# See why your agent decided, not just what it did.

> Product page for RML (Reasoning Markup Language): AISquare records every agent run as claims, evidence with confidence and assumptions, so engineers, reviewers, auditors and other agents can see why an agent decided.

- **URL:** https://aisquare.studio/product/reasoning-graph
- **Audience:** Engineers, reviewers, risk, compliance and audit teams who need to explain AI agent decisions
- **Topics:** RML, Reasoning Markup Language, reasoning markup, reasoning graph, agent explainability, explainable AI, claims, evidence, assumptions, extraction confidence, unbacked claims, hallucination risk, agent observability, OpenTelemetry, prompt injection detection, Trust & Safety Institute, learnings MCP server

## Reasoning Markup Language (RML)

AISquare records every run in RML: the claims the agent made, the evidence behind each one, and the assumptions it filled in.

## The problem

A transcript tells you what was said. It doesn't tell you why.

- The why disappears: The evidence and shortcuts behind an answer are gone the moment it appears.

- Silent assumptions: Agents fill gaps you never see, until one of them is wrong in production.

- No answer for auditors: When someone asks why the agent did that, all you have is a wall of transcript.

## You can't trust an agent you don't understand.

Trust is earned in a loop. Understand why the agent decided, prevent the bad action next time, and fix what already happened. It starts with seeing the reasoning.

- Understand: See why it decided, in RML.

- Prevent: Stop a bad action before it runs.

- Fix: Correct a decision where it happened.

- Remember: Carry the fix to every run.

Here's what understanding looks like in practice.

## One language for how agents reason.

Every model explains itself differently. RML gives every agent one format for its reasoning, so other agents, reviewers, auditors and your own tools all read it the same way.

Any agent writes it: OpenAI agent, Claude agent, Gemini agent, LangChain, Agno, Your own agent.

RML record: Run header · agent, model, steps; Claims; Evidence, with confidence; Assumptions; Inference chain; Unbacked claims flagged.

Anyone can read it:

- Other agents: Reuse past reasoning as precedent.

- Reviewers: Read it in plain language.

- Auditors: Find it in the signed record.

- Your tools: Pull it over the API.

Built on OpenTelemetry, so it fits the tracing you already run.

We're working with the Trust & Safety Institute to publish RML as an open standard.

## The claim sounded right. Nothing backed it.

Agents state numbers with total confidence. Without the reasoning, you can't tell a real figure from a made-up one.

- 1 · The agent says it: “The Global Equity Index Fund has returned an average of 10.5% a year over the last ten years.” Sounds right. Is it?

- 2 · AISquare checks what backs it: Fund factsheet · retrieved, covers 2019 to 2024 only. Performance database · never queried. No source in this run says 10.5%. Unbacked claim.

- 3 · You make it a rule: Every return figure must cite a fund source. Every agent checks it from the next run on.

Illustrative example.

## Three mistakes traces don't show you.

Each one is pinned to the exact step that caused it, so you fix the cause, not the symptom.

- Unbacked claim: Quoted a 10.5% average return. No source retrieved in this run contains that figure. Pinned to · Step 6 · model call

- Skipped step: Never called the eligibility lookup. The instructions require it before any decision. The agent decided without it. Pinned to · Step 4 · tool call missing

- Error that spread: A wrong customer match in step 2 flowed into the decision. The lookup matched the wrong record, and every later step built on it. Pinned to · Step 2 · tool call

Illustrative example.

## Claims, evidence, assumptions.

Every RML record breaks a run into these parts, step by step.

- Claims: What the agent asserted and acted on.

- Evidence: What each claim rests on, each with a confidence score.

- Assumptions: The gaps the agent filled in for itself.

Extraction confidence: How faithfully the reasoning was captured. Low means read the raw trace, not the summary.

The reasoning goes into the signed record for every run.

## Everything you see on every run.

This is the run view your engineers and reviewers open. Here's what every part of it tells you.

- Every step, in order: Each LLM call, tool call and agent hand-off as it ran.

- Latency per step: See which step slowed the run down.

- Tool calls: What the agent called, with inputs and timing.

- Fixed before it shipped: Decisions your rules corrected, marked on the run.

- Cheaper model options: What the same run would cost on other models.

- Attacks caught: Attempts to override the agent, flagged with the pattern and severity.

- Reasoning, rules and the signed record: RML sits next to Policies and Attestations on every run.

- Per step or whole run: Read the reasoning step by step, or for the run.

- Analysis confidence: How faithfully the reasoning was captured.

- Claims, assumptions, evidence: Counted for every run, so risk is visible at a glance.

- Steps with no evidence: Risky steps are marked, so you know where to look.

- Unbacked claims: Claims with nothing behind them, flagged in red.

Observability: Full trace, Latency per step, Tokens and cost, Errors and status, Policy verdicts, Sensitive data screening, Search and filter runs, Prompt injection detection, Cost across providers.

