Drafter AI | Docs
ProductChangelogStatus
  • Getting Started
  • Build
    • Workflow Basics
      • Workflow Builder Overview
      • Builder: Input
      • Builder: Action
      • Builder: Filter
    • Create workflow
      • Launch workflow
      • Design output
      • Export output results
    • Align Pricing Model
  • Launch
    • Apply your brand
    • Connect a custom domain
    • Invite users
  • Scale
    • Process inputs in batches
    • Organize internal knowledge base
    • Template GPT3 prompts
    • Integrate Drafter AI to other apps with Make.com
    • Get started with developer API
  • Maintain
    • Restore output results
    • Export/Import workflows
    • Debug workflows
  • Building blocks
    • Inputs
      • Manual / Form
    • Actions
      • Text Generation (GPT)
      • Web Data Extraction
      • Sentiment Recognition
      • Key Phrases Extraction
      • Classification
      • Entity Extraction
      • Public Search
      • Internal Search
      • Translation
      • PDF Recognition
      • Regular Expression
      • Template
      • Twitter Search Data
      • Twitter Profile Data
      • Youtube Captions Extraction (soon)
      • Speech Recognition (Soon)
      • Speech Generation (Soon)
      • Image Generation (Soon)
      • Video Generation (Soon)
    • Flow Controls
      • Filter
      • Aggregate
      • Split
  • Direct Integrations
    • Make.com *
    • Google Sheets
    • Slack (soon)
    • Zapier (soon)
Powered by GitBook
On this page
  1. Maintain

Debug workflows

How to find an issue in the workflow.

PreviousExport/Import workflowsNextInputs

Last updated 2 years ago

When workflow delivers poor results, you need to figure out, what happened.

Poor results may happen due to 4 cases:

  1. Poor input data

  2. Poor data from public sources

  3. Poorly formatted prompts

  4. Poor workflow design

Every case has its own solution, but you need to find a reason first.

Debug lets you do that.

How to use Debug in Drafter AI:

Every workflow block has a "Debug" view after you tried to execute the workflow.

By clicking it you get access to a JSON view of all the inputs and outputs that were processed in the specific AI block during the last workflow run.

It lets you understand, at what point something went wrong, and make relevant changes.

Flow controls and inputs don't have a "Debug" view.

See, how to use it: