All demosSales Intake

Sales Intake

Turn inbound messages into a sales queue with stated facts, transparent fit criteria and a destination team.

Powered by/yes-no/classify/extract

Run the examples for free. Use your API key for your own inputs. Get a free key

Performance & cost

This page session · since page load

Ready to run
Typical delivery time
Live input tokens
0
Estimated inference cost · USD
$0.00
How these numbers work · 0 successful requests
Live model compute

Average per measured successful live request.

Successful requests
0

Run an example for free to see its measurements.

Delivery time is the median browser time for successful requests, including queue, network, and retries. Cached delivery speed is not inference speed. Model compute can exceed browser time when one request processes many inputs.

Tokens come from response headers. Inference costs use $0.04 per million input tokens, before plan credits. The estimate includes live and recorded tokens at the same rate; cached examples are not charged again. Missing usage is unavailable or a partial total (≥). Demo resets keep these totals; reload to start a new session.

Try it

Run the stock inbox free and adjust fit weights. Use your key for your own messages or criteria.

Build with the SDKTypeScript · Python · dm1

Use these API building blocks in your own app. Each sample is one request from this demo’s supplied inputs. Your code owns the surrounding workflow, validation and actions.

Copied samples call the live API with MS_API_KEY and use your quota. Keep the key on your server. The free demo cache is only for this site.

Install · set your key
npm install @cloudraker/milliseconds
export MS_API_KEY="your-api-key"
example.ts
import { DecisionMachine } from "@cloudraker/milliseconds";

// Run on your server; reads MS_API_KEY from the environment.
const dm = new DecisionMachine();

const { result, usage } = await dm.yesNo(
  [
    "Hi, I'm Maya Chen at Northstar Foods. Email: maya@northstar.example. We need to automate invoice processing across our warehouses. Can we book a software demo? We want to start next month. Our budget is $12,000 per year.",
    "I'm Oliver from Cedar Studio, oliver@cedar.example. We are evaluating software to process client documents automatically. Could you share pricing? No rollout date has been set and our budget is not decided.",
    "Hi, I'm Priya at Fieldwork, priya@fieldwork.example. We already use your product. Our team cannot log in after the latest update. Please help restore access today.",
    "I'm Leo Martinez, leo@candidate.example. Are you hiring frontend engineers? I'd love to apply for an open role. My resume is available on request.",
    "I'm Drew from Pipeline Partners. We sell outsourced appointment setting. Our package starts at $900 per month. Can we pitch our service to your sales director?",
    "I'm Sam at Brightside Books, sam@brightside.example. We need a social media scheduling tool. Can we see a demo of your software? We plan to start next year. Budget: $2,000 annually."
  ],
  [
    "The sender wants to purchase or evaluate software for their organization.",
    "The sender asks for help with a product they already use.",
    "The sender is applying for a job or asking about employment.",
    "The sender is offering to sell their services to the recipient."
  ]
).withUsage();

console.log(result);
console.log({ inputTokens: usage.inputTokens, modelMs: usage.inferenceMs });

From an inbox to the next conversation

The model checks four intent signals, extracts stated facts, and evaluates three criteria. Code routes each message to a team and computes a weighted fit score from the known criteria. Weights reorder the queue locally; new criteria need a fresh model run.

Drafts, ready for a person

These fictional messages demonstrate intake, not enrichment. Exact wording can be highlighted in the source, but a match does not prove the model assigned the right meaning or person. Unknown information stays unknown. Routes and fit judgments can be wrong; nothing is sent to a CRM and no email is sent.