workthin
workthin
PricingBlogChangelogOverviewQuick StartConcepts

Chatbot IntegrationIncident ResponseToken Optimization

Docs for LLMs

llms.txtllms-full.txt
Guides

The Problem

Without workthin, every AI-assisted resolution requires full context:

ApproachTokens per queryMonthly cost (10K queries)
Full context (no workthin)3,000-10,000$150-$500
workthin summary~100$5
workthin standard~500$25

Summary Strategy for Chatbots

For customer-facing chatbots, use summary by default:

const params = new URLSearchParams({
  q: customerMessage,
  detail: 'summary', // ~100 tokens
})

const res = await fetch(
  `https://workthin.app/api/v1/search?${params}`,
  {
    headers: {
      'Authorization': 'Bearer ' + process.env.WORKTHIN_API_KEY,
    },
  }
)

summary returns only title and a body summary — enough for most auto-resolutions.

If the customer needs more detail, escalate to standard:

const detailed = await fetch(
  `https://workthin.app/api/v1/knowledge/${knowledgeId}?detail=standard`,
  {
    headers: {
      'Authorization': 'Bearer ' + process.env.WORKTHIN_API_KEY,
    },
  }
)

Cost Calculation

Without workthinWith workthin (summary)
Queries/month10,00010,000
Tokens/query~5,000~100
Total tokens50M1M
Cost (GPT-4 pricing)~$500/mo~$10/mo
Annual savings—$5,880

For organizations with 100K+ queries/month, annual savings exceed $48,000.

Best Practices

  1. Default to summary for automated integrations
  2. Use standard for interactive CLI and dashboard workflows
  3. Reserve full for incident postmortems and deep analysis
  4. Cache summary responses — they rarely change and are small enough to store

Incident Response

Use workthin in your postmortem workflow with thought chaining.

Security Overview

How workthin protects your knowledge and data.

On this page

The ProblemSummary Strategy for ChatbotsCost CalculationBest Practices