Web research

Web research uses OpenAI to search public sources. One research can cover several competitors, markets, or custom topics, each with its own questions. When a question names an App Store app, Zentrik also reads its rating and recent reviews directly; if several apps match, it asks which one. No provider credentials are needed.

The Competitors page puts your product beside up to four competitors and asks each the same questions: what is live, how they sell, who they target and what customers say. It reads public web pages and the Signals you link to each competitor; your product is read only from its description and its linked Signals. It does not read app store reviews; Public feedback research reads them from the US App Store. Sources can be in any language; answers are written in English.

1. Open Research → Competitors.
2. In the Competitors menu above the table, tick up to four competitors. Add one by name or website; the menu also suggests companies your saved research already covers. Your team shares this list for the product.
3. In the questions menu, choose what to ask. You can add one question of your own.
4. Choose Map landscape, check the competitors, questions and sources, then Start mapping. Mapping uses AI credits, and each column fills in as it finishes.
5. To keep it current, an owner or admin chooses Track weekly. It adds the map's sources to Discovery and maps the same questions every week.

Each answer is one short line with a mark for its strongest evidence:

• First-hand: people describing their own use, such as calls, support tickets, feedback or reviews saved as Signals.
• Reported: independent reporting or research reports.
• Company claim: only what the company says about itself.
• Stated intent: your product's description of what it offers.

Select an answer to read it in full with its sources. Select a row, such as How they sell, to line up its key facts across competitors, like entry price or a trial; your own question lines up its facts too.

Each new map is compared with the one before: a changed answer carries a bar, and changed in the toolbar fades the rest. No alert is sent when something changes, so open the page to see what moved.

1. In Research, choose New research: Market, Public feedback, and Track changes take subjects; Custom research takes a question. Competition opens the Competitors page.
2. Review the plan: the questions, source scope, and research window. If several App Store apps match, choose the one you mean; the plan shows sample reviews from it. Choose Refine to change anything or remove an app.
3. Choose Start research. Results stay in the research until you add them to Discovery.

Under Research options, choose Establish a baseline to include relevant older and undated documents, or Recent developments for a dated window of 1–90 days.

People with workspace edit access can run research. Owners and admins manage saved research and its update frequency. The questions, scope and selected source excerpts are sent to OpenAI for answers. Saved Signal text is redacted for personal information before synthesis.

Find saved research by topic, question, or product from the research home. In a report, Answers lists every question under its subject with the answer's headline. The selected answer appears in full beside the list, with the reviews and pages it cites. On a phone it opens over the list. The line above the list says how many answers changed since the run it is compared with, and how many have no answer yet. Select either to show only those.

Sources groups what the run read, such as App Store reviews or web pages. Open a group to search and filter every saved item. If an answer cannot be prepared, the saved sources remain available.

Saved Signals keep their original type. Citations show the source revision and the excerpt captured for that run. Later edits do not rewrite old results. Unknown dates and shortened excerpts are marked.

The run's date in the report header opens every run; choose one to read it, or Latest to return. A later run of the same plan is compared with the run before it, and a changed answer says what changed in its line and beside it. A changed plan starts a new comparison.

When subjects share questions, Compare places their answers side by side. From the research home, Compare research brings together any saved research with shared questions, without starting new research.

To correct an answer, choose Refine beside it, then Review revised plan and Run revised research. Plan shows what the research reads, every subject with its questions, and how often it updates. To change the whole plan, choose Edit plan there or from the report's More research actions menu.

Each run reads the US App Store rating of every confirmed app, including stars left without a written review. Store ratings, at the top of the answers list, sets the all-time rating beside the average of the ratings that arrived since the last run. The average appears once enough new ratings arrive to state it within a tenth of a star. To measure a longer period, such as since a release, choose an earlier run beside Store ratings.

When a run reads at least five new reviews of an app, What reviewers raise groups them into problems, requests, and what reviewers value, with how many reviews raise each and how that changed since the last run. Select one to read exactly those reviews. Reviews are the most recent ones from the US storefront: a sample, not every customer.

