AI Evidence Trail
See what Graphne asked, read and answered for every AI run, and how people acted on its recommendations.
Requires role: Admin (Evidence tab and the evidence link in reports). Any signed-in user sees the Reasoning panel on their own answers. Related: Multi-Provider AI Configuration | Multi-Agent Intelligence | Investigations | Select Fire | AI Safety Controls
Overview
Every Graphne answer and AI task leaves a record. The record shows which model answered, the exact instructions it received, each graph read it made, what each read returned, and what the model saw. Use it to check an answer, to explain a result to an auditor, or to find out why a run failed.
The Evidence tab on the AI Provider page lists these records. Graphne's Reasoning panel and the investigation report show the same trail in context. When someone acts on a recommendation, GraphnAI also records whether they took it as given, changed it or closed it.
Records are kept for 90 days. The decisions are kept for 7 years in the AI governance audit.
Prerequisites
- Role: Admin, for the Evidence tab and Open evidence.
- AI configured: At least one AI provider. See Multi-Provider AI Configuration.
- Data: Runs made after this feature was installed. Earlier answers have no evidence.
Step-by-step
Find a run in the Evidence tab
- Open AI Provider from the admin menu and select the Evidence tab.
- Filter by run type, outcome, model or date. The list loads more rows as you scroll.
- Select a row to open its flyout.
The tab covers these run types: Chat answer, Explanation, Fix summary, Fix analysis, Investigation, Alert triage, Risk summary and Background analysis.
Outcomes are Answered, From cache, Partial answer, Declined, Blocked, Stopped, Failed and Completed. A stopped run names who or what stopped it.
To see refused queries and fix analysis rows, switch Runs to Other records. Those rows show the refusal rule or the analysis result instead of a run.
To share a view, select Export CSV. It downloads the rows loaded so far, so scroll to load more first.
To link someone to one run, copy the page address after you open its flyout. It ends in ?tab=evidence&run=<id>.
Read a run's chain
The flyout lists the run's steps in order.
- Model call: The provider, the model, the tokens in and out, and how the call ended. A Fallback badge means the first provider failed and the next one answered. Select View instructions to read the exact system prompt sent.
- Tool call: Asked with lists what Graphne passed to the tool. Each graph read sits under a label for how it was built, such as "Graphne's query" or "Built-in query". Returned summarizes the result. What Graphne saw shows the exact text the model received.
- Fingerprints: A fingerprint changes if the data changes. They let you tell whether two reads returned the same data.
- Tasks this started: Links to runs this one launched, such as an investigation started from a chat answer.
If a result contained text that looked like instructions, the step says how many passages Graphne treated as data.
Check an answer in Graphne chat
Any signed-in user can do this for their own answers.
- Ask Graphne a question.
- Open the Reasoning line above the answer.
- Read each step. Asked with shows what Graphne passed to the tool, and the step shows what it returned.
- Read Data from below the steps for the sources Graphne used.
Chat answers show no confidence rating yet.
To read the model's own notes, select Show model reasoning. The notes load on demand. You see the button on your own questions, and Admins see it on any question. If Graphne served your answer from the cache, it was produced by someone else's question. The panel then says the model reasoning isn't shown here.
Graphne never sends these notes back to any model. A model that doesn't share its reasoning shows "This model didn't share its reasoning."
Check how an investigation reached its findings
- Open a finished report from the Investigations page.
- Scroll to How Graphne reached this, below the findings.
- Read the phase steps, the data sources and the confidence meter.
- Admins can select Open evidence to open the run in the Evidence tab and read the model's own notes.
See what people decided
When you run or close a Graphne or fix analysis recommendation in Select Fire, GraphnAI records one of three outcomes:
| Outcome | Meaning |
|---|---|
| Accepted | You ran it as recommended. |
| Modified | You changed it, then ran it. |
| Rejected | You closed it without running it. |
The record names you, the subject and the target. It sits in the AI governance audit for 7 years. A run's evidence flyout lists the decisions made on it under What people did.
Configuration
| Setting | Where | Default |
|---|---|---|
| Evidence retention | Fixed | 90 days |
| Decision retention | Fixed | 7 years |
| Store model reasoning | Server setting | On |
Ask whoever runs your server to turn off the model reasoning setting to stop storing the model's own notes. They're the largest optional part of a record. With the setting off, Show model reasoning says reasoning isn't recorded on this server. Other evidence is unaffected.
Troubleshooting
The Evidence tab says "Couldn't load the evidence"
Select Retry. If it keeps failing, open Platform Health.
The tab shows "No Graphne activity in this range"
Widen the date range or clear the filters. Runs from before this feature was installed have no record, and records older than 90 days are removed.
A run link says it isn't in the record
The run passed its 90-day retention period, or it never existed. Check the run ID.
Show model reasoning says reasoning isn't recorded on this server
The server setting that stores model reasoning is off. Ask whoever runs the server to turn it on. It applies to new answers only.
Show model reasoning doesn't appear
The answer came from the cache for someone else's question, or it has no evidence record. Ask the question again, or open the run in the Evidence tab as an Admin.
Open evidence doesn't appear in a report
Only Admins see it.