# Share a W&B Weave Evaluation — A Link Without a Weights & Biases Seat

Canonical: https://commareports.com/agents/share-weave-eval-report
Published: 2026-09-12

> Weave keeps evaluations inside a W&B project. Export the comparison table to HTML and publish it to Comma so reviewers without a seat can read the scores and comment on the rows.

# Share a W&B Weave evaluation

Weave's evaluation view is genuinely good, and it lives inside a Weights &
Biases project. Every person who needs to read it needs a seat in that
project — which is fine for the ML team and absurd for the one domain expert
who can tell you whether answer 14 is actually wrong.

## Export the evaluation rows

```python
import weave, pandas as pd

client = weave.init("support-agent")

rows = []
for call in client.get_calls(filter={"op_names": ["Evaluation.predict_and_score"]}):
    rows.append({
        "input": call.inputs.get("example", {}).get("question"),
        "output": (call.output or {}).get("model_output"),
        **{k: v for k, v in ((call.output or {}).get("scores") or {}).items()},
    })

pd.DataFrame(rows).to_html("weave-eval.html", index=False, float_format="%.3f", escape=True)
```

Publish the file — drag it into [the app](https://commareports.com/), or from
the job that ran the eval:

```bash
curl -fsS -X PATCH "https://commareports.com/api/v1/reports/$REPORT_ID" \
  -H "Authorization: Bearer $COMMA_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d "$(jq -n --rawfile html weave-eval.html \
        --arg title "Support agent eval — $(date +%F)" '{title: $title, html: $html}')"
```

## What you get that a project invite does not give you

- **Anchored threads** — the objection lands on the row it is about. See
  [commenting on HTML](/comment-on-html).
- **Revisions** — one report id per suite, one revision per run, no dashboard
  to build.
- **Access per report** — private, team-only, or domain-gated, decided per
  report rather than per project. See the [sharing model](/docs/sharing).

## Close the loop with the agent

Reviewer corrections are the highest-value training data you will get this
quarter. An agent can read them back through [the MCP server](/docs/mcp) and
fold them into the eval set —
[let an agent respond to comments](/agents/let-an-agent-respond-to-comments).

## Limits

- **Entry HTML: 5 MB.** Model outputs dominate the size; truncate them or
  export per scorer.
- **Assets: 25 MB per file, 250 MB and 500 files per report.**
- **60 requests/minute per token.**

## Try it

Comma is free — unlimited reports, unlimited commenters, unlimited revision
history.

**[Publish an eval report →](https://commareports.com/)**

### Related

- [Share a W&B report](/share-wandb-report) · [Share an LLM eval report](/agents/share-llm-eval-report)
- [Share a Braintrust eval report](/agents/share-braintrust-eval-report) · [Share a Ragas evaluation report](/agents/share-ragas-eval-report)
- [Share a TensorBoard report](/share-tensorboard-report) · [Publish from CI](/docs/ci)