The right story now, the next story after.
Readers search for events, people and topics that changed yesterday. AACSearch balances relevance with freshness, answers “what happened with…” from your archive, and recommends the next read.
Queries plain keyword search gets wrong
выборы итогиfreshness mattersчто известно о …summary questionинтервью Ивановperson + formatкурс доллара прогнозrecurring topicWhere search loses customers today
Old stories on top
A detailed 2019 article outranks this morning's update.
One article per visit
Readers leave after the article they came for.
Archive without context
Readers want the story so far, not a list of 40 links.
How AACSearch solves it, layer by layer
Each card names the capability behind it. Items marked “in development” are designed and scheduled, not live yet.
Finds the right item from the first letters — typos, synonyms, filters, meaning.
Widens the basket: similar, frequently together, personal.
Next read
Related and trending articles, diversified so the row isn't five versions of the same story.
Answers questions a filter can't, citing your own catalogue and docs.
The story so far
Cited summaries from the archive for “what is known about …” questions.
Learns how items, queries and topics connect — and leads the visitor to the goal.
Entities and storylines
Will link people, organisations and events across articles into storylines readers can follow.
One visitor, from first query to goal
What the visitor does on the left, what AACSearch does on the right.
- 1
Arrive
Searches for a breaking topic.
Today's updates rank above older background pieces.
Instant search - 2
Catch up
Asks what is known so far.
A short cited summary from the archive.
AI answers with citations - 3
Stay
Finishes the article.
Recommends the next related read.
Recommendations
Your first two weeks
A typical rollout for this industry. Most teams are live on day one and spend the rest of the time measuring and tuning.
Day 1
Import the archive via RSS, sitemap or WordPress.
Day 2
Boost by publication date for news queries.
Week 1
Add related-article rows under each story.
Week 2
Measure pages per session.
What to measure
The numbers to judge a rollout by. Compare them with an A/B split or a before/after window on the same traffic.
- Pages per session
- The effect of recommendations.
- Search exit rate
- Searches that end the visit.
- Subscriber conversion from search
- For paywalled publishers.
Connects to
- Sitemap crawl
- RSS / JSON
- WordPress
- REST API
Capabilities used
Coming next
Search for Media & publishing, live this week
Connect a feed or a site, embed one script, and measure the difference on your own traffic.