How to use the Eval review board template

Start a board from it
Use this template opens a new Freero board with the Eval review board template on it (sign up free first). On a board you already have, open Templates in the toolbar and search for “Eval review board”.
Follow the instruction on the board
“Review failures together before changing anything. Group them by cause: a pattern of five beats a fix for one.”
Fill in each part
- Table Columns: Case · Input · What good looks like · What it said · Verdict
- Rubric What every answer is judged on, in this order.
Bring your team and your agents
Invite people to the board or share a link, and work on it together live. The timer is in the top bar, private mode and voting in the board menu, and Claude or ChatGPT can join through Freero’s MCP server.

Work on it with an AI agent

Connect an assistant once and it works on the board with you, with your permissions: by default it reads and proposes, and people decide.

You ask: “Fill in the Eval review board board from these notes.”
What happens It reads the board, then proposes sticky notes for it. Nothing changes until someone on the board accepts them.
You ask: “Group what we wrote into themes and list the actions.”
What happens It proposes clusters with a title each and task cards for the actions, labelled with its name and yours.

Agent control room: A board where AI agents post their plan, status and tasks, and people steer them.

Golden test set
Build the set of test cases an AI feature must pass: realistic inputs, the expected answer, tags and why each case matters.
Prompt iteration log
Keep track of how a prompt evolves: each version, what changed, how it did on your test cases and whether to keep it.
Model option comparison
Compare AI model or tool options for one job on quality, cost, speed, privacy and fit, using your own test cases.
Agent run review
Step through one run of an AI agent: what it did at each step, whether it was right, and what to change in its instructions or tools.
AI pilot plan
Run a small, honest pilot of an AI tool: the job it should do, the baseline, a test group, what you measure and the decision at the end.
Agent permissions review
Decide what an AI agent may do on its own, what needs a person’s approval and what it must never do, action by action.