ToolsConnector
PromptWatch
Track prompts, visibility and competitor comparisons in AI answers, from Claude or ChatGPT, through Tulina's own MCP server, not PromptWatch's own hosted one.
Official site: promptwatch.com
What it can do
2 read/1 write
- 01Write
Track a set of prompts in a monitor across ChatGPT, Claude and Gemini
- 02Read
Read visibility over time, and compare against competitors on a heatmap
- 03Read
Read the answers themselves, their sentiment and the sources they cite
The citations are the half that can be acted on. A model's answer names where it got the claim, which turns "we are invisible in AI answers" from a ranking complaint into a specific list of pages that do not say what someone would need to read. Visibility moves when those sources move.
How do you connect PromptWatch to Claude and ChatGPT?
Through Tulina's own MCP server, not PromptWatch's own hosted one. Track a set of prompts across ChatGPT, Claude and Gemini, read visibility over time and compare against competitors on a heatmap, or read the answers themselves — their sentiment and the sources they cite — from the same chat as Claude or ChatGPT.
Why through Tulina
The connection was never the hard part.
Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.
The keys stay in one place
YouTeamOrganisation
Connect PromptWatch once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
fields droppedmasked or hashedpseudonymised
Roles decide who can reach PromptWatch at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
whatwhowhen
Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.
The run starts knowing your company
namingkey accountsdecisions
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against PromptWatch returns something usable instead of something generic.
Processes that run on PromptWatch
None published yet.