Releasesby GlyphNovember 2026
The sitemap refresh process now automatically syncs monitored pages by adding new URLs and removing those no longer present in the sitemap. Users can track synchronization progress via a new pageSyncJobId.
Searchable Release notes and new features
London, United Kingdom · 17 releases · 5 this month
Also onAcquisitions·Funding(Funding rounds)·Paydays(Pay schedule)
Searchable releases
November 2026 digestNovember 2026
Searchable updated permissions so Workspace Members can edit competitors, alternative names, and source classification rules previously limited to workspace admins.
November 2026
The same branded and unbranded filters on every endpoint GET /projects/{projectId}/visibility/prompts ignored unbranded=true and returned branded prompts too, although the API reference listed the parameter. It now honors unbranded=true and branded=true like every other endpoint. branded=false still returns non-branded prompts only there, as before.
November 2026
Industry ranking's change compares whole windows, and can be null industry_ranking on get_visibility and GET /projects/{projectId}/visibility ( include=industry_ranking ) reports a change for each entity and a brandChange for you. They used to compare one day with an earlier day, and read 0 when either day had no answers.
November 2026
Change an existing project's default location A project's default location, the Knowledge Base's Location in the app, could only be set over the API when the project was created. The new set_default_location MCP tool and PUT /projects/{projectId}/default-location now change it on an existing project.
October 2026
Changes compare the window you asked for with the one before it The change fields on share of voice and sentiment now compare the requested window with the window of the same length just before it.
October 2026
Searchable updated its prompt location sync so that unresolved city lookups keep existing prompt locations rather than defaulting to country-wide tracking.
October 2026
The prompt sync API and MCP tool now track location states when editing prompts in bulk. States without cities are tracked individually, while ambiguous or unrecognized states are noted.
October 2026
Users can now filter competitor data by type, distinguishing between direct competitors and those identified via AI answers. This filter is available across multiple API endpoints for share of voice and sentiment analysis.
October 2026
MCP tool calls are now limited to 600 per minute per API key or OAuth connection. Requests exceeding this limit will return a rate_limited response with retry instructions.
October 2026
New API keys and MCP access tokens can now be created with optional write access. This allows keys to perform actions like updating prompts or brand profiles, while maintaining read-only defaults for security.
October 2026
Ask Searchable from Slack and Microsoft Teams Searchable's MCP server now accepts sign-ins from Slackbot and Microsoft Copilot Studio, and lets Microsoft 365 Copilot load its interactive cards. The new Slack and Teams guide covers Claude Tag, Slackbot, Copilot Studio and Microsoft 365 Copilot.
October 2026
See how AI answers describe your brand for one prompt GET /projects/{projectId}/visibility/prompts now returns sentimentScore in each prompt's metrics : how that prompt's answers describe your brand, from 0 to 100 (positive counts 100, neutral 50, negative 0).
October 2026
Mention counts that follow your window and filters GET /projects/{projectId}/competitors now returns mentionsInWindow beside mentions on every competitor row and on the brand block.
September 2026
Read whole AI answers, not the first 2,000 characters GET /projects/{projectId}/prompts/{promptId}/responses and the get_prompt_answers MCP tool used to cut every answer's text at 2,000 characters, which clipped about half of all ChatGPT answers and nearly every Copilot answer. text now carries the full answer.
August 2026
Follow each page from training crawl to assistant fetch The existing AI Traffic reports now expose the bot identity Searchable already resolves internally. Pass groupBy=botCategory or groupBy=botName on REST /traffic/overview , /traffic/bots , or /traffic/correlation , or use the same groupBy argument on the consolidated get_ai_traffic MCP tool.
July 2026
responseMentionRate is the mention metric to use. It is the percentage (0-100) of AI responses that mention your brand, and it means the same thing on every endpoint , added to both GET /visibility ( summary.responseMentionRate ) and GET /visibility/history (per data point).