Changelog

What we shipped

A timeline of features, improvements, and integrations across the Converra platform.

February 2026

featureFeb 19

Custom Evaluation Criteria

Define business-specific metrics beyond the built-in evaluation suite. Measure what matters most for your agent's domain.

featureFeb 19

LLM Benchmark Comparisons

Compare model performance side-by-side. Run the same scenarios across different LLMs to find the best fit for your agent.

improvementFeb 19

Conversation Insights Redesign

Redesigned conversation insights with above-the-fold metrics, prompt links, and consolidated qualitative sections.

featureFeb 17

Fix-Targeted Optimizations

Optimizations now target the specific agent step responsible for diagnosed failures, instead of optimizing blindly.

featureFeb 17

Agent Failure Patterns

See recurring failure types across all your agents at a glance. Spot systemic issues before they become customer-facing problems.

featureFeb 16

Platform Launch

Converra opens for early access. Autonomous agent optimization with simulation testing, real-time performance tracking, and continuous prompt improvement.

featureFeb 14

Step-Level Agent Failure Diagnosis

Pinpoints which step in a multi-agent conversation caused a failure. See the execution flow, identify the responsible agent, and get actionable fix recommendations.

featureFeb 4

Prompt Structure Optimization

The optimizer now detects and resolves contradictions, redundancy, and formatting issues in your agent's instructions — not just metric-driven changes.

January 2026

featureJan 20

Template Variables & Sibling Deployment

Extract variables from agent templates and deploy optimized variants across sibling agents that share the same structure.

featureJan 15

MCP Server for AI-Native Integration

Converra is now accessible as an MCP server — manage agents, run simulations, and trigger optimizations from any MCP-compatible client.

featureJan 12

Template Segment Metrics

Break down agent performance by segment. See which parts of your agent's instructions contribute most to success or failure.

improvementJan 10

Protected Zones in Variant Generation

Mark sections of your agent's instructions as protected so the optimizer preserves them during variant generation.

December 2025

featureDec 20

Head-to-Head Winner Selection

Variant selection now uses persona-level head-to-head comparisons as the single source of truth, eliminating false positives from aggregated scores.

integrationDec 15

LangSmith Integration

Import production conversations directly from LangSmith. Connect your existing tracing pipeline to Converra without code changes.

featureDec 10

Multi-Agent Discovery

Automatically detect multi-agent architectures from ingested conversations. See which agents participate and how they hand off.

featureDec 1

Bulk Conversation Management

Archive and delete conversations in bulk. Filter, select, and clean up your conversation data at scale.