docs: add Apify AI launch coverage#2633
Draft
marcel-rbro wants to merge 8 commits into
Draft
Conversation
Introduce Apify AI - the conversational AI interface inside Apify Console - and explain that Actors are ranked across Store search, the MCP server, and Apify AI by the same Actor quality score. Refs: #2625 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
|
❌ Preview build for this PR (commit |
Per Daniela: free users have a lower daily limit, all paid plans share the same higher limit. Do not state the exact value - it changes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Store search now uses a recommender system with per-user personalization, so Web Store and Console Store can return different results for the same query. Expand the publisher-facing search guidance in how_store_works.md, soften the "identical across surfaces" wording on the quality score, MCP, and Apify AI pages, and surface the web-vs-Console divergence on the Console Store page.
Drop "recommender system" wording (technology is not publicly acknowledged). Frame ranking around quality-score-like criteria with extra emphasis on popularity, with the explicit caveat that a higher score makes higher placement more likely but not guaranteed. Console search is the only personalization exception: same criteria, individual order.
Move the Store search ranking guidance to its own PR (#2653). This PR now covers only the Apify-AI-specific surface: the new Apify AI page and the Apify AI vs MCP comparison. Soften the MCP page's ranking line to avoid pre-empting the search PR's framing.
Quality score and search ranking are separate systems that evaluate similar parameters, so they correlate strongly without one driving the other. Reword the Apify AI ranking guidance to match. Add a short publisher note on disputing Apify-assigned categories.
marcel-rbro
added a commit
that referenced
this pull request
Jun 18, 2026
The categories dispute guidance is owned by the Apify AI launch wave and covered in PR #2633.
Drop the "separate systems that" preamble. Lead directly with the correlation: search ranking evaluates parameters similar to those in the quality score, so the two correlate strongly.
PMM feedback was scoped to the Search PR only.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds documentation for Apify AI (Console AI chat, launching early July 2026).
Closes #2625
The page documents the daily token limit framing: lower for free, higher and uniform across paid plans, exact value intentionally unstated since it may change. The MCP page also gains a short comparison section explaining when to use the MCP server vs Apify AI.
Store search ranking guidance is now scoped to a separate PR: #2653.
Open questions before un-drafting:
TODOinsources/platform/console/apify-ai.mdwith the Store search bar "Ask AI" screenshot once the feature is visible.