> ## Documentation Index > Fetch the complete documentation index at: https://docs.changeguard.ai/llms.txt > Use this file to discover all available pages before exploring further. # Engineering intelligence > What ChangeGuard AI adds to a judgment and an incident, how it is grounded in evidence, who gets it, and how to turn it on or off. Engineering intelligence is the part of ChangeGuard AI that reads like a senior engineer: it adds context to a pre-flight judgment, takes an owned position on an incident, shows the reasoning behind its confidence, and recalls what happened the last time something similar broke. It is **generally available** since the release of 7 November 2026. It never decides for you. A verdict stays SHIP, HOLD or BLOCK on the evidence; advice stays advice; execution still needs a [Permit](https://docs.changeguard.ai/govern/permit.md). ## The four capabilities | Capability | Where it appears | What it adds | Needs | | - | - | - | - | | [Engineering Advisor](https://docs.changeguard.ai/get-started/engineering-advisor.md) | Beside a pre-flight verdict, on the dashboard check and in CI | The one or two things to raise before shipping into this environment: an active incident in it, a bad recent change record on it. Silent when nothing is material. | Professional or Enterprise; live environment evidence | | [Engineering Opinion](https://docs.changeguard.ai/intelligence/engineering-opinion.md) | The Investigation context of an incident | The most likely cause, a confidence in words, the competing explanation, what it cannot tell yet, what would change its mind, and one next move: investigate, wait, act or escalate | Professional or Enterprise; a root-cause analysis on the incident | | [Engineering Reasoning](https://docs.changeguard.ai/intelligence/engineering-reasoning.md) | Inside the opinion | What raises and lowers the confidence, as at most four factors from real signals, and why not the obvious move | Opinion on | | [Engineering Experience](https://docs.changeguard.ai/intelligence/engineering-experience.md) | Inside the opinion, as "Seen before" | The outcomes of past fixes on the same target and strong similar past incidents in your workspace, only when they changed the decision | Opinion on; recorded outcomes in your workspace | The two collaboration capabilities released with them are documented under Investigate: the [incident workspace](https://docs.changeguard.ai/investigate/incident-workspace.md) and the [Code Graph](https://docs.changeguard.ai/investigate/code-graph.md). ## Grounded in evidence, explicit about uncertainty Every claim an opinion or an advisor note makes is bound to a record ChangeGuard AI holds: an incident, a change record, a root-cause analysis, an evidence line, a remediation outcome. A reason that cannot be attributed to evidence is dropped before you see it; an opinion with no attributable reason is rejected and not stored. Uncertainty is part of the output, not a footnote: * The Advisor says what it cannot see (`blindspots`) and stays silent below its materiality floors. * The Opinion carries a confidence between 5 and 95 percent, stated in words, with the open unknowns and the falsifier (what would change the call). * Reasoning factors are derived by the backend from the signals it has; they cannot weigh evidence the platform never saw. * Experience states similarity as similarity, never identity, and always with the backend's exact counts. Where there is no evidence to stand on, the capability stays quiet: an Advisor with no live environment evidence reports `no_environment_evidence`; an Opinion forms nothing without a root-cause analysis; Experience recalls nothing from a workspace without recorded outcomes. ## Who gets it, and how to control it Availability is decided per tenant and per request from three inputs: the plan, your own setting, and the platform switch. | Input | Where | Effect | | - | - | - | | Plan | Professional and Enterprise carry the Advisor (`advisor`) and the Opinion, Reasoning and Experience (`ai`). The 14-day evaluation and Starter do not. | A tenant without the entitlement is told so in the product (`not_entitled`) and no model call is spent for it. | | Your setting | **Settings > Engineering assistance**: one switch per capability, admin only, every change audited with who made it | Off means off for everyone in the workspace. Turning the Opinion off turns Reasoning and Experience off with it. | | Platform switch | Operated by ChangeGuard AI, deployment-wide | Used to stop a capability for every workspace in an emergency; the product then shows `unavailable` and your own setting is kept. | Each capability is on by default where the plan carries it; there is nothing to request or enrol in. ## When the model is unavailable Judgments, the CSC Score, Permits, execution and verification make no model call and are unaffected by any model's availability. So is the Engineering Advisor: it is a projection over records the platform already holds (active incidents and the recent change record) and makes no model call. The Opinion, with its Reasoning and Experience, reaches Amazon Bedrock through one router with a preferred model and a permanent, evaluated fallback; when neither can answer, the product says so in plain words and nothing is stored. See [Model availability](https://docs.changeguard.ai/intelligence/model-availability.md). ## Challenge it You are supposed to push back. Every opinion lists the evidence it rests on; the incident conversation records what was observed and decided, in order; a re-run of the pre-flight updates a verdict when reality changed; and an override you make is recorded as evidence against the judgment's track record. See [How ChangeGuard AI makes decisions](https://docs.changeguard.ai/concepts/how-changeguard-decides.md). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.