Home / Articles / An analyst's blueprint for RiskMandate / Versions / v1.2.0
An analyst's blueprint for RiskMandate: what changed in v1.2.0
From v1.1.0 (2026-10-21, 78bb7903d) to v1.2.0 (2026-10-21, d9d4562f2), paragraph by paragraph.
0 paragraphs added, 0 removed, 5 changed in place, 76 unchanged. About 94 words added and 0 removed. Insertions are marked like this, deletions like this; unchanged runs are folded to one line; figures appear as their file names.
12 unchanged paragraphs, under In short {#in-short}, The note {#note}
My business partner is at the WestCap CISO Summit in New York this week, and one of our power users, an analyst,users sent us a note from it: what RiskMandate should borrow from the companies whose logos were on the backdrop. To be clear about where it came from: the analysis was written in a ChatGPT session, an AI-assisted analysis rather than independent market research. I later gave this answer back to that session, and its review, which corrects some of what is here, is in approved business mandates. In short, itthe note says:
36 unchanged paragraphs, under Where we agree {#agree}, Who is already there {#landscape}, Their architecture, our pieces {#map}…
First, it puts us in line. As we argued in the key is not the risk, a proxy in the middle isadds a singlecomponent pointthat ofevery failure,call depends on, unless it is deployed redundantly, and it usually lacks the context to judge a request that looks valid; the state lives in the application. Second, the space is full: Drata, Sondera, AWS and the gateway makers all intercept tool calls already, and the customers we want already run some of them. Third, it is not what we are best at. As abp.sgit.ai puts it, a behaviour policy is "not a guardrail. It is what guardrails are compiled from."
2 unchanged paragraphs
• The same rules, compiled for the enforcement points customers already run. We have alreadyshown compiledit ouron a small scale: five rules towritten Cedarfor andan testedearlier them,article, evaluated in Cedar, the language Sondera and AWS evaluate.use, against fourteen requests. That is a demonstration, not yet a general compiler. Kept by a gateway outside the agent's reach, the same rule becomes a boundary.
20 unchanged paragraphs, under Where to start {#start}, More players is good news {#players}, Who plays open source {#open}…
• The note is theAI-assisted. analyst's.**Written Paraphrased,in nota quoted;ChatGPT session and shared by a power user; paraphrased, and the reading of it is mine.
6 unchanged paragraphs, under Where this comes from {#sources}
An analyst'sA note to us from the WestCap CISO Summit, 21 October 2026, written in a ChatGPT session and shared by one of our power users, paraphrased. Drata's announcement of 4 August 2026; Endor Labs' agent governance; Socket's MCP server and hook documentation; Bedrock Data's announcement of March 2026; Sondera's documentation; and the pages of AWS, Ping Identity, Docker, Bishop Fox, Optiv, Kroll and Sygnia, and the public repositories of agentgateway, Docker, Sondera, Cedar, Socket and Endor Labs, all read the same day. Related: a briefing for the WestCap CISO Summit, the RiskMandate roadmap, the key is not the risk, commander's intent is a behaviour policy, Cedar and the policy vault, our first customers. Written up and checked by this site's agent, newsroom.writer; the editorial responsibility is mine.