Skip to main content
OpenBat’s analysis pipeline runs AI-powered analysis on every conversation message. This page describes how the pipeline works end-to-end.

Pipeline stages

Ingestion → Translation (optional) → Analysis → Storage → Surfacing

1. Ingestion

Conversations arrive via the SDK or REST API, authenticated by API key. Each conversation contains messages, metadata, and session context.

2. Translation (optional)

If auto-translation is enabled in Analysis Config, messages in non-primary languages are translated before analysis. The original text is preserved alongside the translation.

3. Analysis

Each message is processed through four configurable AI prompts:
PromptOutput
SentimentNumeric score and label per message
IntentClassified user intent (e.g., “asking about pricing”)
TopicsExtracted topics (e.g., “billing”, “integration”)
FlagsDetected user signals (churn risk, buying signal, etc.)
In addition, assistant messages are analyzed for behavior classifications:
  • Helpful, Yes-Man, Dodging, Over-Apologizing, Hallucinating, Redirecting, Verbose, Robotic
And conversations are assessed for resolution status:
  • Fully Resolved, Partially Resolved, Unresolved

4. Storage

Analysis results are stored as annotations linked to individual messages and aggregated at the conversation level. The Analyzed Today KPI on the dashboard reflects the daily throughput of this stage.

5. Surfacing

Annotations surface across the platform:
WhereWhat appears
Dashboard KPIsAverage sentiment, analyzed count
User InsightsSentiment trends, top frustrations, revenue signals
Assistant PerformanceBehavior alerts, resolution outcomes, quality flags
Conversation detailPer-message clickable annotations
Conversations tableSentiment column with color-coded badges
Workflow triggersConditions evaluated against analysis results

Configurable prompts

Each chatbot has its own set of analysis prompts, editable from Analysis Config > Prompts tab. This means different chatbots can be tuned for different domains — a customer support bot and a sales bot can have different sentiment calibrations. Unmodified prompts use system defaults. See Customize analysis prompts for a guide on editing them.

Semantic search infrastructure

The Deep Search feature relies on a separate vector embedding pipeline:
  1. Conversation content is embedded into vector representations
  2. Vectors are stored in a vector database
  3. Search queries are embedded and compared using cosine similarity
  4. Results are ranked by semantic relevance
This runs independently from the annotation pipeline and powers meaning-based search.

Workflow trigger evaluation

After analysis completes, OpenBat evaluates active workflows against the new annotations. If a workflow’s conditions match (e.g., sentiment below threshold, hallucination detected), the workflow triggers and executes its configured action (webhook delivery). Workflow execution results are logged as runs with status tracking (Pending, Triggered, Success, Failed, Skipped).

Next steps

Analysis configuration

Configure the analysis pipeline for your chatbot.

Data model

Entity relationships and data structures.