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.
Follow this change log by RSS
Free for your reader, newsletter or automation tool. One feed covers the whole index, and every category has its own.
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.
5 entries matching filters
Agent capability
Engine in LangSmith now watches CI on the pull requests it opens for detected issues. When checks fail on its own commits, it pushes a revision that reproduces and fixes the failing checks, up to three revisions or 90 minutes per chain.
Engine can now iterate on its own fixes until CI passes without a developer stepping in, shortening the path from a production issue to a mergeable pull request, with the revision and time caps setting how far it acts alone.
Workflow orchestration
LangSmith launched the public beta of smithtune, a CLI and coding agent skill that turns recorded agent trajectories into supervised fine tuning workflows. It prepares and persists training datasets, submits training jobs to Fireworks or Baseten, compares the resulting model with the base model through LangSmith evaluations, and can deploy the selected model. Users need a LangSmith account with agent traces and an API key for a supported training provider.
Teams can test whether their production examples support a specialized agent model without building separate data preparation, training, and evaluation pipelines. Recorded datasets and evaluation comparisons give reviewers a way to inspect gains and regressions before deployment.
Deployment / data residency
LangSmith SaaS now caps extended trace retention at 180 days. Existing settings above 180 days are reduced automatically for new traces; self hosted and bring your own cloud deployments are unaffected.
Teams that relied on longer retention for audit or evaluation history need to export traces or move to a self hosted deployment. This is a quiet change with compliance consequences.
Deployment / data residency
LangSmith launched Managed Deep Agents in public beta. This release allows developers to deploy Deep Agents to a managed LangSmith runtime that includes durable execution, memory, sandboxes, channels, and evaluations.
Engineering teams can now host and run long-running agents directly on LangSmith's managed infrastructure. This reduces the operational overhead required to build custom deployment environments for stateful agent execution.
Observability / auditability
LangChain launched native Python tracing integrations in LangSmith for Pipecat voice agents. The integration captures end-to-end voice pipeline telemetry, including conversation audio, speech-to-text and text-to-speech latency, voice activity detection events, interruptions, and tool calls.
Production observability is a critical hurdle for voice AI. This integration enables teams deploying Pipecat to monitor, debug, and evaluate their real-time agents using LangSmith, allowing them to share the same evaluation workflows used for text-based agents.
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 1648 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 Oct 21, 2026, covering Equal AI, Kognitos, Findem.
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. The same entries are published as a free RSS feed at agenticindex.io/feeds/changes.xml, with one feed per ranking category listed at agenticindex.io/use-this-data.
Last updated: Oct 21, 2026 · 1648 tracked changes across 550 vendors