ResearchNode tools · Product preview

PokeAIAI security testing,
with the evidence in view.

A local workbench for assessing chatbots, retrieval systems, AI agents and MCP connections. Plan a test, follow what happened and review the evidence in one project.

The assessment, at a glance.

PokeAI / Project overview
PokeAI dark project overview showing run history, findings and assessment scope
Project overview · A synthetic teaching sampleView full size ↗: PokeAI dark project overview showing run history, findings and assessment scope

The images on this page show the supplied interface preview and local teaching sample. The example finding illustrates the workflow; it is not a result from a customer system.

The tool

Test the application around the model.

PokeAI is the desktop experience built on the AdverScope assessment framework. It connects test configuration, recorded interactions and human review.

01 / Conversations

Chatbots & APIs

Explore prompt injection and information disclosure through browser chatbots or supported API connections. Keep each probe with the response it produced.

02 / Context

Retrieval & content

Assess how retrieved documents and other external content influence a system. Compare test behavior with legitimate tasks and inspect the supporting records.

03 / Actions

Agents & MCP

Examine tool access, permissions and multi-step actions using configured targets and evidence checks. Available coverage depends on the target and its integrations.

01 / Set up

Start with a project.

Create a new assessment or reopen an existing one. Project records, settings and evidence stay organized together in your chosen workspace.

Guided setup connects your planning model and target, records permission and limits, and lets you review the plan before a run. A built-in sample introduces the workflow without connecting a live target.

PokeAI welcome screen with New project and Open project
A clear starting point for each assessmentView full size ↗: PokeAI welcome screen with New project and Open project

02 / Test and review

From an observation to an explainable finding.

A result is the beginning of the review. Follow the conversation, inspect the retained evidence and decide what needs action.

Keep the conclusion tied to the test.

Review the evidence before accepting a finding or exporting a report. An uncertain or untested check does not establish that a system is secure. PokeAI remains a beta tool for controlled, authorized assessments.

PokeAI project overview in light mode
The same workspace, in light modeView full size ↗: PokeAI project overview in light mode

03 / Work your way

One workflow.
A choice of appearance.

The desktop app offers light, dark and system appearance, with the same project history, findings and scope in each view.

Project records are stored locally. Model-assisted work can use a local model or an approved remote provider; the selected connection determines where model requests are processed.

Continue exploring

Learn the method. Practise in the lab.

Pair the workbench with ResearchNode’s AI security explanations and Project 2501’s hands-on exercises.