Changelog
API and product changes for AISquare, with RSS and Markdown feeds.
Two streams of changes. The API changelog tags every entry Breaking or not (Stripe style). The product changelog is date headed (Anthropic style). Subscribe with the RSS feed, or read the whole changelog as Markdown.
Subscribe with the RSS feed or read the whole changelog as Markdown.
API changelog
Changes to the API surface. Every entry is tagged Breaking or not.
Publish the initial governed API reference
The first version of the API reference is live. It documents the governed call surface end to end, with every endpoint deep linkable.
This is the starting point for the API changelog. From here, each change is listed with a Breaking tag so you can tell at a glance whether it affects your integration.
Product changelog
What shipped for the product, newest first.
Collective Intelligence, repositioned as the layer
Collective Intelligence is no longer presented as a step in the journey. It is the reasoning-aware, auditable, governable layer with the memory and context of both agents and humans: traceability, policy enforcement, and Studios all write into it, and all of them are powered by it, on the reasoning graph at the base.
The journey diagram now renders it as a full-width band beneath the three working surfaces, and the Collective Intelligence, Prevent, Remember, and Studios pages describe the two-way flow.
AI + BI = CI, the equation behind Collective Intelligence
The docs now name the equation the platform runs on: artificial intelligence, plus the brain intelligence of the humans in the loop, compounds into Collective Intelligence. The Collective Intelligence page introduces it, and Studios, the Fix step, and the landing page tie back to it.
Compliance and audit reference
A new reference page maps the per-decision record to the frameworks auditors bring most often: the EU AI Act, ISO/IEC 42001, and the NIST AI RMF. It lists what every governed decision leaves behind and which obligation each artifact answers.
The reasoning-graph docs now also draw the line between a reasoning graph and a knowledge graph: one is a map of facts, the other is the record of how an agent used them on a specific run.
New documentation site, built for agents and people
The AISquare documentation site is live. It follows the product narrative: govern your agents, run the Trust Loop on every decision (Understand, Prevent, Fix, Remember), so Collective Intelligence compounds and your teams ship it as Studios.
The site is AI first. Every page is available as Markdown (append .md to any docs URL, or send an Accept: text/markdown header), there is a copy for LLM action on each page, and the full corpus is published at /llms.txt and /llms-full.txt for agents to ingest.
You can also bring the docs into your own agent over MCP, so an assistant can read and answer from them directly.