# Triage findings with a model of your choice

> Pick a provider, check the setup without sending a finding, run a bounded review in Keryn Web and act on the five verdicts.

Source: https://keryn.dev/docs/guides/triage/

## Goal

Get a second opinion on a long list of findings from a model you chose, inside bounds you can read, and end with decisions that are yours. A verdict is evidence. It closes nothing.

## Try a recorded review

Open [Keryn Web](https://keryn.app) in a fresh browser session. Choose **Demos**, then **Risky AI route**. When the findings appear, select **Investigate with AI** to read the recorded review. The demo uses a built-in sample and needs no model account or credentials.

## Before you start

- A scan result in [Keryn Web](https://keryn.dev/docs/guides/web-app/) with findings. In Keryn Web, triage uses the result in the tab. To triage a saved result from a terminal, see [`keryn ai`](https://keryn.dev/docs/reference/cli/ai/).
- A model you may use for this code. The chosen model receives finding details. A hosted provider receives a short code window only if you select **Include code excerpts** when it is available, and a model running on your machine keeps the request local. If your policy says source code may not go to a hosted model, take the local route in step 1.
- Time to read the [agentic triage](https://keryn.dev/docs/edges/agentic-triage/) page once: it defines the bounds, the five verdicts and what leaves the tab. This guide does not repeat them.

## 1. Choose where the review runs

| You want | Use | Page |
|---|---|---|
| Nothing to leave your machine | a local Ollama server | [Ollama](https://keryn.dev/docs/reference/connectors/ollama/) |
| A hosted model, key kept in the tab | Claude or OpenAI directly | [Claude](https://keryn.dev/docs/reference/connectors/anthropic/), [OpenAI](https://keryn.dev/docs/reference/connectors/openai/) |
| Your cloud's own model service | Azure OpenAI, Amazon Bedrock, Google Gemini | [Azure](https://keryn.dev/docs/reference/connectors/azure/), [Bedrock](https://keryn.dev/docs/reference/connectors/bedrock/), [Gemini](https://keryn.dev/docs/reference/connectors/google/) |
| One gateway for several models | Cloudflare AI Gateway, Vercel AI Gateway, OpenRouter, or any OpenAI-compatible address | [Cloudflare](https://keryn.dev/docs/reference/connectors/cloudflare/), [Vercel](https://keryn.dev/docs/reference/connectors/vercel/), [OpenRouter](https://keryn.dev/docs/reference/connectors/openrouter/), [compatible](https://keryn.dev/docs/reference/connectors/compatible/) |
| The provider key off the page, or a provider that does not answer browsers | a relay you deploy | [Keryn relay](https://keryn.dev/docs/reference/connectors/relay/) |

Each page lists the endpoint, the key header and the fields the connector sends, generated from the product's connector catalog. The full list is the [connectors overview](https://keryn.dev/docs/reference/connectors/).

## 2. Set it up and test it without a finding

Open Settings, Connectors, pick the connector, fill in the fields it asks for (address, model name, key) and press **Test**. Test sends a short fixed message that contains no finding and no code. It tells you whether the address answers and the key is accepted, so you learn about a wrong key or a blocked address before any finding is involved.

The page can reach only the hosts its content security policy lists. If Test fails for a provider that is not on the list, or one that does not allow browser requests, use a [relay](https://keryn.dev/docs/reference/connectors/relay/) on your own account.

## 3. Prepare the result

Triage reviews a limited number of findings per run, errors first and then the highest proof. Make the list worth reviewing before you start:

- Look at the findings at [proof](https://keryn.dev/docs/concepts/proof-ladder/) level 3 and above first: those have a flow you can read yourself.
- Leave out what you have already decided. [Suppressed](https://keryn.dev/docs/guides/suppressions/) findings and inventory entries are never sent.

## 4. Run it

Press **Triage**. A panel names the model, the host and the number of findings that will go, and shows an unchecked **Include code excerpts** box. You can select it only when GitHub lists the repository as public and your organization’s sharing setting allows excerpts. Leave it unchecked to send the [finding details](https://keryn.dev/docs/edges/agentic-triage/#what-leaves-your-machine) without code excerpts. Confirm, or cancel: nothing leaves the tab before you confirm, and every run asks again.

Verdicts appear next to the findings as each batch returns. **Stop** keeps the verdicts received so far.

![The Investigate with AI panel of Keryn Web with no model configured: a recorded example review of a pinned public repository, labelled as recorded with no live model run and nothing sent, and a Configure a model button.](https://keryn.dev/screens/web-triage-1280-light.webp)

*Before a model is configured, Investigate with AI shows recorded example reviews and sends nothing; once a model is set in Connectors, Triage opens the panel described above.. Taken from keryn.app main-DIcUUbkq.js.*

## 5. Read the verdicts

| Verdict | What to do |
|---|---|
| upheld | Read the grounds. If they quote the line you would have quoted, the review agrees with you. If not, the verdict is not worth more than the finding. |
| refuted | The model thinks the details it received contradict the finding. Check the grounds and the relevant code. If you verify the control, record your decision with a [suppression](https://keryn.dev/docs/guides/suppressions/) that names it. |
| needs context | Read what is missing (the caller, the function outside the window). Supply it by widening the question yourself, or settle it by reading the code. This is a common and correct answer. |
| unsupported | The window neither supports nor contradicts the finding. Treat it as no information. |
| declined | The model would not judge it, or answered outside the five verdicts. Nothing was recorded as a verdict beyond that. |

Confidence is the number the model stated, not a measurement. A verdict never changes a finding's proof level, its severity, the gate or the exit code.

## 6. Keep the result, if you want it kept

Verdicts live in the tab with the result. To keep them with the findings, send both to a store you run: see [Supabase and FalkorDB export](https://keryn.dev/docs/guides/export-stores/). The verdict, its grounds and its fix travel as separate fields and the proof level as its own, unchanged.

## What you just proved

The edge here runs from your findings to a model, and it is the only place a finding can leave the page. You set its destination, you saw the list it carries, and you pressed the button. The boundary held because it has four hand-offs, each one yours: the connector you configured, the host the panel named, the code window you left ticked or not, and the confirmation. If you used a local model, nothing crossed the machine at all.

## Next

- The rules of the game: [agentic triage](https://keryn.dev/docs/edges/agentic-triage/).
- Write the decision down: [suppressions with a justification](https://keryn.dev/docs/guides/suppressions/).
- Keep the result: [Supabase and FalkorDB export](https://keryn.dev/docs/guides/export-stores/).
