Agentic Index
Agentic AI Platform Change Log
Agentic Index tracks material changes across agentic AI platforms, including new agent capabilities, workflow orchestration updates, integrations, MCP/tool-calling changes, memory features, human approval controls, observability, deployment options, pricing, funding, and verification-status updates. This change log is the index that tracks changes to agentic AI platforms, updated weekly. If you are trying to keep up with changes to AI agent platforms without reading every vendor's release notes separately, this is the feed to read.
Public-source research. All entries are sourced from official vendor blogs, changelogs, documentation, or press materials. Support levels marked Needs Review or Publicly Claimed should be independently verified before relying on them for procurement decisions.
7 entries matching filters
MCP / tool calling / API
Langfuse introduced stable, ID-based public APIs for managing LLM-as-a-Judge and code evaluators. Users can now programmatically create, version, and manage both evaluators and their associated evaluation rules.
Engineering teams can integrate evaluator management directly into their deployment pipelines or infrastructure-as-code setups. This ensures evaluation logic remains version-controlled and synchronized across different environments.
Agent capability
Langfuse introduced and defaulted to background execution for in-app agents, including client and web support. This changes the default operational path for these agents to run asynchronously.
Developers can build more responsive applications by offloading agent execution to the background, preventing UI blocking during long-running LLM tasks.
Observability / auditability
Langfuse added the ability to perform bulk exports and imports of prompts.
Teams managing large libraries of prompts can now easily migrate, back up, or update their prompt configurations in bulk, streamlining prompt engineering workflows.
Observability / auditability
The V2 metrics API now exposes semantic roots, and evaluator metadata is propagated to generation spans.
This provides deeper analytical capabilities for observability, allowing teams to better track and evaluate the performance and semantic meaning of agent outputs.
Observability / auditability
Langfuse updated its observations table to default to a focused view of application entry points for projects using the latest Python and JS/TS SDKs. The new automatic root filter temporarily hides nested tool and retrieval calls to surface top-level requests first.
This change reduces noise when initially investigating agent logs and helps users quickly identify critical inputs and outputs. It streamlines the debugging process for nested applications by establishing a clear starting point for drill-down analysis.
Observability / auditability
Langfuse rebuilt its trace graph view on a deterministic renderer to include two layout modes: Aggregated and Expanded. The Aggregated mode groups repeated steps into single nodes with counters to show an overall shape, while the Expanded mode unrolls all loops into an execution-ordered directed acyclic graph.
This update makes auditing complex agent executions much easier. Evaluators and developers can quickly switch between a high-level structural overview and a granular step-by-step breakdown without losing their place on large traces.
Feature release
Langfuse shipped Monitors and Alerts (proactive alerting on metrics and thresholds) and the Langfuse Assistant (natural-language trace filtering, powered by AWS Bedrock with zero data retention) on June 19, followed by Multi-modal datasets on June 23.
Adds proactive production monitoring and alerting plus natural-language trace querying to the observability platform. For buyers evaluating LLM observability and eval tooling, these reduce reliance on manual dashboard checks.
Current rankings
These changes feed the index. See where each category stands: the best vendors of 2026, ranked by verified capability coverage.
Capability coverage
Every change above is graded against the same 14 capability axes. Each axis has its own page showing how much of the index documents it, which categories concentrate it, and the leading platform in each.
The AI agent directory for business · The full feature taxonomy · Pricing research
Common questions
How do I keep up with changes to AI agent platforms?
Read one maintained change log instead of tracking each vendor's release notes separately. The Agentic Index change log records 981 verified updates across agentic AI platforms, updated weekly, covering new agent capabilities, MCP and tool calling changes, memory, human approval controls, observability, deployment options, pricing and funding. Every entry names the vendor, the date, the change type and an impact level, and links to that vendor's profile.
How often is the agentic AI change log updated?
Weekly. The most recent update was Sep 4, 2026, covering LivePerson, Serval, ServiceNow.
How do I track changes for one specific AI agent vendor?
Filter the change log by vendor, or open that vendor's profile page, where the same verified entries appear alongside its capability coverage across the 14 point Agentic Index taxonomy.
Where can I find a single feed of agentic AI platform updates?
This page is that feed. Agentic Index reviews vendor blogs, changelogs, documentation and press materials every week and files what materially changed, so keeping up with changes to AI agent platforms is one page rather than several hundred. Entries are filterable by vendor, change type, impact level and verification status, and each one carries the evidence basis it was graded from.
Last updated: Sep 4, 2026 · 981 tracked changes across 372 vendors