpus of websites where revenue has been observed: their visitors were observed paying for their products. This listing is one of ten single-step components. Each does one thing; chain them by ids to answer bigger questions. All components run on one Megido account, so an id returned by one component is valid in every other.

The set:

1. Find niche: a description of a market -> up to 5 candidate niches with ids.
2. Niche distributions: a niche id -> size and how its sites spread over quality, scale, growth, countries and site type.
3. Niche hierarchy: a niche id -> its parent, sub-niches and neighbouring niches with ids.
4. Projects: a description, a niche id or a look-alike project id -> up to 10 anonymous sites with ids.
5. Project card: a project id -> description, quality index by axis, niches.
6. Domain lookup: a domain -> whether it is in the corpus, its project id, other domains and payment service.
7. Reveal: a project id -> its domain, other domains and payment service.
8. Audience: a project id -> traffic and engagement in bands.
9. Traffic channels: a project id -> the three leading channels and social platforms, in bands.
10. Search demand: a project id -> branded and non-branded share of search traffic, in bands.

Every result ends with a JSON block ("schema": "megido.component/1") whose "data" is the corpus answer as it came and whose "next" holds ready inputs for the following components. You may send your input as plain words or as JSON ("schema": "megido.input/1").

Anonymous mode. Sites stay anonymous unless you call Reveal or Domain lookup. Profile figures (traffic, channels, search) come as bands, never as exact values, and a reveal in one task does not carry to another: Audience, Traffic channels and Search demand always answer in bands, even for a site you have revealed.

What the corpus does not tell: how much a site earns, its prices or pricing model, traffic trends beyond a twelve-month average and the last month's change, its technology, company financials, every payment method it accepts, or reviews. Figures are estimates, not the site owner's analytics.

The result is for your own use: do not resell it or pass the data on.