# How to boost an office, web or coding agent on WorkBuddy tasks with harness2

Repo: [google-research/harness2](https://github.com/google-research/harness2) | Difficulty: Advanced | Time: 2 hours | Basis: Seen in the wild

Refine an agent's harness on one WorkBuddy-Bench subset to see if office, web or code results improve.

**Who it is for:** Builder of an internal assistant that edits documents, browses, or writes code and wants a measurable harness upgrade

**The problem:** Hand-tuning prompts for office, web and code tasks is guesswork with no consistent score to compare against.

**The outcome:** A judged WorkBuddy run for one subset showing whether a Propose-Probe-Compose step beat the base harness.

## Steps

1. Install the benchmark (needs Docker): harness2-setup wb
2. Check prerequisites: harness2-check --bench wb --subset office
3. Refine one task (inferred, adapting the LAB example to WorkBuddy): harness2 --bench wb --subset office --k 1 --mode parallel --max-tasks 1
4. Judge and report with matching flags: harness2-judge --bench wb --subset office --k 1 --mode parallel
5. Read the report: harness2-report --bench wb --subset office --k 1 --mode parallel

## Prompt to paste into your agent

```text
In google-research/harness2, set up WorkBuddy-Bench with harness2-setup wb and run one task from --subset office with --k 1 --mode parallel, then judge and report with identical flags. Verify Docker is running first and that the subset flag is passed on every command after setup.
```

## Caveat

WorkBuddy-Bench needs Docker and the --subset flag on every command after setup, and the README guide for WorkBuddy should be checked for the exact task-selection flags before running.

## Seen in the wild

- X (Oct 2026): https://x.com/i/web/status/2112341275932586114

Dual-use notice: only use this on software, sites and systems you own or are authorized to test.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/google-research-harness2/improve-office-web-code-agent-workbuddy/