A verdict per option
Fits, fails or cannot tell, for every requirement, with the value and where it came from.
For AI agents
A procurement agent that checks the spec, not the brochure.
Give the agent the spec and the candidate suppliers or parts. Pulse returns, for each one, which requirements its data meets, which it fails, and which it leaves blank, so the shortlist is defensible and the follow-up questions write themselves.
Where you are
A missing rating is not a pass.
Supplier data is uneven: one datasheet states the IP rating, another omits it. An agent that treats a blank as a yes puts the wrong part on a purchase order.
A blank field is a question for the supplier, not an answer.
What happens
How does it work?
One call, from MCP or HTTP. Nothing to train, nothing stored.
- Ask01
State what is needed
As requirements such as "voltage = 24V", or in plain words; a budget in the words becomes a price requirement.
- Send02
Pass the options
Up to 50 at a time, with whatever fields and text you have. A stated field always wins over text read off a page.
- Answer03
Answer from the verdicts
Each option comes back fits, fails or cannot tell, with the attributes that are missing. The agent says what the evidence shows, and only that.
What you get
What the agent gets
"The evidence does not say"
A first-class answer instead of a guess, with the missing attributes named.
A to-do for the owner
Every unknown is exactly what the option's owner should publish next.
MCP or HTTP
The open-source MCP server for agents, or one HTTP call from your own code.
A worked example
Spec IP67, 24V, delivery within 14 days: Acme fits, Borealis fails on IP rating, Corvid fails on lead time and leaves its IP rating unstated.
What you get
Before and after
Without Pulse
- Treats missing ratings as acceptable
- Shortlists from the most confident text
- No record of why a supplier was chosen
With Pulse
- Fails or flags every unmet requirement
- Names the fields to request from each supplier
- Every verdict shows its source
Before you commit
What it will and will not do
What this does
- Give each option a verdict per requirement, grounded in its own evidence
- Name what is missing instead of guessing it
- Work in any domain whose options carry structured attributes
- Answer the same input the same way every time
What it does not do
- State an attribute the evidence never stated
- Read facts out of free text outside laptops yet; send the fields instead
- Make decisions about people, such as hiring or lending
- Promise a business result. Nothing has been measured on your data
Questions
The ones that decide it.
- Does it work with our own supplier fields?
- Yes. Send any attribute names and values; numbers compare as numbers and text compares without case.
- Which agents can use it?
- Claude Code, Claude Desktop, Cursor and Codex through the open-source MCP server, which runs on your machine, and any agent or program that can make an HTTP call. ChatGPT's web app needs a remote MCP server, which is planned.
- Is it a model?
- No. It applies rules to the evidence each option states, so the same input always gives the same verdict, and every verdict shows its source.
Add it to your agent.
Install the MCP server with one line, or call the API from your code. The open-source repository has runnable examples.
Opensource
An API key comes from the Pulse dashboard.