Reasoning: Claims, Evidence with confidence, Assumptions, Inference chain, Unbacked claims and hallucination risk, Extraction confidence, Plain-English summary, Suggested fixes, Sent for review.

Every item is also available over the API.

## One run, read by an engineer or a reviewer.

Engineers follow the steps. Reviewers read what happened in plain English. Same run, same record.

- Every step, with latency and cost

- The policy check is its own step

- The same run in plain English

- Same run, same signed record

Both are reading the same RML record.

## Read the reasoning over the API.

Every run's RML record is one API call away. Prefer tools? The learnings MCP server wraps every read for Claude Code, Cursor and any MCP client.

## Questions about AI agent explainability and reasoning graphs.

- What is RML? RML, or reasoning markup, is how AISquare structures an agent's thinking on each run: the claims it made, the evidence each claim rests on with a confidence score, the assumptions it filled in, and the inference chain that connects them.

- How is RML different from OpenTelemetry? OpenTelemetry records what happened: the calls, timings and costs of a run. RML adds the reasoning on top: what the agent claimed, what backed each claim and what it assumed. AISquare's SDK is OpenTelemetry-native, so RML fits the tracing you already run.

- Is RML open? We're working with the Trust & Safety Institute to publish RML as an open standard, so any agent or tool can write and read it. Today, every RML record from your agents is yours to read and export over the API.

- Isn't this just the model's own reasoning? No. A model's reasoning is its own account of what it did. RML checks each claim against the evidence the agent actually retrieved and the steps it actually ran, so a confident claim with nothing behind it still gets flagged.

- How is a reasoning graph different from a knowledge graph? A knowledge graph stores what your organization knows. A reasoning graph records how an agent used that knowledge on one specific run: which claims it committed to, what evidence it weighed and what it assumed. They work together, and a knowledge lookup shows up as a step on the reasoning graph.

- How do you catch a claim with nothing behind it? Every claim is linked to the evidence the agent actually retrieved, with a confidence per item. A claim with weak or missing evidence stands out on the run, so a reviewer sees it and can turn it into a rule for every agent.

- How accurate is the flagging? Every analysis carries an extraction confidence, and a low score tells you to read the raw trace. Reviewers can accept or dismiss each finding, and those calls sharpen how each rule is graded over time.

- How are assumptions detected? Assumptions are facts the agent inferred rather than received, like a customer tier it resolved on its own. They carry a lower confidence and are marked separately, so you can challenge them.

- What is extraction confidence? It's how sure AISquare is that it captured the agent's reasoning faithfully. A low score is a prompt to read the raw trace rather than rely on the structured view.

- Does capturing reasoning slow my agent down? No. Reasoning is extracted asynchronously after a run lands, so the agent runs at its normal speed.

- Do our traces leave our environment? Traces go only to your own AISquare workspace, over TLS. PII, PHI and PCI are screened before anything is saved and can be masked. Talk to us if you have stricter residency needs.

- Can it catch a step the agent skipped? Yes. Because every run is recorded step by step, a required tool call that never happened shows up as a gap on the run, next to the decision that was made without it.

- Which frameworks and models does it work with? Any agent connected through the proxy or the SDK, including Anthropic, OpenAI, Azure OpenAI and Gemini models, Agno, LangChain, custom agents, and existing OpenTelemetry setups.

- Can I read the reasoning programmatically? Yes. List runs, fetch the graph and fetch the reasoning over the API, or use the learnings MCP server from Claude Code, Cursor or any MCP client.

## Start your journey with AISquare

Stop trusting outputs you cannot explain.

Connect one agent and see its reasoning, assumptions and all, in your own workspace.

## Links

- [Book a demo](https://calendly.com/d/dws4-msf-8jc/aisquare-gtm-team)
- [Read the docs](https://docs.aisquare.studio/docs/govern/understand/)
- [Read the API guide](https://docs.aisquare.studio/docs/govern/understand/#read-it-over-the-api)
- [See the Policy Engine](https://aisquare.studio/product/policy-gates)
- [See Audit](https://aisquare.studio/product/audit)
- [Trust & Safety Institute](https://aisquare.studio/tsi)

---

**Machine-readable AISquare**

- Site index for LLMs: https://aisquare.studio/llms.txt
- Agent instructions (when to use AISquare): https://aisquare.studio/agents.md
- OpenAPI specification: https://aisquare.studio/openapi.json
- MCP endpoint (Streamable HTTP, POST): https://aisquare.studio/mcp
- Sitemap: https://aisquare.studio/sitemap.xml
- Blog feed (RSS, full posts): https://aisquare.studio/blogs/rss.xml
- Any page on this site also serves markdown: append `.md` to its path (the homepage is `/index.md`) or send `Accept: text/markdown`.