1. Choose Add to Discovery, pick the product the sources become evidence for, and add them. Each source becomes a Signal: a web page keeps its link, dates, and an AI summary; a review keeps its author’s words, rating, date, and link. Company announcements stay the company’s claims.
2. After the addition, the same button reads In Discovery and shows what was added. Choose Only when I ask, Weekly, or Daily there, or later under Plan. Automatic research starts only after you save a frequency, and each update uses your workspace’s AI allowance.

Later runs look for new sources, with a three-day overlap. Pages and reviews already added are skipped; edits to a page already read are not detected. Review and add a revised plan’s sources before it replaces an existing schedule.

Choose Pause updates to stop automatic runs. Pause before archiving; archiving keeps the run history and the Signals already added. Research frequency is separate from Brief emails.

You can also read and run research from a connected MCP agent or the Research API.

Use Track changes for requirements, vendor deprecations, or platform changes that may need a product response. One source can warrant review; repeated customer requests are not required.

1. Choose Track changes in new research, or Track regulatory or technical changes from Web research in Integrations. Choose a category and subject. Under Sources and scope, you can restrict searches to official domains.
2. Review the plan, start research, and check the original sources. Dates, affected scope, and possible impact are AI interpretations for you to confirm.
3. Choose Add to Discovery and select a product. This saves the evidence and creates product responses under Responses in this research and in Current Brief.
4. Choose Assess impact. Record whether it applies, the next action and review date, and optionally assign the response to yourself. Under Deadline and related work, confirm dates and optionally link external work. Save the assessment.
5. For an applicable change, choose Use evidence to create or attach an Idea or Opportunity, or create a Task. The source stays linked; the work follows Zentrik’s existing planning and delivery flows.

For example, an API may retire on November 1. Accept that deadline after checking which versions it affects, target October 20 for migration, and set October 12 to review the plan.

Review needed flags a first assessment or a change to the requirement, scope, status, or date conditions. Compare the amendment with the last accepted assessment beside it. Title and impact rewrites do not request review. Action due follows dates your team saved; a new assessment does not set urgency. Mark Response verified after checking completion, or Does not apply with a reason. Choose Assess another product to reuse the source. Each product keeps its own decision, dates, owner, and verification.

When that Evidence supports an Idea or Opportunity for the same product, Direction shows its confirmed dates. Dates within 30 days take precedence in Analysis without increasing customer demand scores. Pending amendments keep the last accepted constraint visible, marked for review. A previously verified response needs reassessment before it gains deadline priority. Accepting a removed deadline or withdrawal updates Direction without another analysis. Saved priorities change only when you accept or edit them. The existing Idea Send to Jira preview includes accepted constraints, dates, and source links. Completing work does not verify the response.

If an update is published on a different page, add it through Research, then choose Use a newer source on the existing response. Link the notice from the same publisher and review the amendment for each product. Existing work and accepted decisions remain linked.

Responses remain in Current Brief after the research window moves on. To repeat the search, save an update frequency. Updates search public documents; they do not guarantee coverage, detect every edit to an existing page, or send deadline reminders.

Sources per section sets how many qualifying sources a section keeps. A first run makes one search round per section and keeps three by default; scheduled runs make up to three rounds to reach the target. Rejected and duplicate sources do not count, and a target is not a promise that matching evidence exists.

A run reads up to four confirmed App Store apps: 40 recent reviews in total, at most 25 per app, from the US storefront. A section limited to the App Store skips web search.

New public sources in recent research must fall inside the research window. Selected saved Signals keep their original dates, even outside that window. A review keeps its own date, and a month-only date qualifies when the whole month is inside the window. Recent research skips undated pages; a baseline can keep relevant ones, marked as undated.

Coverage notes name topics that stayed unverified, which is different from a topic researched with no new findings. When a section finds no accepted sources, or falls short with limited coverage, the next run keeps the same window. Search never guarantees complete coverage of a market.